Volume
OASIcs, Volume 125
35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)
-
Part of:
Series:
Open Access Series in Informatics (OASIcs)
Conference: International Conference on Principles of Diagnosis and Resilient Systems (DX)
Event
DX 2024, November 4-7, 2024, Vienna, AustriaEditors
Publication Details
- published at: 2024-11-26
- Publisher: Schloss Dagstuhl – Leibniz-Zentrum für Informatik
- ISBN: 978-3-95977-356-0
Access Numbers
- Detailed Access Statistics available here
-
Total Document Accesses (updated on a weekly basis):
0PDF Downloads
Documents
No documents found matching your filter selection.
Document
Complete Volume
OASIcs, Volume 125, DX 2024, Complete Volume
Abstract
OASIcs, Volume 125, DX 2024, Complete Volume
Cite as
35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 1-534, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@Proceedings{pill_et_al:OASIcs.DX.2024,
title = {{OASIcs, Volume 125, DX 2024, Complete Volume}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {1--534},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024},
URN = {urn:nbn:de:0030-drops-222256},
doi = {10.4230/OASIcs.DX.2024},
annote = {Keywords: OASIcs, Volume 125, DX 2024, Complete Volume}
}
Document
Front Matter
Front Matter, Table of Contents, Preface, Conference Organization
Abstract
Front Matter, Table of Contents, Preface, Conference Organization
Cite as
35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 0:i-0:xvi, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{pill_et_al:OASIcs.DX.2024.0,
author = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
title = {{Front Matter, Table of Contents, Preface, Conference Organization}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {0:i--0:xvi},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.0},
URN = {urn:nbn:de:0030-drops-222242},
doi = {10.4230/OASIcs.DX.2024.0},
annote = {Keywords: Front Matter, Table of Contents, Preface, Conference Organization}
}
Document
A Hierarchical Monitoring and Diagnosis System for Autonomous Robots
Abstract
This paper addresses the capability of autonomous robots to achieve flexible goals in dynamic environments. In such a setting numerous challenges jeopardize the robustness of such systems. Thus, we propose a hierarchical diagnosis concept for layered control architectures, that can detect and deal with such challenges to maintain a consistent knowledge about the world and to allow reliable decision-making. Layered control systems use various knowledge representations and decision-making mechanisms teamed with specialized isolated fault-handling approaches. However, some issues can only be identified if the information from different layers is combined. Our approach addresses challenges like failing actions, uncertain observations, and unmodeled events by propagating observations and diagnoses results throughout the hierarchy. This enhances adaptability and dependability in various domains. In this paper, we present a prototype architecture following this approach.
Cite as
Gerald Steinbauer-Wagner, Leo Fürbaß, Marco De Bortoli, and Louise Travé-Massuyès. A Hierarchical Monitoring and Diagnosis System for Autonomous Robots. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 1:1-1:9, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{steinbauerwagner_et_al:OASIcs.DX.2024.1,
author = {Steinbauer-Wagner, Gerald and F\"{u}rba{\ss}, Leo and De Bortoli, Marco and Trav\'{e}-Massuy\`{e}s, Louise},
title = {{A Hierarchical Monitoring and Diagnosis System for Autonomous Robots}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {1:1--1:9},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.1},
URN = {urn:nbn:de:0030-drops-220938},
doi = {10.4230/OASIcs.DX.2024.1},
annote = {Keywords: Cognitive Architecture, Autonomous Agents, Dependability, Hierarchical Monitoring and Diagnosis}
}
Document
A Model-Based Approach for Monitoring and Diagnosing Digital Twin Discrepancies
Abstract
Recent decades have seen the increasing use of Digital Twins (DTs) - that is, digital models used over the lifetime of a physical product or system for tasks such as predictive maintenance or optimization - in a number of domains such as buildings, manufacturing, or design. DTs face a challenge known as the DT synchronization problem; a DT, often based on machine-learned, or complex simulation models, needs to adequately mirror the physical product or system at all times, as any deviations might affect the quality of predictions or control actions. In this paper, we present a model-based approach that aims to add a level of awareness to DT models by supervising if they are in sync with the physical counterpart. The approach is agnostic to the type of models used in the DT, as long as they are compositional, and based on monitoring critical properties (behavioral or functional aspects) of the system at run-time. In the case violations are detected, it reasons on the DT’s structure to localize and identify parts of the model that cause deviations and need to be adapted. We give a formal description and an implementation of this approach, and illustrate it with an example from building climatisation.
Cite as
Elaheh Hosseinkhani, Martin Leucker, Martin Sachenbacher, Hendrik Streichhahn, and Lars B. Vosteen. A Model-Based Approach for Monitoring and Diagnosing Digital Twin Discrepancies. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 2:1-2:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{hosseinkhani_et_al:OASIcs.DX.2024.2,
author = {Hosseinkhani, Elaheh and Leucker, Martin and Sachenbacher, Martin and Streichhahn, Hendrik and Vosteen, Lars B.},
title = {{A Model-Based Approach for Monitoring and Diagnosing Digital Twin Discrepancies}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {2:1--2:15},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.2},
URN = {urn:nbn:de:0030-drops-220944},
doi = {10.4230/OASIcs.DX.2024.2},
annote = {Keywords: Digital Twins, Runtime Verification, Diagnosis, FDIR, TeSSLa}
}
Document
A Review of Fault Diagnosis Techniques Applied to Aircraft Air Data Sensors
Abstract
Air data sensors provide essential measurements to ensure the availability of autopilot and to maintain aircraft performance, flight envelope protection and optimal aerodynamic surfaces control laws. The importance of these sensors imply the existence of embedded fault tolerance features, mainly represented by hardware redundancy. The latter is prone to fail in case of common fault of multiple sensors, especially if the faults are coherent and simultaneous. Increasing the robustness of fault detection and isolation (FDI) techniques for air data sensors to the aforementioned conditions is essential for the development of more autonomous aircraft, reducing crew workload and guaranteeing flight protections under adverse conditions. This paper reviews recent works on Air Data System (ADS) FDI, assessing proposed model, data and signal-driven approaches. We finally argue in favor of data-driven and hybrid approaches for the development of virtual sensors and semi-supervised anomaly detectors, offering an overview of ways forward.
Cite as
Lucas Lima Lopes, Louise Travé-Massuyès, Carine Jauberthie, and Guillaume Alcalay. A Review of Fault Diagnosis Techniques Applied to Aircraft Air Data Sensors. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 3:1-3:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{limalopes_et_al:OASIcs.DX.2024.3,
author = {Lima Lopes, Lucas and Trav\'{e}-Massuy\`{e}s, Louise and Jauberthie, Carine and Alcalay, Guillaume},
title = {{A Review of Fault Diagnosis Techniques Applied to Aircraft Air Data Sensors}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {3:1--3:20},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.3},
URN = {urn:nbn:de:0030-drops-220957},
doi = {10.4230/OASIcs.DX.2024.3},
annote = {Keywords: air data, FDI, aeronautics, review, survey, diagnostics, fault}
}
Document
A Study on Redundancy and Intrinsic Dimension for Data-Driven Fault Diagnosis
Abstract
Data-driven fault diagnosis of technical systems use training data from nominal and faulty operation to train machine learning models to detect and classify faults. However, data-driven fault diagnosis is complicated by the fact that training data from faults is scarce. The fault diagnosis task is often treated as a standard classification problem. There is a need for methods to design fault detectors using only nominal data. In model-based diagnosis, the ability construct fault detectors depends on analytical redundancy properties. While analytical redundancy is a model property, it describes the diagnosability properties of the system. In this work, the connection between analytical redundancy and the distribution of observations from the system on low-dimensional manifolds in the observation space is studied. It is shown that the intrinsic dimension can be used to identify signal combinations that can be used for constructing residual generators. A data-driven design methodology is proposed where data-driven residual generators candidates are identified using the intrinsic dimension. The method is evaluated using two case studies: a simulated model of a two-tank system and data collected from a fuel injection system. The results demonstrate the ability to diagnose abnormal system behavior and reason about its cause based on selected signal combinations.
Cite as
Daniel Jung and David Axelsson. A Study on Redundancy and Intrinsic Dimension for Data-Driven Fault Diagnosis. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 4:1-4:17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{jung_et_al:OASIcs.DX.2024.4,
author = {Jung, Daniel and Axelsson, David},
title = {{A Study on Redundancy and Intrinsic Dimension for Data-Driven Fault Diagnosis}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {4:1--4:17},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.4},
URN = {urn:nbn:de:0030-drops-220964},
doi = {10.4230/OASIcs.DX.2024.4},
annote = {Keywords: Data-driven diagnosis, intrinsic dimension, model-based diagnosis, structural methods}
}
Document
Bridging Hardware and Software Diagnosis: Leveraging Fault Signature Matrix and Spectrum-Based Fault Localization Similarities
Abstract
This paper examines two prominent Fault Detection and Isolation methodologies: the Signature Matrix approach, traditionally used in hardware systems, and the Spectrum-based approach, applied in software fault localization. Despite their distinct operational domains, both methods share the objective of precisely identifying and isolating faults. This study aims to compare these approaches and to highlight their similarities in principle. Through a comparative analysis, we assess how the structured pattern recognition of the Signature Matrix method and the statistical analysis capabilities of the Spectrum-based approach can be synergized to enhance diagnostic processes of cyber-physical systems that are composed of both hardware and software components. The investigation is motivated by the prospect of developing a hybrid Fault Detection and Isolation strategy that incorporates the robust detection mechanisms of hardware diagnostics with the techniques used in software fault localization. The findings are intended to advance the theoretical framework of Fault Detection and Isolation systems and suggest practical implementations across varied technological platforms, thereby improving the reliability and efficiency of fault detection and isolation in both hardware and software contexts.
Cite as
Louise Travé-Massuyès and Franz Wotawa. Bridging Hardware and Software Diagnosis: Leveraging Fault Signature Matrix and Spectrum-Based Fault Localization Similarities. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 5:1-5:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{travemassuyes_et_al:OASIcs.DX.2024.5,
author = {Trav\'{e}-Massuy\`{e}s, Louise and Wotawa, Franz},
title = {{Bridging Hardware and Software Diagnosis: Leveraging Fault Signature Matrix and Spectrum-Based Fault Localization Similarities}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {5:1--5:15},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.5},
URN = {urn:nbn:de:0030-drops-220972},
doi = {10.4230/OASIcs.DX.2024.5},
annote = {Keywords: Diagnosis, Fault detection and identification, Software debugging}
}
Document
Challenges for Model-Based Diagnosis
Abstract
Since the seminal works by Reiter and de Kleer and Williams published in the late 80’s, Model-based Diagnosis has been a significant area of research. This has been motivated by the fact that MBD assists us in tackling a challenge that we face almost on a daily basis, i.e., by MBD allowing us to reason in a structured manner about the root causes for some encountered problem. MBD achieves this in an intuitive, complete and sound way, based on the central idea of investigating the compliance of some observed behavior with a model that describes how a system should behave - given this or that input scenario and parameter set. Over the last 40 years, MBD has been adopted for a multitude of applications, and we saw the emergence of a diverse set of algorithmic, optimizations, as well as extensions to the initial theoretical concepts.We argue that MBD remains highly relevant, with numerous scientific challenges to tackle as we face increasingly complex diagnostic problems. We discuss several such challenges and suggest related topics for PhD theses that have the potential to significantly contribute to the state-of-the-art in MBD research.
Cite as
Ingo Pill and Johan de Kleer. Challenges for Model-Based Diagnosis. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 6:1-6:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{pill_et_al:OASIcs.DX.2024.6,
author = {Pill, Ingo and de Kleer, Johan},
title = {{Challenges for Model-Based Diagnosis}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {6:1--6:20},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.6},
URN = {urn:nbn:de:0030-drops-220983},
doi = {10.4230/OASIcs.DX.2024.6},
annote = {Keywords: Model-based Diagnosis, Diagnosis, Algorithms}
}
Document
Design Principles for Falsifiable, Replicable and Reproducible Empirical Machine Learning Research
Abstract
Machine learning is becoming increasingly important in the diagnosis and planning fields, where data-driven models and algorithms are being employed as alternatives to traditional first-principle approaches. Empirical research plays a fundamental role in the machine learning domain. At the heart of impactful empirical research lies the development of clear research hypotheses, which then shape the design of experiments. The execution of experiments must be carried out with precision to ensure reliable results, followed by statistical analysis to interpret these outcomes. This process is key to either supporting or refuting initial hypotheses. Despite its importance, there is a high variability in research practices across the machine learning community and no uniform understanding of quality criteria for empirical research. To address this gap, we propose a model for the empirical research process, accompanied by guidelines to uphold the validity of empirical research. By embracing these recommendations, greater consistency, enhanced reliability and increased impact can be achieved.
Cite as
Daniel Vranješ, Jonas Ehrhardt, René Heesch, Lukas Moddemann, Henrik Sebastian Steude, and Oliver Niggemann. Design Principles for Falsifiable, Replicable and Reproducible Empirical Machine Learning Research. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 7:1-7:13, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{vranjes_et_al:OASIcs.DX.2024.7,
author = {Vranje\v{s}, Daniel and Ehrhardt, Jonas and Heesch, Ren\'{e} and Moddemann, Lukas and Steude, Henrik Sebastian and Niggemann, Oliver},
title = {{Design Principles for Falsifiable, Replicable and Reproducible Empirical Machine Learning Research}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {7:1--7:13},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.7},
URN = {urn:nbn:de:0030-drops-220991},
doi = {10.4230/OASIcs.DX.2024.7},
annote = {Keywords: machine learning, hypothesis design, research design, experimental research, statistical testing, diagnosis, planning}
}
Document
Diagnosing Multi-Agent STRIPS Plans
Abstract
The increasing use of multi-agent systems demands that many challenges be addressed. One such challenge is diagnosing failed multi-agent plan executions, sometimes in system setups where the different agents are not willing to disclose their private actions. One formalism for generating multi-agent plans is the well-known MA-STRIPS formalism. While there have been approaches for delivering as robust plans as possible, we focus on the plan execution stage. Specifically, we address the problem of diagnosing plans that failed their execution. We propose a Model-Based Diagnosis approach to solve this problem. Given an MA-STRIPS problem, a plan that solves it, and an observation that indicates execution failure, we define the MA-STRIPS diagnosis problem. We compile that problem into a boolean satisfiability problem (SAT) and then use an off-the-shelf SAT solver to obtain candidate diagnoses. We further expand this approach to address privacy by proposing a distributed algorithm that can find these same diagnoses in a decentralized manner. Additionally, we propose an enhancement to the distributed algorithm that uses information generated during the diagnosis process to provide significant speedups. We found that the improved algorithm runs more than 10 times faster than the basic decentralized version and, in one case, runs faster than the centralized algorithm.
Cite as
Avraham Natan, Roni Stern, Meir Kalech, William Yeoh, and Tran Cao Son. Diagnosing Multi-Agent STRIPS Plans. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 8:1-8:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{natan_et_al:OASIcs.DX.2024.8,
author = {Natan, Avraham and Stern, Roni and Kalech, Meir and Yeoh, William and Son, Tran Cao},
title = {{Diagnosing Multi-Agent STRIPS Plans}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {8:1--8:20},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.8},
URN = {urn:nbn:de:0030-drops-221001},
doi = {10.4230/OASIcs.DX.2024.8},
annote = {Keywords: Model-based diagnosis, Multi-agent systems, Distributed diagnosis, Privacy}
}
Document
Inferring Sensor Placement Using Critical Pairs and Satisfiability Modulo Theory
Abstract
Industrial fault diagnosis exhibits the perennial problem of reasoning with partial and real-valued information. This is mainly due to the fact that in real-world applications, industrial systems are only instrumented insofar, as sensor information is required for their functioning. However, such instrumentation leaves out much information that would be useful for fault diagnosis. This is problematic since consistency-based fault diagnosis uses available information and computes intermediate values within a system description. These values are then used to compare expected normal behaviour to actual observed values. In the past, this was done only for Boolean circuits. Recently, satisfiability modulo non-linear arithmetic (SMT) formulations have been developed that allow the calculation of real values, instead of only Boolean ones. Leveraging those formulations, we in this article present a novel method to infer missing sensor values using an SMT system description and the notion of critical pairs. We show on a running example and also empirically that we can infer novel measurements for five process industrial systems. We conclude that, although SMT calculations accumulate some error, we can infer novel optimal measurements for all systems.
Cite as
Alexander Diedrich, René Heesch, Marco Bozzano, Björn Ludwig, Alessandro Cimatti, and Oliver Niggemann. Inferring Sensor Placement Using Critical Pairs and Satisfiability Modulo Theory. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 9:1-9:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{diedrich_et_al:OASIcs.DX.2024.9,
author = {Diedrich, Alexander and Heesch, Ren\'{e} and Bozzano, Marco and Ludwig, Bj\"{o}rn and Cimatti, Alessandro and Niggemann, Oliver},
title = {{Inferring Sensor Placement Using Critical Pairs and Satisfiability Modulo Theory}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {9:1--9:19},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.9},
URN = {urn:nbn:de:0030-drops-221013},
doi = {10.4230/OASIcs.DX.2024.9},
annote = {Keywords: Sensor Placement, Satisfiability Modulo Theory, Critical Pairs, Diagnosability}
}
Document
Leveraging Answer Set Programming for Continuous Monitoring, Fault Detection, and Explanation of Automated and Autonomous Driving Systems
Abstract
Recent advancements in automated and autonomous driving systems have facilitated their integration into modern vehicles, enabling them to accurately perceive their surroundings and support or even fully undertake complex driving tasks. Given the complexity and unpredictable nature of driving environments and traffic situations, ensuring the correct behavior of such systems is essential to prevent hazardous situations, increase user acceptance, and avoid human harm. However, the increased complexity of these systems and the extensive search space of possible scenarios introduce significant challenges to testing and real-time fault management. Hence, besides rigorous testing during the development phase, there is a need for additional validation and verification during operation. This paper proposes utilizing Answer Set Programming (ASP), a form of declarative programming, for continuous real-time monitoring, fault detection, and explanation to ensure the correct functioning of automated and autonomous driving systems. Our approach aims to enhance the reliability and safety of such systems by detecting violations and providing explanations that can support fault-adaptive control or mitigation strategies. We demonstrate the effectiveness of our methodology across diverse scenarios executed within a simulation environment, discuss the main challenges encountered, and outline future research directions.
Cite as
Lorenz Klampfl and Franz Wotawa. Leveraging Answer Set Programming for Continuous Monitoring, Fault Detection, and Explanation of Automated and Autonomous Driving Systems. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 10:1-10:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{klampfl_et_al:OASIcs.DX.2024.10,
author = {Klampfl, Lorenz and Wotawa, Franz},
title = {{Leveraging Answer Set Programming for Continuous Monitoring, Fault Detection, and Explanation of Automated and Autonomous Driving Systems}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {10:1--10:20},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.10},
URN = {urn:nbn:de:0030-drops-221023},
doi = {10.4230/OASIcs.DX.2024.10},
annote = {Keywords: Autonomous Driving, Answer Set Programming, Continuous Monitoring}
}
Document
Leveraging Causal Information for Multivariate Timeseries Anomaly Detection
Abstract
Anomaly detection in multivariate timeseries is used in various domains, such as finance, IT, or aerospace, to identify irregular behavior in the used applications. Prior research in anomaly detection has focused on estimating the joint probability of all variables. Then, anomalies are scored based on the probability they receive. Thereby, the variables' dependencies are only considered implicitly. This work follows recent work in anomaly detection that integrates information about the causal relations between the variables in the timeseries into the detection mechanism. The causal mechanisms of the variables are then used to identify anomalies. An observation is identified as anomalous if at least one of the variables it contains deviates from its regular causal mechanism. These regular causal mechanisms are estimated via the conditional distribution of a variable given its causal parent variables, i.e., the variables having a causal influence on a variable. We further develop previous work by gathering information about the causal parents of the variables by applying causal discovery algorithms adapted to the timeseries setting. We apply Conditional Kernel Density Estimation and Conditional Variational Autoencoders to estimate the conditional probabilities. With this causal approach, we outperform methods that rely on the joint probability of the variables in our synthetically generated datasets and the C-MAPPS dataset, which provides simulation data of turbofan engines. Moreover, we investigate the causal approach’s inferred scores on the C-MAPPS dataset to gather insights into the measurements responsible for the prediction of anomalies. Furthermore, we investigate the influence of deviations from the true causal graph on the anomaly detection performance using synthetic data.
Cite as
Lukas Heppel, Andreas Gerhardus, Ferdinand Rewicki, Jan Deeken, and Günther Waxenegger-Wilfing. Leveraging Causal Information for Multivariate Timeseries Anomaly Detection. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 11:1-11:18, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{heppel_et_al:OASIcs.DX.2024.11,
author = {Heppel, Lukas and Gerhardus, Andreas and Rewicki, Ferdinand and Deeken, Jan and Waxenegger-Wilfing, G\"{u}nther},
title = {{Leveraging Causal Information for Multivariate Timeseries Anomaly Detection}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {11:1--11:18},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.11},
URN = {urn:nbn:de:0030-drops-221034},
doi = {10.4230/OASIcs.DX.2024.11},
annote = {Keywords: Anomaly Detection, Causal Discovery, Multivariate Timeseries}
}
Document
Minimalist Diagnosis of Discrete-Event Systems
Abstract
Model-based diagnosis of discrete-event systems (DESs) is afflicted by two major difficulties, the former being the huge size of the search space, which has a heavy impact on the processing time, the latter being a possibly large number of diagnoses explaining the perceived sequence of observations, which may cause a cognitive overload in human diagnosticians or even delays in post-processing. These difficulties add up and they are exacerbated in critical scenarios where an action must be taken in real-time. To make DES diagnosis viable in these contexts, a Minimalist Diagnosis Engine is presented, which is based on a parsimony principle: instead of computing the set of all diagnoses inherent to the given sequence of observations, only minimal diagnoses are elicited as candidates. Since in this paper, as in most contributions on model-based diagnosis of DESs in the literature, a diagnosis is defined as a set of faults, minimal diagnoses are subset minimal. The proposal is justified since minimal diagnoses are suitable for DESs, and since the new diagnosis engine is able to prune the search space, thus reducing the computation effort with respect to a sound and complete method. Moreover, in order to further decrease the execution time, whenever the method is dealing with a new observation, it performs online a (partial) knowledge-compilation so as the portions of the DES space that have already been processed and transformed into chunks of compiled knowledge can speed up the next abductive reasoning steps, relevant to the upcoming observations.
Cite as
Gianfranco Lamperti and Marina Zanella. Minimalist Diagnosis of Discrete-Event Systems. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 12:1-12:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{lamperti_et_al:OASIcs.DX.2024.12,
author = {Lamperti, Gianfranco and Zanella, Marina},
title = {{Minimalist Diagnosis of Discrete-Event Systems}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {12:1--12:20},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.12},
URN = {urn:nbn:de:0030-drops-221046},
doi = {10.4230/OASIcs.DX.2024.12},
annote = {Keywords: model-based reasoning, diagnosis during monitoring, discrete-event systems, active systems, subset-minimal diagnosis, dynamical knowledge-compilation, minimalism, laziness}
}
Document
MSO Sets and MTES for Dummies
Abstract
Structural analysis-based diagnosis allows for the extraction of a wealth of information and properties by studying a structural model that represents a physical system. This diagnosis approach is centered on structurally overdetermined sets, which enable the generation of residuals for fault detection and isolation. As the 'for Dummies' editorial collection, this article aims at taking on complex concepts and making them easy to understand. It aims to clarify and compare key concepts in structural analysis, focusing on Minimally Structurally Overdetermined (MSO) sets and Minimal Test Equation Supports (MTES). Additionally, we explain and illustrate the Dulmage-Mendelsohn decomposition, which helps identify structurally overdetermined parts of the system and plays a important role in the structural analysis process. Through detailed exploration and practical examples, we demonstrate the roles, applications, and interrelations of these sets, highlighting their respective strengths and limitations. The paper provides an overview of the algorithms used to identify and use these sets, including a theoretical and practical comparison of their computational efficiency and diagnostic capabilities.
Cite as
Maxence Glotin, Louise Travé-Massuyès, and Elodie Chanthery. MSO Sets and MTES for Dummies. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 13:1-13:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{glotin_et_al:OASIcs.DX.2024.13,
author = {Glotin, Maxence and Trav\'{e}-Massuy\`{e}s, Louise and Chanthery, Elodie},
title = {{MSO Sets and MTES for Dummies}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {13:1--13:15},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.13},
URN = {urn:nbn:de:0030-drops-221054},
doi = {10.4230/OASIcs.DX.2024.13},
annote = {Keywords: Structural analysis, MTES, MSO sets}
}
Document
One-Class Classification and Cluster Ensembles for Anomaly Detection and Diagnosis in Multivariate Time Series Data
Abstract
Real-world automated systems such as building automation, power plants, and more have benefited from data-driven learning methodologies for anomaly detection and diagnosis. Typically, these methodologies heavily rely on prior knowledge related to abnormal operations, i.e., data points labeled as anomalies. However, in practice, such labelled data points are often unavailable which poses challenges in effective anomaly detection, particularly in diagnosis. In this paper, we propose One-class Classification Cluster ENsembles (OCCEN) anomaly detection and diagnosis approach for multivariate time series data. OCCEN utilizes one-class classification learning methods for anomaly detection followed by the decomposition of anomalies into multiple clusters. Then each cluster is treated as a binary classification problem and classifiers are trained to learn cluster representations. These trained models in combination with explainable AI models are used to generate a ranked list of diagnoses, i.e., features. Finally, we re-rank those features to account for temporal dependencies through the dynamic time-warping technique. The practical evaluation of OCCEN for air handling units (AHU) demonstrates its effectiveness in identifying faults. The framework consistently outperforms the baseline in fault diagnosis, as higher scores are observed for detection and diagnostic evaluation metrics, including F1 score, intersection over union, HitRate@k, and RootCause@k.
Cite as
Adil Mukhtar, Thomas Hirsch, and Gerald Schweiger. One-Class Classification and Cluster Ensembles for Anomaly Detection and Diagnosis in Multivariate Time Series Data. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 14:1-14:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{mukhtar_et_al:OASIcs.DX.2024.14,
author = {Mukhtar, Adil and Hirsch, Thomas and Schweiger, Gerald},
title = {{One-Class Classification and Cluster Ensembles for Anomaly Detection and Diagnosis in Multivariate Time Series Data}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {14:1--14:19},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.14},
URN = {urn:nbn:de:0030-drops-221064},
doi = {10.4230/OASIcs.DX.2024.14},
annote = {Keywords: Anomaly Detection and Diagnosis, Machine Learning, Explainable AI, One-class Classification}
}
Document
Property Learning-Based Fault Detection for Liquid Propellant Rocket Engine Control Systems
Abstract
Accommodating the dynamic and uncertain operational environments that are typical for aerospace applications, our work focuses on robust fault detection and accurate diagnosis in the context of Liquid Propellant Rocket Engines. To this end, we employ techniques based on learning temporal properties which are then dynamically adapted and refined based on observed behavior. Leveraging the capabilities of genetic programming, our methodology evolves and optimizes temporal properties that are validated through formal methods in order to ensure precise, interpretable real-time fault monitoring and diagnosis. Our integrated strategy enables us to enhance resilience, safety and reliability when operating rocket engines - due to the proactive detection and systematic analysis of operational deviations before they would escalate into critical failures. We demonstrate the effectiveness of our method via a rigorous evaluation across varied simulated fault conditions, in order to showcase its potential to significantly mitigate the fault-related risks in aerospace systems.
Cite as
Andrea Urgolo, Ingo Pill, Günther Waxenegger-Wilfing, and Manuel Freiberger. Property Learning-Based Fault Detection for Liquid Propellant Rocket Engine Control Systems. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 15:1-15:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{urgolo_et_al:OASIcs.DX.2024.15,
author = {Urgolo, Andrea and Pill, Ingo and Waxenegger-Wilfing, G\"{u}nther and Freiberger, Manuel},
title = {{Property Learning-Based Fault Detection for Liquid Propellant Rocket Engine Control Systems}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {15:1--15:20},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.15},
URN = {urn:nbn:de:0030-drops-221074},
doi = {10.4230/OASIcs.DX.2024.15},
annote = {Keywords: Machine learning, Runtime verification, Property learning, Monitoring, Fault detection, Diagnosis, Genetic programming, Explainable AI}
}
Document
Quantifying the Sim-To-Real Gap in UAV Disturbance Rejection
Abstract
Due to the safety risks and training sample inefficiency, it is often preferred to develop controllers in simulation. However, minor differences between the simulation and the real world can cause a significant sim-to-real gap. This gap can reduce the effectiveness of the developed controller. In this paper, we examine a case study of transferring an octorotor reinforcement learning controller from simulation to the real world. First, we quantify the effectiveness of the real-world transfer by examining safety metrics. We find that although there is a noticeable (around 100%) increase in deviation in real flights, this deviation may not be considered unsafe, as it will be within > 2m safety corridors. Then, we estimate the densities of the measurement distributions and compare the Jensen-Shannon divergences of simulated and real measurements. From this, we show that the vehicle’s orientation is significantly different between simulated and real flights. We attribute this to a different flight mode in real flights where the vehicle turns to face the next waypoint. We also find that the reinforcement learning controller actions appear to correctly counteract disturbance forces. Then, we analyze the errors of a measurement autoencoder and state transition model neural network applied to real data. We find that these models further reinforce the difference between the simulated and real attitude control, showing the errors directly on the flight paths. Finally, we discuss important lessons learned in the sim-to-real transfer of our controller.
Cite as
Austin Coursey, Marcos Quinones-Grueiro, and Gautam Biswas. Quantifying the Sim-To-Real Gap in UAV Disturbance Rejection. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 16:1-16:18, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{coursey_et_al:OASIcs.DX.2024.16,
author = {Coursey, Austin and Quinones-Grueiro, Marcos and Biswas, Gautam},
title = {{Quantifying the Sim-To-Real Gap in UAV Disturbance Rejection}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {16:1--16:18},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.16},
URN = {urn:nbn:de:0030-drops-221087},
doi = {10.4230/OASIcs.DX.2024.16},
annote = {Keywords: sim-to-real, disturbance rejection, unmanned aerial vehicles}
}
Document
Real-Time Sensor Fault Detection in Drones: A Correlation-Based Algorithmic Approach
Abstract
Drones, or unmanned aerial vehicles (UAVs), are becoming increasingly vital across various industries, where their reliable operation is crucial for safety and efficiency. Ensuring this reliability requires the early detection of sensor-related faults, which are critical for maintaining the performance and safety of UAVs. This study addresses this challenge by leveraging real-world data from an Aero-Sentinel Military UAV Sentinel G2 quadcopter. The data was collected through a collaboration with Maris-Tech Ltd, using their advanced Mercury Nano system to capture detailed communication between the drone and its control unit. A set of correlation-based algorithms was developed and evaluated, specifically tailored to address the unique complexities of drone sensor data, which is often influenced by environmental factors. Among the algorithms tested, two novel methods emerged as particularly effective, demonstrating significant improvement compared to previous methods, in fault detection accuracy. These methods, designed to accurately identify and predict sensor malfunctions, offer a robust solution for enhancing the reliability and safety of UAV operations.
Cite as
Inbal Roshanski, Magenya Roshanski, and Meir Kalech. Real-Time Sensor Fault Detection in Drones: A Correlation-Based Algorithmic Approach. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 17:1-17:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{roshanski_et_al:OASIcs.DX.2024.17,
author = {Roshanski, Inbal and Roshanski, Magenya and Kalech, Meir},
title = {{Real-Time Sensor Fault Detection in Drones: A Correlation-Based Algorithmic Approach}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {17:1--17:20},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.17},
URN = {urn:nbn:de:0030-drops-221092},
doi = {10.4230/OASIcs.DX.2024.17},
annote = {Keywords: Drones, Sensor Fault Detection, Correlation-Based Algorithms, Sensor Data Analysis, Anomaly Detection, Data-Driven Fault Detection}
}
Document
Simulation-Based Diagnosis for Cyber-Physical Systems - A General Approach and Case Study on a Dual Three-Phase E-Machine
Abstract
This paper presents a simulation-based approach for fault diagnosis in cyber-physical systems. We utilize simulation models to generate training data for machine learning classifiers to detect faults and identify the root cause. The presented processing pipeline includes simulation model validation, training data generation, data preprocessing, and the implementation of a diagnosis method. A case study with a dual three-phase e-machine highlights the results and challenges of the simulation-based diagnosis approach. The e-machine simulation model provides a complex and robust system representation, including the capability to inject inter-turn short-circuit faults. The introduced validation procedures of the simulation model revealed limitations in signal similarity and distinguishability compared to real system behavior. Based on the discovered limitations, the overall best results are achieved by applying an Autoencoder model for anomaly detection, followed by a Random Forest classifier to identify the specific anomalies. Further, the focus is on identifying the affected e-machine phase rather than the exact number of faulty winding turns. The paper shows the challenges when applying a simulation-based diagnosis approach to time-series data and underlines the required analysis of simulation models. In addition, the flexible adaption in the diagnosis strategies enhances the efficient utilization of cyber-physical system models in fault diagnosis and root cause identification.
Cite as
David Kaufmann, Matus Kozovsky, and Franz Wotawa. Simulation-Based Diagnosis for Cyber-Physical Systems - A General Approach and Case Study on a Dual Three-Phase E-Machine. In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 18:1-18:21, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{kaufmann_et_al:OASIcs.DX.2024.18,
author = {Kaufmann, David and Kozovsky, Matus and Wotawa, Franz},
title = {{Simulation-Based Diagnosis for Cyber-Physical Systems - A General Approach and Case Study on a Dual Three-Phase E-Machine}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {18:1--18:21},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.18},
URN = {urn:nbn:de:0030-drops-221105},
doi = {10.4230/OASIcs.DX.2024.18},
annote = {Keywords: Cyber-Physical System, Fault diagnosis, Root cause analysis, Simulation-Based Diagnosis, Machine Learning, Artificial Neural Networks}
}
Document
Short Paper
Achieving Complete Structural Test Coverage in Embedded Systems Using Trace-Based Monitoring (Short Paper)
Abstract
This paper presents a systematic approach to achieving, in a well-defined sense, 100% structural test coverage for large embedded software projects. In embedded systems, high code coverage is a critical part of the testing process to ensure that the system works correctly. Measuring code coverage provides insight into the effectiveness of the testing process, the quality of the software, and can help identify untested or partially tested areas of the code. Traditionally, coverage is often measured when unit tests are executed. The proposed approach instead uses integration tests as the starting point for determining test completeness. Measuring code coverage at the integration test level in embedded systems can be challenging due to the limitations of software instrumentation (additional memory requirements and additional CPU load). To overcome these limitations, embedded trace technology is used to measure code coverage continuously and non-intrusively. The use of these techniques will help to increase the reliability of embedded software and reduce the likelihood of missed integration tests, missed high-level requirements, and undetected software defects.
Cite as
Alexander Weiss, Albert Schulz, Martin Heininger, Martin Sachenbacher, and Martin Leucker. Achieving Complete Structural Test Coverage in Embedded Systems Using Trace-Based Monitoring (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 19:1-19:12, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{weiss_et_al:OASIcs.DX.2024.19,
author = {Weiss, Alexander and Schulz, Albert and Heininger, Martin and Sachenbacher, Martin and Leucker, Martin},
title = {{Achieving Complete Structural Test Coverage in Embedded Systems Using Trace-Based Monitoring}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {19:1--19:12},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.19},
URN = {urn:nbn:de:0030-drops-221115},
doi = {10.4230/OASIcs.DX.2024.19},
annote = {Keywords: structural tests, integration tests, code coverage, embedded trace}
}
Document
Short Paper
Data-Driven Diagnosis of Electrified Vehicles: Results from a Structured Literature Review (Short Paper)
Abstract
Traditional onboard vehicle diagnostics are rapidly evolving concomitant to the rise of electrified powertrains, digital transformation, and intelligent technologies for advanced system management. The big data now available in modern vehicles offers unprecedented opportunities for condition monitoring and prognosis, but also presents challenges in scaling and integrating multimodal sensor data across components with varying timescale dynamics. Machine learning techniques have proven particularly effective in implementing diagnostic functions within electrified vehicle powertrains. This study systematically reviews intelligent, data-driven techniques for health monitoring and prognosis of electrified powertrains. We categorize existing research based on diagnostic functions and machine learning methods, with a focus on approaches that do not require prior knowledge of faulty operational states. Our findings indicate that deep learning methods are state-of-the-art across several diagnostic functions, fault modes, system levels, and multimodal sensor integration.
Cite as
Stan Muñoz Gutiérrez, Adil Mukhtar, and Franz Wotawa. Data-Driven Diagnosis of Electrified Vehicles: Results from a Structured Literature Review (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 20:1-20:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{munozgutierrez_et_al:OASIcs.DX.2024.20,
author = {Mu\~{n}oz Guti\'{e}rrez, Stan and Mukhtar, Adil and Wotawa, Franz},
title = {{Data-Driven Diagnosis of Electrified Vehicles: Results from a Structured Literature Review}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {20:1--20:14},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.20},
URN = {urn:nbn:de:0030-drops-221128},
doi = {10.4230/OASIcs.DX.2024.20},
annote = {Keywords: Diagnostic functions, Machine Learning, Powertrain, Electrified vehicles}
}
Document
Short Paper
Data-Driven RUL Prediction Using Performance Metrics (Short Paper)
Abstract
Prognostics is the scientific study of component and system degradation with use, and the prediction of when failure may occur. In this work, we propose a new data-driven method for predicting a system’s remaining useful life (RUL) without needing an accurate system model or expert knowledge. Instead, we use system operational data to estimate how the system’s performance metrics change with time. Although this is a purely data-driven approach, the method’s design is inspired by model-based techniques. First, we frame a novel Multitask Machine Learning architecture to simultaneously learn the general pattern of performance degradation and the individual trajectories from run-to-failure performance trajectory data. We apply this method to the set of performance metrics that determine the system’s end-of-life (EOL), building a performance trajectory library of the system operation under different operational conditions. We leverage the performance metric library as prior belief and develop a Bayesian deep learning approach to update the performance measures over time and predict the system EOL. We evaluate our method on two datasets of the N-CMAPSS benchmark, achieving satisfactory results in terms of overall performance and uncertainty estimation accuracy. Overall, our approach illustrates a generalized deep learning architecture that can more effectively predict the system RUL for a collection of identical systems.
Cite as
Abel Diaz-Gonzalez, Austin Coursey, Marcos Quinones-Grueiro, Chetan S. Kulkarni, and Gautam Biswas. Data-Driven RUL Prediction Using Performance Metrics (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 21:1-21:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{diazgonzalez_et_al:OASIcs.DX.2024.21,
author = {Diaz-Gonzalez, Abel and Coursey, Austin and Quinones-Grueiro, Marcos and Kulkarni, Chetan S. and Biswas, Gautam},
title = {{Data-Driven RUL Prediction Using Performance Metrics}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {21:1--21:15},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.21},
URN = {urn:nbn:de:0030-drops-221135},
doi = {10.4230/OASIcs.DX.2024.21},
annote = {Keywords: remaining useful life, data-driven methods, machine learning, performance metric, multitask machine learning, Monte Carlo}
}
Document
Short Paper
Detecting Soft Faults in Heat Pumps (Short Paper)
Abstract
Heat pumps are critical for energy-efficient heating and cooling, but their performance can be compromised by soft faults like condenser silting. It is vital to detect and fix such faults early in order to ensure optimal performance and longevity of heat pump systems, and consequently optimize the positive effect of heat pumps to our environment. In this paper, we tackle the problem of early fault detection and propose a supervised machine learning approach that detects soft faults. In particular, we used a random forest approach to learn the regular behavior of heat pumps. We detect faults via comparing the expected behavior obtained from the learned model with the current behavior. In addition to the description of the used methodology, we provide and discuss the results obtained from an experimental study that is based on synthetic data of two different heat pumps.
Cite as
Birgit Hofer and Franz Wotawa. Detecting Soft Faults in Heat Pumps (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 22:1-22:10, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{hofer_et_al:OASIcs.DX.2024.22,
author = {Hofer, Birgit and Wotawa, Franz},
title = {{Detecting Soft Faults in Heat Pumps}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {22:1--22:10},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.22},
URN = {urn:nbn:de:0030-drops-221145},
doi = {10.4230/OASIcs.DX.2024.22},
annote = {Keywords: Fault detection, heat pumps, supervised machine learning}
}
Document
Short Paper
Diagnosing Non-Intermittent Anomalies in Reinforcement Learning Policy Executions (Short Paper)
Abstract
Reinforcement learning (RL) algorithms output policies specifying which action an agent should take in a given state. However, faults can sometimes arise during policy execution due to internal faults in the agent. As a result, actions may have unexpected effects. In this work, we aim to diagnose such faults and infer their root cause. We consider two types of diagnosis problems. In the first, which we call RLDXw, we assume we only know what a normal execution looks like. In the second, called RLDXs, we assume we have models for the faulty behavior of a component, which we call fault modes. The solution to RLDXw is a time step at which a fault occurred for the first time. The solution to RLDXs is more informative, represented as a fault mode according to which the RL task was executed. Solving those problems is useful in practice to facilitate efficient repair of faulty agents, since it can focus the repair efforts on specific actions. We formally define RLDXw and RLDXs and design two algorithms called WFMa and SFMa for solving them. We evaluate our algorithms on a benchmark of RL domains and discuss their strengths and limitations. When the number of the observed states increases, both WFMa and SFMa report a decrease in runtime (up to significantly 6.5 times faster). Additionally, the runtime of SFMa increases linearly with the increase in candidate fault modes.
Cite as
Avraham Natan, Roni Stern, and Meir Kalech. Diagnosing Non-Intermittent Anomalies in Reinforcement Learning Policy Executions (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 23:1-23:13, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{natan_et_al:OASIcs.DX.2024.23,
author = {Natan, Avraham and Stern, Roni and Kalech, Meir},
title = {{Diagnosing Non-Intermittent Anomalies in Reinforcement Learning Policy Executions}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {23:1--23:13},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.23},
URN = {urn:nbn:de:0030-drops-221151},
doi = {10.4230/OASIcs.DX.2024.23},
annote = {Keywords: Diagnosis, Reinforcement Learning, Autonomous Systems}
}
Document
Short Paper
Faster Diagnosis with Answer Set Programming (Short Paper)
Abstract
From hardware to software to human patients, diagnosis has been one of the first areas of interest in artificial intelligence, and has remained a relevant topic since. Recent research in model-based diagnosis has shown that answer set programming not only allows for an easy expression of diagnosis problems, but also efficient solving. In this paper, we improve on previous results by making use of various modern answer set programming techniques. Our experiments compare multi-shot solving, heuristics and preferences, with results indicating that heuristics provide the fastest solutions on most instances we studied.
Cite as
Liliana Marie Prikler and Franz Wotawa. Faster Diagnosis with Answer Set Programming (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 24:1-24:13, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{prikler_et_al:OASIcs.DX.2024.24,
author = {Prikler, Liliana Marie and Wotawa, Franz},
title = {{Faster Diagnosis with Answer Set Programming}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {24:1--24:13},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.24},
URN = {urn:nbn:de:0030-drops-221160},
doi = {10.4230/OASIcs.DX.2024.24},
annote = {Keywords: Answer set programming, model-based diagnosis, performance comparison}
}
Document
Short Paper
FLEX: Fault Localization and Explanation Using Open-Source Large Language Models in Powertrain Systems (Short Paper)
Abstract
Cyber-physical systems (CPS) are critical to modern infrastructure, but are vulnerable to faults and anomalies that threaten their operational safety. In this work, we evaluate the use of open-source Large Language Models (LLMs), such as Mistral 7B, Llama3.1:8b-instruct-fp16, and others to detect anomalies in two distinct datasets: battery management and powertrain systems. Our methodology utilises retrieval-augmented generation (RAG) techniques, incorporating a novel two-step process where LLMs first infer operational rules from normal behavior before applying these rules for fault detection. During the experiments, we found that the original prompt design yielded strong results for the battery dataset but required modification for the powertrain dataset to improve performance. The adjusted prompt, which emphasises rule inference, significantly improved anomaly detection for the powertrain dataset. Experimental results show that models like Mistral 7B achieved F1-scores up to 0.99, while Llama3.1:8b-instruct-fp16 and Gemma 2 reached perfect F1-scores of 1.0 in complex scenarios. These findings demonstrate the impact of effective prompt design and rule inference in improving LLM-based fault detection for CPS, contributing to increased operational resilience.
Cite as
Herbert Muehlburger and Franz Wotawa. FLEX: Fault Localization and Explanation Using Open-Source Large Language Models in Powertrain Systems (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 25:1-25:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{muehlburger_et_al:OASIcs.DX.2024.25,
author = {Muehlburger, Herbert and Wotawa, Franz},
title = {{FLEX: Fault Localization and Explanation Using Open-Source Large Language Models in Powertrain Systems}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {25:1--25:14},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.25},
URN = {urn:nbn:de:0030-drops-221170},
doi = {10.4230/OASIcs.DX.2024.25},
annote = {Keywords: Fault detection, anomaly detection, powertrain systems, large language models, open-source LLMs}
}
Document
Short Paper
Hyperplanes Based Zonotopic Contractor (Short Paper)
Abstract
This article introduces a novel method for constructing a "zonotopic contractor" based on hyperplane properties. While zonotopes, a special class of polytopes, offer computational advantages due to their symmetric matrix representation, they are not closed under intersection, often necessitating over-approximations that lead to conservatism in practical applications. The proposed contractor addresses this issue by providing a more efficient solution for approximating zonotope intersections, reducing conservatism. This method generates a new zonotope that closely covers the intersection of two zonotopes. The reliability and effectiveness of the proposed approach are demonstrated through simulations on a bicycle model, showing potential benefits in safety-critical applications like autonomous driving, where precise uncertainty management is crucial for decision-making and control.
Cite as
Rahma Bengamra, Soheib Fergani, and Carine Jauberthie. Hyperplanes Based Zonotopic Contractor (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 26:1-26:13, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{bengamra_et_al:OASIcs.DX.2024.26,
author = {Bengamra, Rahma and Fergani, Soheib and Jauberthie, Carine},
title = {{Hyperplanes Based Zonotopic Contractor}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {26:1--26:13},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.26},
URN = {urn:nbn:de:0030-drops-221182},
doi = {10.4230/OASIcs.DX.2024.26},
annote = {Keywords: Contractors, Zonotopes, Hyperplanes}
}
Document
Short Paper
On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)
Abstract
In an industrial maintenance context, degradation diagnosis is the problem of determining the current level of degradation of operating machines based on measurements. With the emergence of Machine Learning techniques, such a problem can now be solved by training a degradation model offline and by using it online. While such models are more and more accurate and performant, they are often black-box and their decisions are therefore not interpretable for human maintenance operators. On the contrary, interpretable ML models are able to provide explanations for the model’s decisions and consequently improves the confidence of the human operator about the maintenance decision based on these models. This paper proposes a new method to quantitatively measure the interpretability of such models that is agnostic (no assumption about the class of models) and that is applied on degradation models. The proposed method requires that the decision maker sets up some high level parameters in order to measure the interpretability of the models and then can decide whether the obtained models are satisfactory or not. The method is formally defined and is fully illustrated on a decision tree degradation model and a model trained with a recent neural network architecture called Multiclass Neural Additive Model.
Cite as
Charles-Maxime Gauriat, Yannick Pencolé, Pauline Ribot, and Gregory Brouillet. On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 27:1-27:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{gauriat_et_al:OASIcs.DX.2024.27,
author = {Gauriat, Charles-Maxime and Pencol\'{e}, Yannick and Ribot, Pauline and Brouillet, Gregory},
title = {{On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {27:1--27:14},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.27},
URN = {urn:nbn:de:0030-drops-221196},
doi = {10.4230/OASIcs.DX.2024.27},
annote = {Keywords: XAI, Interpretability, multiclass supervised learning, degradation diagnosis}
}
Document
Short Paper
Test Selection for Diagnosing Multimode Systems (Short Paper)
Abstract
This work considers the problem of selecting residuals for consistency-based diagnosis of multimode systems. The system operation mode is assumed to be given by a set of known discrete variables. The number of operation modes grows exponentially with the number of binary variables, thus methods enumerating the modes are not feasible. Here a method is proposed to select a small subset of residuals for diagnosing multimode systems. The selection is based on the fault signature of the residuals for the different modes of operation. To avoid the exponential growth of the number of modes, the multimode fault signature matrix is used to compute the diagnosability of the residuals. The approach is inspired and exemplified by a dynamically configurable battery pack. The result is a small set of residuals with the maximum diagnosability in all operation modes.
Cite as
Mattias Krysander and Fatemeh Hashemniya. Test Selection for Diagnosing Multimode Systems (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 28:1-28:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{krysander_et_al:OASIcs.DX.2024.28,
author = {Krysander, Mattias and Hashemniya, Fatemeh},
title = {{Test Selection for Diagnosing Multimode Systems}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {28:1--28:14},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.28},
URN = {urn:nbn:de:0030-drops-221209},
doi = {10.4230/OASIcs.DX.2024.28},
annote = {Keywords: Consistency-based Diagnosis, Residual Selection, Multimode Systems, Battery Application}
}
Document
Short Paper
Transformer-Based Signal Inference for Electrified Vehicle Powertrains (Short Paper)
Abstract
The scarcity of labeled data for intelligent diagnosis of non-linear technical systems is a common problem for developing robust and reliable real-world applications. Several deep learning approaches have been developed to address this challenge, including self-supervised learning, representation learning, and transfer learning. Due largely to their powerful attention mechanisms, transformers excel at capturing long-term dependencies across multichannel and multi-modal signals in sequential data, making them suitable candidates for time series modeling. Despite their potential, studies applying transformers for diagnostic functions, especially in signal reconstruction through representation learning, remain limited. This paper aims to narrow this gap by identifying the requirements and potential of transformer self-attention mechanisms for developing auto-associative inference engines that learn exclusively from healthy behavioral data. We apply a transformer backbone for signal reconstruction using simulated data from a simplified powertrain. Feedback from these experiments, and the reviewed evidence from the literature, allows us to conclude that autoencoder and autoregressive approaches are potentiated by transformers.
Cite as
Stan Muñoz Gutiérrez, Adil Mukhtar, and Franz Wotawa. Transformer-Based Signal Inference for Electrified Vehicle Powertrains (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 29:1-29:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{munozgutierrez_et_al:OASIcs.DX.2024.29,
author = {Mu\~{n}oz Guti\'{e}rrez, Stan and Mukhtar, Adil and Wotawa, Franz},
title = {{Transformer-Based Signal Inference for Electrified Vehicle Powertrains}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {29:1--29:14},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.29},
URN = {urn:nbn:de:0030-drops-221217},
doi = {10.4230/OASIcs.DX.2024.29},
annote = {Keywords: Signal Inference, Deep Learning, Self-Supervised Learning, Multimodal Transformer Autoencoder, Electric Vehicle, Powertrain, Electric Motor}
}
Document
Short Paper
Usability of Symbolic Regression for Hybrid System Identification - System Classes and Parameters (Short Paper)
Abstract
Hybrid systems, which combine both continuous and discrete behavior, are used in many fields, including robotics, biological systems, and control systems. However, due to their complexity, finding an accurate model is a challenge. This paper discusses the usage of symbolic regression to learn hybrid systems from data and specifically analyses learning parameters for a recent algorithm. Symbolic regression is a powerful tool that can automatically discover accurate and interpretable mathematical models in the form of symbolic expressions.
Models generated by symbolic regression are a valuable tool for system identification and diagnosis, e.g., to predict future system behavior or detect anomalies. A major opportunity of our approach is the ability to detect transitions between different continuous behaviors of a system directly based on the dynamics. From a diagnosis perspective, this can advantageously be used to detect the system entering fault modes and identify their models. This paper presents a parameter study for a symbolic regression based identification algorithm.
Cite as
Swantje Plambeck, Maximilian Schmidt, Audine Subias, Louise Travé-Massuyès, and Goerschwin Fey. Usability of Symbolic Regression for Hybrid System Identification - System Classes and Parameters (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 30:1-30:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{plambeck_et_al:OASIcs.DX.2024.30,
author = {Plambeck, Swantje and Schmidt, Maximilian and Subias, Audine and Trav\'{e}-Massuy\`{e}s, Louise and Fey, Goerschwin},
title = {{Usability of Symbolic Regression for Hybrid System Identification - System Classes and Parameters}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {30:1--30:14},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.30},
URN = {urn:nbn:de:0030-drops-221223},
doi = {10.4230/OASIcs.DX.2024.30},
annote = {Keywords: Hybrid Systems, Symbolic Regression, System Identification}
}
Document
Short Paper
Using Multi-Modal LLMs to Create Models for Fault Diagnosis (Short Paper)
Abstract
Creating models that are usable for fault diagnosis is hard. This is especially true for cyber-physical systems that are subject to architectural changes and may need to be adapted to different product variants intermittently. We therefore can no longer rely on expert-defined and static models for many systems. Instead, models need to be created more cheaply and need to adapt to different circumstances. In this article we present a novel approach to create physical models for process industry systems using multi-modal large language models (i.e ChatGPT). We present a five-step prompting approach that uses a piping and instrumentation diagram (P&ID) and natural language prompts as its input. We show that we are able to generate physical models of three systems of a well-known benchmark. We further show that we are able to diagnose faults for all of these systems by using the Fault Diagnosis Toolbox. We found that while multi-modal large language models (MLLMs) are a promising method for automated model creation, they have significant drawbacks.
Cite as
Silke Merkelbach, Alexander Diedrich, Anna Sztyber-Betley, Louise Travé-Massuyès, Elodie Chanthery, Oliver Niggemann, and Roman Dumitrescu. Using Multi-Modal LLMs to Create Models for Fault Diagnosis (Short Paper). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 31:1-31:15, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{merkelbach_et_al:OASIcs.DX.2024.31,
author = {Merkelbach, Silke and Diedrich, Alexander and Sztyber-Betley, Anna and Trav\'{e}-Massuy\`{e}s, Louise and Chanthery, Elodie and Niggemann, Oliver and Dumitrescu, Roman},
title = {{Using Multi-Modal LLMs to Create Models for Fault Diagnosis}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {31:1--31:15},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.31},
URN = {urn:nbn:de:0030-drops-221236},
doi = {10.4230/OASIcs.DX.2024.31},
annote = {Keywords: Fault Diagnosis, Large Language Models, LLMs, Physical Modelling, Process Industry, P\&IDs}
}
Document
Extended Abstract
Summary of "A Lazy Approach to Neural Numerical Planning with Control Parameters" (Extended Abstract)
Abstract
This is an extended abstract of the manuscript "A Lazy Approach to Neural Numerical Planning with Control Parameters" [René Heesch et al., 2024]. The paper presents a lazy, hierarchical approach to tackle the challenge of planning in complex numerical domains, where the effects of actions are influenced by control parameters, and may be described by neural networks.
Cite as
René Heesch, Alessandro Cimatti, Jonas Ehrhardt, Alexander Diedrich, and Oliver Niggemann. Summary of "A Lazy Approach to Neural Numerical Planning with Control Parameters" (Extended Abstract). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 32:1-32:3, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{heesch_et_al:OASIcs.DX.2024.32,
author = {Heesch, Ren\'{e} and Cimatti, Alessandro and Ehrhardt, Jonas and Diedrich, Alexander and Niggemann, Oliver},
title = {{Summary of "A Lazy Approach to Neural Numerical Planning with Control Parameters"}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {32:1--32:3},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.32},
URN = {urn:nbn:de:0030-drops-221243},
doi = {10.4230/OASIcs.DX.2024.32},
annote = {Keywords: Satisfiability Modulo Theory, Neural Numerical Planning with Control Parameters, Neural Networks}
}
Document
Extended Abstract
Summary of "Randomized Problem-Relaxation Solving for Over-Constrained Schedules" (Extended Abstract)
Abstract
We present a general framework for tackling over-constrained job shop scheduling problems (JSSP) where the volume of jobs (orders) exceeds the production capacity for a given planning horizon. The goal is to process as many or as utile jobs as possible within the available time. The suggested framework approaches this optimization problem by solving multiple randomly modified relaxed problem instances, thereby taking a sample in a solution space that covers all optimal solutions. By continuously storing the best solution found so far, the result is a complete anytime algorithm that incrementally approximates an optimal solution. The proposed framework allows for highly parallel computations, and all of its modules are treated as black-boxes, allowing them to be instantiated with the most performant algorithms for the respective sub-problems. Using IBM’s cutting-edge CP Optimizer suite, experiments on well-known JSSP benchmark problems demonstrate that the proposed framework consistently schedules more jobs in less computation time compared to a standalone constraint solver approach. Due to the generality of the proposed approach and its applicability to computing minimum-cardinality or most preferred minimal diagnoses, this work has the potential to positively impact the field of model-based diagnosis.
Cite as
Patrick Rodler, Erich Teppan, and Dietmar Jannach. Summary of "Randomized Problem-Relaxation Solving for Over-Constrained Schedules" (Extended Abstract). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 33:1-33:4, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{rodler_et_al:OASIcs.DX.2024.33,
author = {Rodler, Patrick and Teppan, Erich and Jannach, Dietmar},
title = {{Summary of "Randomized Problem-Relaxation Solving for Over-Constrained Schedules"}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {33:1--33:4},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.33},
URN = {urn:nbn:de:0030-drops-221259},
doi = {10.4230/OASIcs.DX.2024.33},
annote = {Keywords: diagnosis computation, randomized diagnosis computation, minimum-cardinality diagnoses, most preferred diagnoses, maximum-probability diagnoses, applications of diagnosis (over-constrained scheduling problems), diagnosis-based optimization, constraint programming, CP Optimizer, job shop scheduling problem, job set optimization problem, operations research, scheduling, industry use cases, minimal subset subject to a monotone predicate (MSMP) problem, problem relaxation, sampling for optimization, anytime algorithm}
}
Document
Extended Abstract
Summary of "Sequence-Oriented Diagnosis of Discrete-Event Systems" (Extended Abstract)
Abstract
What follows is an extended abstract of a paper recently published in the Journal of Artificial Intelligence Research [G. Lamperti et al., 2023]. Broadly speaking, the approaches to model-based diagnosis of discrete-event systems (DESs) can be accommodated within a spectrum ranging from no to total knowledge-compilation. That paper presents three approaches, one for either end of the spectrum, and one falling in between, in order to compute diagnoses that are sequences of faults.
In the literature, model-based diagnosis has always been conceived as set-oriented, meaning that a candidate is a set of faults, or faulty components, that explains a collection of observations. This perspective applies to both static and dynamical systems. Diagnosis of DESs is no exception: a candidate is traditionally a set of faults occurring in a trajectory of the DES that conforms with a given sequence of observations, namely a temporal observation. To improve diagnostic explanation and support decision making, a sequence-oriented perspective to diagnosis of DESs is presented, where a candidate is a sequence of faults occurring in a trajectory of the DES that produces the temporal observation. That candidate, called a fault sequence, differs from a classical candidate mainly in three ways: (i) it includes the multiset of faults occurred in the trajectory, where all the occurrences of the same fault are encompassed, (ii) it provides a total temporal order of faults, and (iii) its length may be unbounded, as the same fault may occur an unlimited number of times in the trajectory. Therefore, in a sequence-oriented perspective, the diagnosis output is the (possibly infinite) set of all distinct fault sequences, each relevant to a (possibly infinite) set of trajectories of the DES that produce a given temporal observation. Having a possibly unbounded set of candidates contrasts with set-oriented diagnosis, where the set of candidates is bounded by the powerset of the domain of faults. Still, a possibly unbounded set of fault sequences is shown to be a regular language, which can be defined as a regular expression over the domain of faults: this regular expression represents the output of sequence-oriented diagnosis.
The additional information on the chronological order of faults and their multiple occurrences embedded in a fault sequence may be important for ranking purposes, as well as for supporting diagnosticians and/or troubleshooting algorithms to make decisions in critical scenarios and, possibly, to take some sequential diagnosis steps. Since the output of sequence-oriented diagnosis includes additional pieces of information with respect to the output of set-oriented diagnosis, two questions raise quite naturally: how can the sequence-oriented task be performed, and which is its performance? The paper addresses the former question for a class of DESs usually considered by the authors (active systems) in three ways, and shows some experimental evidence to answer the latter.
Specifically, three sound and complete techniques to perform the task of monitoring-based diagnosis are described and compared, where a new candidate set is generated at the occurrence of each observation, namely: (1) blind diagnosis, with no compiled knowledge, (2) greedy diagnosis, with total knowledge compilation, and (3) lazy diagnosis, with partial knowledge compilation. By knowledge we mean a data structure, slightly similar to a classical DES diagnoser, which is called an explainer, that can be generated (compiled) either entirely offline (greedy diagnosis) or incrementally online (lazy diagnosis). Among them, only the blind diagnosis engine relies solely on the model of the DES, without producing any data structure offline nor performing any offline processing. It constructs and iteratively updates the portion of a DES behavioral space that conforms with the temporal observation perceived so far. To compute the resulting regular expression, a state-elimination algorithm has been exploited from the literature, which takes as input a non-deterministic automaton and generates the regular expression of the accepted language. In greedy diagnosis, the explainer generated offline has a size that is smaller than the size of the classical diagnoser that enables the online computation of set-oriented candidates. However, its smaller size comes with a disadvantage: the explainer is a non-deterministic finite automaton, whereas the diagnoser is deterministic. Hence, in greedy diagnosis, whenever a new observable event is perceived, the time required by the online search within the explainer may be longer than the search time in the diagnoser. Moreover, building a complete explainer is out of the question for real size DESs, owing to the exponential explosion of the states involved. The building blocks of the explainer are called fault spaces. Each fault space is generated by a variant of the state-elimination algorithm in the literature, whose pseudocode is specified in the paper. In the construction of a complete explainer, the generation of the regular expressions is very expensive since there is a trade-off between the richness of the information embedded in the diagnosis output and the time required for its computation. The paper includes some hints about the asymptotic time complexity of the algorithms. A possible mitigation of the complexity comes from lazy diagnosis, which performs only partial knowledge compilation, thus obtaining a partial explainer. The three diagnosis engines have been implemented, with the software code being open source (see [G. Lamperti et al., 2023] for the link). The experimental activity recorded in the paper indicates that only lazy diagnosis may be viable in non-trivial application domains, both for the construction of the partial explainer and for the online computation of the candidates. A partial explainer can be progressively extended, the upgrade being relevant either just to a single observable event (the latest one perceived during monitoring, in case it is not encompassed yet by the current partial explainer) or to the observation pattern corresponding to a behavioral scenario. Typically, behavioral scenarios can be defined to represent frequent and/or critical evolutions of the DES that we want to detect quickly during monitoring via compiled knowledge.
A sample application inspired by a small real-world example in the literature is described in the paper. The aim is to show that in the considered domain of Labour Market, as well as in other similar domains, sequence-oriented diagnosis is actually more convenient than set-oriented diagnosis.
Cite as
Gianfranco Lamperti, Stefano Trerotola, Marina Zanella, and Xiangfu Zhao. Summary of "Sequence-Oriented Diagnosis of Discrete-Event Systems" (Extended Abstract). In 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024). Open Access Series in Informatics (OASIcs), Volume 125, pp. 34:1-34:2, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)
Copy BibTex To Clipboard
@InProceedings{lamperti_et_al:OASIcs.DX.2024.34,
author = {Lamperti, Gianfranco and Trerotola, Stefano and Zanella, Marina and Zhao, Xiangfu},
title = {{Summary of "Sequence-Oriented Diagnosis of Discrete-Event Systems"}},
booktitle = {35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)},
pages = {34:1--34:2},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-356-0},
ISSN = {2190-6807},
year = {2024},
volume = {125},
editor = {Pill, Ingo and Natan, Avraham and Wotawa, Franz},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2024.34},
URN = {urn:nbn:de:0030-drops-221267},
doi = {10.4230/OASIcs.DX.2024.34},
annote = {Keywords: model-based reasoning, monitoring-based diagnosis, discrete-event systems, sequence-oriented diagnosis, active systems, knowledge-compilation, laziness}
}