Volume
OASIcs, Volume 136
36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)
-
Part of:
Series:
Open Access Series in Informatics (OASIcs)
Conference: International Conference on Principles of Diagnosis and Resilient Systems (DX)
Event
DX 2025, September 22-24, 2025, Nashville, TN, USAEditors
- Institute for Software Integrated Systems, Vanderbilt University, Nashville, TN, USA
Publication Details
- published at: 2025-11-10
- Publisher: Schloss Dagstuhl – Leibniz-Zentrum für Informatik
- ISBN: 978-3-95977-394-2
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 136, DX 2025, Complete Volume
Abstract
OASIcs, Volume 136, DX 2025, Complete Volume
Cite as
36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 1-304, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@Proceedings{quinonesgrueiro_et_al:OASIcs.DX.2025,
title = {{OASIcs, Volume 136, DX 2025, Complete Volume}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {1--304},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025},
URN = {urn:nbn:de:0030-drops-249851},
doi = {10.4230/OASIcs.DX.2025},
annote = {Keywords: OASIcs, Volume 136, DX 2025, Complete Volume}
}
Document
Front Matter
Front Matter, Table of Contents, Preface, Conference Organization
Abstract
Front Matter, Table of Contents, Preface, Conference Organization
Cite as
36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 0:i-0:xii, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{quinonesgrueiro_et_al:OASIcs.DX.2025.0,
author = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
title = {{Front Matter, Table of Contents, Preface, Conference Organization}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {0:i--0:xii},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.0},
URN = {urn:nbn:de:0030-drops-249842},
doi = {10.4230/OASIcs.DX.2025.0},
annote = {Keywords: Front Matter, Table of Contents, Preface, Conference Organization}
}
Document
Beyond Static Diagnosis: A Temporal ASP Framework for HVAC Fault Detection
Abstract
Improving sustainability in the building sector requires more efficient operation of energy-intensive systems such as Heating, Ventilation, and Air Conditioning (HVAC). We present a novel diagnostic framework for HVAC systems that integrates Answer Set Programming (ASP) with Functional Event Calculus (FEC). Our approach exploits the declarative nature of ASP for modeling and incorporates FEC to capture temporal system dynamics.
We demonstrate the feasibility of our approach through a case study on a real-world heating system, where we model key components and system constraints. Our evaluation on nominal and faulty traces shows that exploiting ASP in combination with FEC can identify plausible diagnoses. Moreover, we explore the difference between static and rolling-window strategies and provide insights into runtime versus soundness on those variants. Our work provides a step toward the practical application of ASP-based temporal reasoning in building diagnostics.
Cite as
Roxane Koitz-Hristov, Liliana Marie Prikler, and Franz Wotawa. Beyond Static Diagnosis: A Temporal ASP Framework for HVAC Fault Detection. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 1:1-1:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{koitzhristov_et_al:OASIcs.DX.2025.1,
author = {Koitz-Hristov, Roxane and Prikler, Liliana Marie and Wotawa, Franz},
title = {{Beyond Static Diagnosis: A Temporal ASP Framework for HVAC Fault Detection}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {1:1--1:20},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.1},
URN = {urn:nbn:de:0030-drops-247901},
doi = {10.4230/OASIcs.DX.2025.1},
annote = {Keywords: Model-based diagnosis, Answer set programming, HVAC, Modeling for diagnosis, Experimental evaluation}
}
Document
Are Diagnostic Concepts Within the Reach of LLMs?
Abstract
Model-based diagnosis is a cornerstone of system health monitoring, allowing for the identification of faulty components based on observed behavior and a formal system model. However, obtaining a useful and reliable model is often an expensive and manual task. While the generation of a formal model was the aim of previous work, in this paper, we propose a methodology to use large language models to generate Minimal Structurally Overdetermined sets (MSOs). MSOs are specific subsets of the model equations from which diagnosis tests can be obtained. We investigate two different directions: (i) the large-language-models' ability to generate MSO sets for hybrid systems, similar to those generated by the well-known Fault Diagnosis Toolbox (FDT) (ii) the automated generation of MSOs for Boolean circuits, as well as the computation of the diagnoses. We thus show how both dynamic and static systems can be analysed by large-language models and how their output can be used for effective fault diagnosis. We evaluate our approach on a set of arithmetic and logic circuits, using OpenAI’s LLMs 4o-mini, o1, and o3-mini.
Cite as
Anna Sztyber-Betley, Elodie Chanthery, Louise Travé-Massuyès, Silke Merkelbach, Karol Kukla, Maxence Glotin, Alexander Diedrich, and Oliver Niggemann. Are Diagnostic Concepts Within the Reach of LLMs?. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 2:1-2:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{sztyberbetley_et_al:OASIcs.DX.2025.2,
author = {Sztyber-Betley, Anna and Chanthery, Elodie and Trav\'{e}-Massuy\`{e}s, Louise and Merkelbach, Silke and Kukla, Karol and Glotin, Maxence and Diedrich, Alexander and Niggemann, Oliver},
title = {{Are Diagnostic Concepts Within the Reach of LLMs?}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {2:1--2:20},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.2},
URN = {urn:nbn:de:0030-drops-247913},
doi = {10.4230/OASIcs.DX.2025.2},
annote = {Keywords: Fault Diagnosis, Large Language Models, LLMs, Model Based Diagnosis, MSO, Redundancy Relations, Conflicts, Diagnoses}
}
Document
Combining Dynamic Slicing and Spectrum-Based Fault Localization - A First Experimental Evaluation
Abstract
Identifying and localizing bugs in programs has always been considered a complex but essential topic. Whereas the former has led to substantial progress in areas like formal verification and testing with a high degree of automation, the latter has not been satisfactorily automated. Approaches like program slicing, model-based diagnosis, and, more recently, spectrum-based fault localization can be used to find possible causes of a misbehaving program automatically, but often come with high computational complexity or a larger list of diagnoses, which require additional manual effort. In this paper, we present the first experimental results of an approach that combines program slicing with spectrum-based fault localization aiming at improving the outcome of automated debugging methods. In contrast to previous work, where we illustrated potential improvements only by considering a particular use case, we present an evaluation based on 22 different example programs in this paper. The approach improves the wasted effort on average by around 5 to 15% on average.
Cite as
Jonas Schleich and Franz Wotawa. Combining Dynamic Slicing and Spectrum-Based Fault Localization - A First Experimental Evaluation. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 3:1-3:18, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{schleich_et_al:OASIcs.DX.2025.3,
author = {Schleich, Jonas and Wotawa, Franz},
title = {{Combining Dynamic Slicing and Spectrum-Based Fault Localization - A First Experimental Evaluation}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {3:1--3:18},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.3},
URN = {urn:nbn:de:0030-drops-247927},
doi = {10.4230/OASIcs.DX.2025.3},
annote = {Keywords: Software fault localization, program slicing, spectrum-based fault localization, automated debugging}
}
Document
Using Qualitative Simulation Models for Monitoring and Diagnosis
Abstract
Many systems in our daily lives control physical processes, which are parametrized and adapted, such as heating systems in buildings. Faults and non-optimized settings lead to a high energy demand and, therefore, need to be detected as early as possible. Unfortunately, due to specific adaptations, only the basic principles remain the same, but not the concrete implementations, making the use of techniques like machine learning difficult. Therefore, we suggest using abstract models that cover the basic behavior in a way that allows us to reuse the models in different installations. In particular, we discuss the application of qualitative simulation for fault detection and introduce a formal definition of conformance between the results of qualitative simulation and the monitored behavior. We discuss arising difficulties and provide a basis for further research and applications.
Cite as
Ankita Das, Roxane Koitz-Hristov, and Franz Wotawa. Using Qualitative Simulation Models for Monitoring and Diagnosis. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 4:1-4:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{das_et_al:OASIcs.DX.2025.4,
author = {Das, Ankita and Koitz-Hristov, Roxane and Wotawa, Franz},
title = {{Using Qualitative Simulation Models for Monitoring and Diagnosis}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {4:1--4:14},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.4},
URN = {urn:nbn:de:0030-drops-247934},
doi = {10.4230/OASIcs.DX.2025.4},
annote = {Keywords: Qualitative Simulation, Fault Detection, Model-based Diagnosis, Monitoring, Application}
}
Document
Assessing Diagnosis Algorithms: Of Sampling, Baselines, Metrics and Oracles
Abstract
Assessing and comparing diagnosis algorithms is a surprisingly complex challenge. We have to make decisions ranging from identifying the implications of the chosen baseline, via defining and ensuring a representative sampling strategy, to the choice of metric best suited to capture the computational, probing, or repair costs as well as the deviations from the baseline. We discuss several aspects of the overall challenge, identify related issues, and evaluate a special economic metric.
Cite as
Ingo Pill and Johan de Kleer. Assessing Diagnosis Algorithms: Of Sampling, Baselines, Metrics and Oracles. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 5:1-5:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{pill_et_al:OASIcs.DX.2025.5,
author = {Pill, Ingo and de Kleer, Johan},
title = {{Assessing Diagnosis Algorithms: Of Sampling, Baselines, Metrics and Oracles}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {5:1--5:19},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.5},
URN = {urn:nbn:de:0030-drops-247941},
doi = {10.4230/OASIcs.DX.2025.5},
annote = {Keywords: Model-based Diagnosis, Diagnosis, Algorithms}
}
Document
Towards Predictive Maintenance in an Aluminum Die-Casting Process Using Deep Learning Clustering and Dimensionality Reduction
Abstract
In the manufacturing industry, predictive maintenance requires the estimation of the health status of key subsystems or components. In this study, we will look for degradation patterns in the piston of an injection machine used in an aluminum die casting process operating in an automobile factory in Valladolid (Spain). The injection machine produces a new engine block every 90 seconds and each injection device provides 2000 measurements of various physical variables. This study faced the challenge of finding piston head degradation patterns for an injection machine in the factory, using time series data obtained from the controller, as a preliminary step to estimate the remaining useful life (RUL) of the piston head. The proposed solution used advanced deep learning clustering techniques to generate an index related with the progression of the degradation of the components. The results indicated that degradation patterns can be identified. Later on, using an exponential function an approximation of the RUL can be provided to the plant operator to achieve an ordered piston replacement.
Cite as
Miguel Cubero, Luis Ignacio Jiménez, Daniel López, Belarmino Pulido, and Carlos Alonso-González. Towards Predictive Maintenance in an Aluminum Die-Casting Process Using Deep Learning Clustering and Dimensionality Reduction. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 6:1-6:16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{cubero_et_al:OASIcs.DX.2025.6,
author = {Cubero, Miguel and Jim\'{e}nez, Luis Ignacio and L\'{o}pez, Daniel and Pulido, Belarmino and Alonso-Gonz\'{a}lez, Carlos},
title = {{Towards Predictive Maintenance in an Aluminum Die-Casting Process Using Deep Learning Clustering and Dimensionality Reduction}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {6:1--6:16},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.6},
URN = {urn:nbn:de:0030-drops-247951},
doi = {10.4230/OASIcs.DX.2025.6},
annote = {Keywords: Prognostics, Deep Learning, Clustering, UMAP, LOWESS regression}
}
Document
One-Shot Learning in Hybrid System Identification: A New Modular Paradigm
Abstract
Identification of hybrid systems requires learning models that capture both discrete transitions and continuous dynamics from observational data. Traditional approaches follow a stepwise process, separating trace segmentation and mode-specific regression, which often leads to inconsistencies due to unmodeled interdependencies. In this paper, we propose a new iterative learning paradigm that jointly optimizes segmentation and flow function identification. The method incrementally constructs a hybrid model by evaluating and expanding candidate flow functions over observed traces, introducing new modes only when existing ones fail to explain the data. The approach is modular and agnostic to the choice of the regression technique, allowing the identification of hybrid systems with varying levels of complexity. Empirical results on benchmark examples demonstrate that the proposed method produces more compact models compared to traditional techniques, while supporting flexible integration of different regression methods. By favoring fewer, more generalizable modes, the resulting models are not only likely to reduce complexity but also simplify diagnostic reasoning, improve fault isolation, and enhance robustness by avoiding overfitting to spurious mode changes.
Cite as
Swantje Plambeck, Maximilian Schmidt, Louise Travé-Massuyès, and Goerschwin Fey. One-Shot Learning in Hybrid System Identification: A New Modular Paradigm. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 7:1-7:18, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{plambeck_et_al:OASIcs.DX.2025.7,
author = {Plambeck, Swantje and Schmidt, Maximilian and Trav\'{e}-Massuy\`{e}s, Louise and Fey, Goerschwin},
title = {{One-Shot Learning in Hybrid System Identification: A New Modular Paradigm}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {7:1--7:18},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.7},
URN = {urn:nbn:de:0030-drops-247969},
doi = {10.4230/OASIcs.DX.2025.7},
annote = {Keywords: Hybrid System, Model Learning, Symbolic Regression}
}
Document
Safe to Fly? Real-Time Flight Mission Feasibility Assessment for Drone Package Delivery Operations
Abstract
Ensuring flight safety for small unmanned aerial systems (sUAS) requires continuous in-flight monitoring and decision-making, as unexpected events can alter power consumption and deplete battery energy faster than anticipated. Such events may result in insufficient battery capacity to complete a mission, thereby compromising flight safety. In this paper, we present an online feasibility assessment and contingency management framework that continuously monitors the aircraft’s battery state and the energy required to complete the flight in real-time, which enables informed decision-making to enhance flight safety. The framework consists of two main components: power consumption prediction and battery voltage trajectory prediction. The power consumption prediction is conducted using a model that is based on momentum theory, while the voltage trajectory prediction is performed using a Neural Ordinary Differential Equation (Neural ODE)-based data-driven model. By integrating these two components, the framework evaluates the feasibility of a flight mission in real time and determines whether to proceed with the mission or initiate rerouting. We evaluate the framework’s performance in a drone delivery scenario in the Dallas–Fort Worth (DFW) area, where the aircraft encounters an unexpected energy depletion event mid-flight. The proposed framework is tasked with assessing the feasibility of completing the mission and, if necessary, rerouting the aircraft for an emergency landing. The results demonstrate that the framework accurately and efficiently detects energy insufficiencies in real-time and re-routes the aircraft to a [3] predefined emergency landing site.
Cite as
Abenezer Taye, Austin Coursey, Marcos Quinones-Grueiro, Chao Hu, Gautam Biswas, and Peng Wei. Safe to Fly? Real-Time Flight Mission Feasibility Assessment for Drone Package Delivery Operations. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 8:1-8:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{taye_et_al:OASIcs.DX.2025.8,
author = {Taye, Abenezer and Coursey, Austin and Quinones-Grueiro, Marcos and Hu, Chao and Biswas, Gautam and Wei, Peng},
title = {{Safe to Fly? Real-Time Flight Mission Feasibility Assessment for Drone Package Delivery Operations}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {8:1--8:20},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.8},
URN = {urn:nbn:de:0030-drops-247970},
doi = {10.4230/OASIcs.DX.2025.8},
annote = {Keywords: Battery Modeling, Neural ODE, Unmanned Aerial Vehicles}
}
Document
Optimized Spectral Fault Receptive Fields for Diagnosis-Informed Prognosis
Abstract
This paper introduces Spectral Fault Receptive Fields (SFRFs), a biologically inspired technique for degradation state assessment in bearing fault diagnosis and remaining useful life (RUL) estimation. Drawing on the center-surround organization of retinal ganglion cell receptive fields, we propose a frequency-domain feature extraction algorithm that enhances the detection of fault signatures in vibration signals. SFRFs are designed as antagonistic spectral filters centered on characteristic fault frequencies, with inhibitory surrounds that enable robust characterization of incipient faults under variable operating conditions. A multi-objective evolutionary optimization strategy based on NSGA-II algorithm is employed to tune the receptive field parameters by simultaneously minimizing RUL prediction error, maximizing feature monotonicity, and promoting smooth degradation trajectories. The method is demonstrated on the XJTU-SY bearing run-to-failure dataset, confirming its suitability for constructing condition indicators in health monitoring applications. Key contributions include: (i) the introduction of SFRFs, inspired by the biology of vision in the primate retina; (ii) an evolutionary optimization framework guided by condition monitoring and prognosis criteria; and (iii) experimental evidence supporting the detection of early-stage faults and their precursors. Furthermore, we confirm that our diagnosis-informed spectral representation achieves accurate RUL prediction using a bagging regressor. The results highlight the interpretability and principled design of SFRFs, bridging signal processing, biological sensing principles, and data-driven prognostics in rotating machinery.
Cite as
Stan Muñoz Gutiérrez and Franz Wotawa. Optimized Spectral Fault Receptive Fields for Diagnosis-Informed Prognosis. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 9:1-9:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{munozgutierrez_et_al:OASIcs.DX.2025.9,
author = {Mu\~{n}oz Guti\'{e}rrez, Stan and Wotawa, Franz},
title = {{Optimized Spectral Fault Receptive Fields for Diagnosis-Informed Prognosis}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {9:1--9:20},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.9},
URN = {urn:nbn:de:0030-drops-247986},
doi = {10.4230/OASIcs.DX.2025.9},
annote = {Keywords: Health Perception, Spectral Fault Receptive Fields, Remaining Useful Life, Incipient Fault Diagnosis, Prognostics and Health Management, Condition Monitoring, Evolutionary Multi-Objective Optimization, Bagged Regression Tree Ensemble, Bearing Fault Diagnosis}
}
Document
Automating Control System Design: Using Language Models for Expert Knowledge in Decentralized Controller Auto-Tuning
Abstract
Fully-automated optimal controller design for engineering systems is a challenging task. While, optimization-based, automated control parameter tuning techniques have been widely discussed in the literature, most works do not discuss expert knowledge requirements for system design, which result in significant human intervention. In this work, we discuss a multistage controller tuning framework for decentralized control that highlights expert knowledge requirements in automated controller design. We propose a methodology to automate the input-output pairing and stage definition steps in the framework using Large Language Models (LLMs) for a family of multi-tank benchmarks. We achieve this by proposing a mathematical language to describe the system and design an algorithm to bind this mathematical representation to the input prompt space of an LLM. We demonstrate that our methodology can produce consistent expert knowledge outputs from the LLM with over 97% accuracy for the multi-tank benchmarks. We also empirically show that, correct stage definition by the LLM can improve tuned controller performance by up to 52%.
Cite as
Marlon J. Ares-Milian, Gregory Provan, and Marcos Quinones-Grueiro. Automating Control System Design: Using Language Models for Expert Knowledge in Decentralized Controller Auto-Tuning. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 10:1-10:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{aresmilian_et_al:OASIcs.DX.2025.10,
author = {Ares-Milian, Marlon J. and Provan, Gregory and Quinones-Grueiro, Marcos},
title = {{Automating Control System Design: Using Language Models for Expert Knowledge in Decentralized Controller Auto-Tuning}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {10:1--10:20},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.10},
URN = {urn:nbn:de:0030-drops-247996},
doi = {10.4230/OASIcs.DX.2025.10},
annote = {Keywords: controller auto-tuning, automated system design, large language models}
}
Document
A Data-Driven Particle Filter Approach for System-Level Prediction of Remaining Useful Life
Abstract
Accurate estimation of the remaining useful life (RUL) of industrial systems is a critical component of predictive maintenance strategies. This work presents a data-driven method for RUL prediction that also quantifies uncertainty, drawing inspiration from model-based particle filtering techniques. Instead of simulating system state transitions, we model degradation as a stochastic process governed by performance metrics and use a Bayesian particle filtering framework to infer its underlying parameters. Our approach bypasses traditional state-space modeling by directly estimating the end-of-life distribution from observed performance data. Key characteristics of the filter, such as propagation noise and observation correction strength, are adapted over time based on current observations and past predictive performance, enabling better capture of future uncertainty. We evaluate the proposed method using an unmanned aerial vehicle simulation dataset developed for system-level prognostics research, which includes high-fidelity degradation signals and ground-truth system performance metrics for validating predictive accuracy.
Cite as
Abel Diaz-Gonzalez, Austin Coursey, Marcos Quinones-Grueiro, and Gautam Biswas. A Data-Driven Particle Filter Approach for System-Level Prediction of Remaining Useful Life. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 11:1-11:13, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{diazgonzalez_et_al:OASIcs.DX.2025.11,
author = {Diaz-Gonzalez, Abel and Coursey, Austin and Quinones-Grueiro, Marcos and Biswas, Gautam},
title = {{A Data-Driven Particle Filter Approach for System-Level Prediction of Remaining Useful Life}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {11:1--11:13},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.11},
URN = {urn:nbn:de:0030-drops-248006},
doi = {10.4230/OASIcs.DX.2025.11},
annote = {Keywords: remaining useful life, particle filter methods, data-driven methods, system-level prognostics, performance metrics}
}
Document
GEMMA-FD: Zero-Shot Fault Detection in Heat Pumps Using Multimodal Language Models
Abstract
Fault detection in heating systems is critical for ensuring energy efficiency and operational reliability. Traditional approaches rely on labeled fault data and expert-defined rules, which are often unavailable or costly to obtain. We introduce GEMMA-FD (GEMMA for Fault Detection), a novel zero-shot framework for fault detection in heat pumps that leverages large language models (LLMs) without requiring labeled anomalies or predefined fault signatures. Our method transforms multivariate sensor time series into structured natural language prompts and augments them with visual features, such as line plots of key variables, to facilitate multimodal reasoning. Using GEMMA-3, an open-weight multimodal LLM, we classify heat pump system states as either normal or faulty. Experiments on a real-world heat pump dataset show that GEMMA-FD can identify unseen faults with reasonable precision, although its performance remains lower than a supervised XGBoost baseline trained on the same prompts. Specifically, GEMMA-FD achieves a macro-F1 score of 0.252, compared to 0.69 for XGBoost, underscoring the trade-off between generalization and targeted accuracy. Nevertheless, GEMMA-FD demonstrates the potential of foundation models for interpretable, multilingual fault detection in cyber-physical systems, while highlighting the need for prompt engineering, few-shot augmentation, and multimodal inputs to improve the classification of rare and complex fault types.
Cite as
Herbert Muehlburger and Franz Wotawa. GEMMA-FD: Zero-Shot Fault Detection in Heat Pumps Using Multimodal Language Models. In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 12:1-12:17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{muehlburger_et_al:OASIcs.DX.2025.12,
author = {Muehlburger, Herbert and Wotawa, Franz},
title = {{GEMMA-FD: Zero-Shot Fault Detection in Heat Pumps Using Multimodal Language Models}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {12:1--12:17},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.12},
URN = {urn:nbn:de:0030-drops-248015},
doi = {10.4230/OASIcs.DX.2025.12},
annote = {Keywords: fault detection, anomaly detection, cyber-physical systems, HVAC, heat pumps, energy systems, large language models, zero-shot learning, open-weight LLMs, interpretable AI, multimodal prompts, smart energy}
}
Document
Short Paper
Beyond Dynamic Bayesian Networks: Fusing Temporal Logic Monitors with Probabilistic Diagnosis (Short Paper)
Abstract
Conventional diagnostic systems often fail to account for temporal dynamics - such as duration, frequency, or sequence of events - which are critical for accurate fault assessment. Existing solutions that model time, like Dynamic Bayesian Networks (DBNs), typically suffer from computational complexity and scalability issues.
This paper introduces a hybrid diagnostic architecture that integrates a standard Bayesian Networks (BNs) with a powerful temporal reasoner R2U2 (Realizable Responsive Unobtrusive Unit). By decoupling temporal logic from probabilistic inference, our approach allows the specialized R2U2 engine to efficiently process complex time-dependent conditions and provide nuanced inputs to the BNs. The result is a more scalable, flexible, and robust framework for diagnosing failures in systems where temporal behavior is a key factor. The paper will detail this architecture, its generation from system models, and demonstrate its capabilities using a UAV electric powertrain example.
Cite as
Chetan Kulkarni and Johann Schumann. Beyond Dynamic Bayesian Networks: Fusing Temporal Logic Monitors with Probabilistic Diagnosis (Short Paper). In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 13:1-13:17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{kulkarni_et_al:OASIcs.DX.2025.13,
author = {Kulkarni, Chetan and Schumann, Johann},
title = {{Beyond Dynamic Bayesian Networks: Fusing Temporal Logic Monitors with Probabilistic Diagnosis}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {13:1--13:17},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.13},
URN = {urn:nbn:de:0030-drops-248022},
doi = {10.4230/OASIcs.DX.2025.13},
annote = {Keywords: Bayesian diagnostic network, temporal logic, fault diagnosis, temporal reasoning, probabilistic inference, scalability}
}
Document
DX Competition
The DX Competition 2025 and Its Benchmarks (DX Competition)
Abstract
Fault diagnosis has been addressed in many research communities, leading to a variety of available fault diagnosis techniques. Deciding as a user which fault diagnosis methods are suitable for a specific application is thus a nontrivial task. Benchmarks can provide the community with a holistic understanding of the landscape of newly developed and available fault diagnosis methods when making this decision. After a long hiatus, we revived the DX Competition with three fault diagnosis benchmarks: SLIDe, LUMEN, and LiU-ICE. The purpose of the benchmarks is to inspire fault diagnosis research with challenging problems in cyber-physical systems relevant for industry. The benchmarks share a common code structure and we used similar performance metrics in order to simplify the adaptation of diagnosis system solutions to the different case studies.
Cite as
Ingo Pill, Daniel Jung, Eldin Kurudzija, Anna Sztyber-Betley, Michał Syfert, Kai Dresia, Günther Waxenegger-Wilfing, and Johan de Kleer. The DX Competition 2025 and Its Benchmarks (DX Competition). In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 14:1-14:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{pill_et_al:OASIcs.DX.2025.14,
author = {Pill, Ingo and Jung, Daniel and Kurudzija, Eldin and Sztyber-Betley, Anna and Syfert, Micha{\l} and Dresia, Kai and Waxenegger-Wilfing, G\"{u}nther and de Kleer, Johan},
title = {{The DX Competition 2025 and Its Benchmarks}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {14:1--14:19},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.14},
URN = {urn:nbn:de:0030-drops-248030},
doi = {10.4230/OASIcs.DX.2025.14},
annote = {Keywords: Diagnosis, Algorithms, Evaluation}
}
Document
DX Competition
Data-Driven Fault Detection and Isolation Enhanced with System Structural Relationships (DX Competition)
Abstract
Fault detection and isolation are becoming increasingly important as modern systems become more complex. To encourage the development of new fault detection solutions that can operate with limited noisy data and an incomplete mathematical model, the DX 2025 LiU-ICE competition for diagnosis of the air path of an internal combustion engine was introduced. In this paper, we present our winning solution to this competition. Our fault detection architecture starts with a semi-supervised Transformer Autoencoder trained to reconstruct nominal data. Detected faults are then passed through a rule-based fault persistence filter that aims to suppress false positives. Once a fault is detected, we use four neural networks trained to estimate features determined from structural analysis of a partial system model. The residuals of these networks are fed to a supervised fault classification network that estimates the fault probabilities. With this architecture, we achieved an 87% detection rate with a 0% false alarm rate on the provided competition data. Additionally, our isolation architecture assigned the correct fault 73.8% probabilty on average. On unseen competition data from a new driving cycle, we achieved a 100% detection rate and assigned the correct fault 66.2% probability on average. On the other hand, the Transformer Autoencoder failed to transfer to the new driving conditions, causing many false alarms. We discuss ways future work can reduce this.
Cite as
Austin Coursey, Abel Diaz-Gonzalez, Marcos Quinones-Grueiro, and Gautam Biswas. Data-Driven Fault Detection and Isolation Enhanced with System Structural Relationships (DX Competition). In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 15:1-15:17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{coursey_et_al:OASIcs.DX.2025.15,
author = {Coursey, Austin and Diaz-Gonzalez, Abel and Quinones-Grueiro, Marcos and Biswas, Gautam},
title = {{Data-Driven Fault Detection and Isolation Enhanced with System Structural Relationships}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {15:1--15:17},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.15},
URN = {urn:nbn:de:0030-drops-248043},
doi = {10.4230/OASIcs.DX.2025.15},
annote = {Keywords: fault detection, fault isolation, autoencoder}
}
Document
PhD Panel
Unsupervised Multimodal Learning for Fault Diagnosis and Prognosis - Application to Radiotherapy Systems (PhD Panel)
Abstract
Modern complex systems, such as radiotherapy machines, require robust strategies for fault detection, diagnosis, and prognosis to ensure operational continuity and patient safety. While data-driven methods have gained traction, few studies address diagnostic and prognostic tasks using multimodal operational data under unsupervised or semi-supervised learning settings. This gap is particularly critical given the scarcity of labeled failure data in real-world environments. This work aims to design a unified approach for fault detection, diagnosis, and prognosis using multimodal data in the absence of complete labeling. To this end, autoencoders (AEs) are employed due to their suitability for unsupervised and self-supervised learning, flexibility in handling heterogeneous data, and ability to construct latent representations optimized for various downstream tasks. A specific implementation based on a Long Short-Term Memory β-Variational Autoencoder (LSTM-β-VAE) was developed to detect anomalies in machine logs. This framework is applied to TomoTherapy® systems - a highly complex and under-explored use case within the radiotherapy domain. Initial results demonstrate strong anomaly detection performance on both a public benchmark dataset (HDFS) and a proprietary dataset derived from real-world TomoTherapy® machine faults. Beyond methodology, the paper includes a concise literature review of multimodal learning and data-driven diagnosis and prognosis with a focus on AEs. Based on this review, key research directions are identified for the continuation of the thesis, especially the integration of explainable AI as a means to enhance diagnosis capabilities in the absence of labeled faults.
Cite as
Kélian Poujade, Louise Travé-Massuyès, Jérémy Pirard, and Laure Vieillevigne. Unsupervised Multimodal Learning for Fault Diagnosis and Prognosis - Application to Radiotherapy Systems (PhD Panel). In 36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025). Open Access Series in Informatics (OASIcs), Volume 136, pp. 16:1-16:17, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)
Copy BibTex To Clipboard
@InProceedings{poujade_et_al:OASIcs.DX.2025.16,
author = {Poujade, K\'{e}lian and Trav\'{e}-Massuy\`{e}s, Louise and Pirard, J\'{e}r\'{e}my and Vieillevigne, Laure},
title = {{Unsupervised Multimodal Learning for Fault Diagnosis and Prognosis - Application to Radiotherapy Systems}},
booktitle = {36th International Conference on Principles of Diagnosis and Resilient Systems (DX 2025)},
pages = {16:1--16:17},
series = {Open Access Series in Informatics (OASIcs)},
ISBN = {978-3-95977-394-2},
ISSN = {2190-6807},
year = {2025},
volume = {136},
editor = {Quinones-Grueiro, Marcos and Biswas, Gautam and Pill, Ingo},
publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
address = {Dagstuhl, Germany},
URL = {https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2025.16},
URN = {urn:nbn:de:0030-drops-248058},
doi = {10.4230/OASIcs.DX.2025.16},
annote = {Keywords: Artificial Intelligence, Diagnosis, Prognosis, Radiotherapy machines}
}