DROPS

Document

DOI: 10.4230/OASIcs.DX.2026.12

Reinforcement Learning-Driven Predictive Maintenance Planning via Timed Automata Modeling

Authors: Ferhat Tamssaouet, Pauline Ribot, and Yannick Pencolé

Published in: OASIcs, Volume 148, 37th International Conference on Principles of Diagnosis and Resilient Systems (DX 2026)

Abstract

Predictive maintenance of multi-component systems requires decisions that account for both local component degradation and system-level redundancy. This paper proposes a formal framework for synthesizing interpretable maintenance policies from a system functional architecture. The system is modeled as a network of Dynamic Priced Timed Game Automata (DPTGA): each component automaton encodes degradation dynamics, stochastic failure windows, and repair and replacement costs, while a System Health Monitor automaton is automatically derived from the minimal cut sets of the functional architecture and detects system failure as soon as any cut set becomes unavailable. We execute the DPTGA semantics in an explicit-state simulator and optimize a compact threshold policy with the Cross-Entropy Method (CEM). The policy contains one age-fraction threshold per component and an embedded subsystem-safe predicate that forbids any preventive action that would immediately realize a cut set, making the learned strategy provably safe and directly interpretable as a rule-based maintenance plan. On a seven-component benchmark comprising a parallel subsystem and a 2-out-of-5 redundant block, the CEM policy reduces mean cumulative cost by 15% and median cost by 16% relative to the best rule-based heuristic (corrective, systematic, and condition-based maintenance), while maintaining a 98.7% system survival rate. The approach therefore provides a compact and explainable alternative to deep reinforcement learning for architecture-aware predictive maintenance.

Cite as

Ferhat Tamssaouet, Pauline Ribot, and Yannick Pencolé. Reinforcement Learning-Driven Predictive Maintenance Planning via Timed Automata Modeling. In 37th International Conference on Principles of Diagnosis and Resilient Systems (DX 2026). Open Access Series in Informatics (OASIcs), Volume 148, pp. 12:1-12:20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@InProceedings{tamssaouet_et_al:OASIcs.DX.2026.12,
  author =	{Tamssaouet, Ferhat and Ribot, Pauline and Pencol\'{e}, Yannick},
  title =	{{Reinforcement Learning-Driven Predictive Maintenance Planning via Timed Automata Modeling}},
  booktitle =	{37th International Conference on Principles of Diagnosis and Resilient Systems (DX 2026)},
  pages =	{12:1--12:20},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-455-0},
  ISSN =	{2190-6807},
  year =	{2026},
  volume =	{148},
  editor =	{Pill, Ingo and Zanella, Marina and Provan, Gregory},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/OASIcs.DX.2026.12},
  URN =		{urn:nbn:de:0030-drops-278260},
  doi =		{10.4230/OASIcs.DX.2026.12},
  annote =	{Keywords: System Remaining Useful Life, Predictive Maintenance, Timed Automata, Reinforcement Learning}
}

Document

Short Paper

DOI: 10.4230/OASIcs.DX.2024.27

On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)

Authors: Charles-Maxime Gauriat, Yannick Pencolé, Pauline Ribot, and Gregory Brouillet

Published in: OASIcs, Volume 125, 35th International Conference on Principles of Diagnosis and Resilient Systems (DX 2024)

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}
}

Search Results

Documents authored by Pencolé, Yannick

Reinforcement Learning-Driven Predictive Maintenance Planning via Timed Automata Modeling

Abstract

Cite as

On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)

Abstract

Cite as

Thanks for your feedback!

Could not send message