Safety Verification and Optimization in Industrial Drive Systems

2025-03-27

AI Summary

To address the challenges of safety verification difficulty and low diagnostic efficiency arising from stochastic faults in industrial Basic Drive Modules (BDMs), this paper proposes a safety-enhancement methodology integrating formal modeling with data-driven optimization. We pioneer the synergistic use of Uppaal Stratego model checking and reinforcement learning for automated synthesis of safety-critical control strategies; based on timed automata models, our approach generates optimal strategies satisfying a 90% safety-failure suppression threshold. The method achieves rigorous formal verification of both functional and safety requirements on a real-world BDM platform, improving safety-failure detection rate to 90% and significantly enhancing system reliability and safety assurance. The core contribution is a verifiable–optimizable closed-loop framework that overcomes the limitations of conventional static verification and empirical tuning.

Technology Category

• Reasoning under Uncertainty: Stochastic Optimization
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Safety and reliability are crucial in industrial drive systems, where hazardous failures can have severe consequences. Detecting and mitigating dangerous faults on time is challenging due to the stochastic and unpredictable nature of fault occurrences, which can lead to limited diagnostic efficiency and compromise safety. This paper optimizes the safety and diagnostic performance of a real-world industrial Basic Drive Module(BDM) using Uppaal Stratego. We model the functional safety architecture of the BDM with timed automata and formally verify its key functional and safety requirements through model checking to eliminate unwanted behaviors. Considering the formally verified correct model as a baseline, we leverage the reinforcement learning facility in Uppaal Stratego to optimize the safe failure fraction to the 90 % threshold, improving fault detection ability. The promising results highlight strong potential for broader safety applications in industrial automation.

Problem

• Optimizing safety and diagnostic performance in industrial drive systems
• Formally verifying functional safety architecture to eliminate unwanted behaviors
• Improving fault detection ability to meet 90% safe failure threshold

Innovation

• Uppaal Stratego for safety verification
• Timed automata model checking
• Reinforcement learning optimizes fault detection