Interpretable Early Failure Detection via Machine Learning and Trace Checking-based Monitoring

2025-08-25

AI Summary

Existing runtime monitoring of Signal Temporal Logic (STL) formulas requires constructing doubly exponential-sized deterministic automata, hindering real-time, early fault detection. Method: This paper proposes a lightweight monitoring framework integrating machine learning and trajectory checking. First, it restricts STL to pure past-time co-safe fragments, reducing monitoring to a polynomial-time trajectory-checking problem. Second, it employs genetic programming to automatically learn interpretable temporal properties from historical trajectories. Third, it leverages vectorized implementation and GPU acceleration to maximize throughput. Results: Experiments demonstrate that our approach outperforms state-of-the-art methods across detection accuracy, latency, and interpretability, with key metrics improved by 2%–10%. The framework significantly enhances early fault identification capability while maintaining computational efficiency and transparency.

Technology Category

• Machine Learning: Statistical Relational/Logic Learning
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Monitoring is a runtime verification technique that allows one to check whether an ongoing computation of a system (partial trace) satisfies a given formula. It does not need a complete model of the system, but it typically requires the construction of a deterministic automaton doubly exponential in the size of the formula (in the worst case), which limits its practicality. In this paper, we show that, when considering finite, discrete traces, monitoring of pure past (co)safety fragments of Signal Temporal Logic (STL) can be reduced to trace checking, that is, evaluation of a formula over a trace, that can be performed in time polynomial in the size of the formula and the length of the trace. By exploiting such a result, we develop a GPU-accelerated framework for interpretable early failure detection based on vectorized trace checking, that employs genetic programming to learn temporal properties from historical trace data. The framework shows a 2-10% net improvement in key performance metrics compared to the state-of-the-art methods.

Problem

• Reducing monitoring complexity for runtime verification
• Enabling efficient early failure detection via trace checking
• Learning temporal properties from historical data interpretably

Innovation

• GPU-accelerated vectorized trace checking framework
• Genetic programming learns temporal properties from data
• Polynomial-time monitoring via trace checking reduction