Process mining-driven modeling and simulation to enhance fault diagnosis in cyber-physical systems

2025-06-26

AI Summary

Conventional fault diagnosis in Cyber-Physical Systems (CPS) relies heavily on manual modeling, suffers from poor interpretability, and lacks support for root-cause analysis and digital twin integration. Method: This paper proposes an end-to-end unsupervised framework that jointly leverages multivariate time-series collective anomaly detection, process mining (via Inductive Miner), and stochastic simulation to automatically synthesize executable, temporally distributed Petri net models directly from raw sensor data. Contribution/Results: It is the first work to couple process mining with stochastic simulation for CPS fault behavior modeling—enabling interpretable fault dictionary construction and predictive maintenance. Evaluated on the Robotic Arm Dataset, the method achieves significantly improved fault classification accuracy, precisely reproduces canonical failure patterns, and successfully enables digital twin deployment.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing

Abstract

Fault diagnosis in Cyber-Physical Systems (CPSs) is essential for ensuring system dependability and operational efficiency by accurately detecting anomalies and identifying their root causes. However, the manual modeling of faulty behaviors often demands extensive domain expertise and produces models that are complex, error-prone, and difficult to interpret. To address this challenge, we present a novel unsupervised fault diagnosis methodology that integrates collective anomaly detection in multivariate time series, process mining, and stochastic simulation. Initially, collective anomalies are detected from low-level sensor data using multivariate time-series analysis. These anomalies are then transformed into structured event logs, enabling the discovery of interpretable process models through process mining. By incorporating timing distributions into the extracted Petri nets, the approach supports stochastic simulation of faulty behaviors, thereby enhancing root cause analysis and behavioral understanding. The methodology is validated using the Robotic Arm Dataset (RoAD), a widely recognized benchmark in smart manufacturing. Experimental results demonstrate its effectiveness in modeling, simulating, and classifying faulty behaviors in CPSs. This enables the creation of comprehensive fault dictionaries that support predictive maintenance and the development of digital twins for industrial environments.

Problem

• Automating fault diagnosis in cyber-physical systems without manual modeling
• Detecting and analyzing anomalies in multivariate time-series sensor data
• Enhancing root cause analysis through process mining and stochastic simulation

Innovation

• Unsupervised fault diagnosis with anomaly detection
• Process mining transforms anomalies into event logs
• Stochastic simulation enhances root cause analysis