Federated Learning for Efficient Condition Monitoring and Anomaly Detection in Industrial Cyber-Physical Systems

2025-01-28

AI Summary

To address insufficient robustness in anomaly detection for industrial cyber-physical systems—caused by sensor heterogeneity, frequent node failures, and measurement noise—this paper proposes a lightweight federated learning framework. The method integrates federated learning with Mann–Whitney U statistical testing and fault-aware resource scheduling. Key contributions include: (1) an adaptive model aggregation mechanism grounded in sensor reliability modeling; (2) a dynamic node selection strategy; and (3) a Weibull distribution–driven fault-tolerant checkpointing technique. Evaluated on NASA bearing and hydraulic system datasets, the framework achieves 99.5% AUC-ROC. It maintains stable detection accuracy under random node failures and significantly improves computational efficiency (p < 0.05). Results demonstrate its effectiveness and robustness in resource-constrained, high-failure-rate operational environments.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Natural Language Processing: Safety and Robustness
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Detecting and localizing anomalies in cyber-physical systems (CPS) has become increasingly challenging as systems grow in complexity, particularly due to varying sensor reliability and node failures in distributed environments. While federated learning (FL) provides a foundation for distributed model training, existing approaches often lack mechanisms to address these CPS-specific challenges. This paper introduces an enhanced FL framework with three key innovations: adaptive model aggregation based on sensor reliability, dynamic node selection for resource optimization, and Weibull-based checkpointing for fault tolerance. The proposed framework ensures reliable condition monitoring while tackling the computational and reliability challenges of industrial CPS deployments. Experiments on the NASA Bearing and Hydraulic System datasets demonstrate superior performance compared to state-of-the-art FL methods, achieving 99.5% AUC-ROC in anomaly detection and maintaining accuracy even under node failures. Statistical validation using the Mann-Whitney U test confirms significant improvements, with a p-value less than 0.05, in both detection accuracy and computational efficiency across various operational scenarios.

Problem

• Anomaly Detection
• Complex Cyber-Physical Systems
• Industrial Environment

Innovation

• Dynamic Model Adjustment
• Optimized Resource Utilization
• Robustness Enhancement with Weibull Distribution