Explainable AI guided unsupervised fault diagnostics for high-voltage circuit breakers

2025-07-25

AI Summary

In online condition monitoring of high-voltage circuit breakers, the absence of authentic fault labels, limited coverage of underlying failure mechanisms by conventional threshold-based methods, and reliance on offline detection hinder practical deployment. Method: This paper proposes an unsupervised fault detection and segmentation framework leveraging synchronized vibration and acoustic signals. Trained exclusively on healthy-state data, it integrates self-supervised representation learning with anomaly segmentation for fine-grained localization of deviations. Additionally, explainable AI (XAI) is incorporated to perform physics-informed attribution analysis of unlabeled anomalies, facilitating identification of aging or failing components. Results: Evaluated on real-world experimental data, the method accurately detects subtle health deviations, discriminates among multiple latent fault patterns, and significantly enhances the practicality and reliability of online monitoring—without requiring fault annotations or manual threshold tuning.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Segmentation
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Commercial high-voltage circuit breaker (CB) condition monitoring systems rely on directly observable physical parameters such as gas filling pressure with pre-defined thresholds. While these parameters are crucial, they only cover a small subset of malfunctioning mechanisms and usually can be monitored only if the CB is disconnected from the grid. To facilitate online condition monitoring while CBs remain connected, non-intrusive measurement techniques such as vibration or acoustic signals are necessary. Currently, CB condition monitoring studies using these signals typically utilize supervised methods for fault diagnostics, where ground-truth fault types are known due to artificially introduced faults in laboratory settings. This supervised approach is however not feasible in real-world applications, where fault labels are unavailable. In this work, we propose a novel unsupervised fault detection and segmentation framework for CBs based on vibration and acoustic signals. This framework can detect deviations from the healthy state. The explainable artificial intelligence (XAI) approach is applied to the detected faults for fault diagnostics. The specific contributions are: (1) we propose an integrated unsupervised fault detection and segmentation framework that is capable of detecting faults and clustering different faults with only healthy data required during training (2) we provide an unsupervised explainability-guided fault diagnostics approach using XAI to offer domain experts potential indications of the aged or faulty components, achieving fault diagnostics without the prerequisite of ground-truth fault labels. These contributions are validated using an experimental dataset from a high-voltage CB under healthy and artificially introduced fault conditions, contributing to more reliable CB system operation.

Problem

• Unsupervised fault detection for circuit breakers without labeled data
• Explainable AI diagnostics for identifying faulty components
• Online condition monitoring using vibration and acoustic signals

Innovation

• Unsupervised fault detection using vibration signals
• Explainable AI for fault diagnostics without labels
• Integrated framework clusters faults with healthy data