ABIGX: A Unified Framework for eXplainable Fault Detection and Classification

TL;DR

ABIGX is a novel unified framework that enhances explainability in fault detection and classification by integrating adversarial reconstruction and gradient-based explanations, outperforming existing methods.

Contribution

It introduces ABIGX, the first explanation framework providing variable contributions for general FDC models, and addresses fault class smearing effectively.

Findings

ABIGX outperforms existing explanation methods in accuracy.

Theoretical link between ABIGX and traditional fault diagnosis methods.

Experimental results demonstrate ABIGX's superiority in explanation quality.

Abstract

For explainable fault detection and classification (FDC), this paper proposes a unified framework, ABIGX (Adversarial fault reconstruction-Based Integrated Gradient eXplanation). ABIGX is derived from the essentials of previous successful fault diagnosis methods, contribution plots (CP) and reconstruction-based contribution (RBC). It is the first explanation framework that provides variable contributions for the general FDC models. The core part of ABIGX is the adversarial fault reconstruction (AFR) method, which rethinks the FR from the perspective of adversarial attack and generalizes to fault classification models with a new fault index. For fault classification, we put forward a new problem of fault class smearing, which intrinsically hinders the correct explanation. We prove that ABIGX effectively mitigates this problem and outperforms the existing gradient-based explanation methods. For fault detection, we theoretically bridge ABIGX with conventional fault diagnosis methods by proving that CP and RBC are the linear specifications of ABIGX. The experiments evaluate the explanations of FDC by quantitative metrics and intuitive illustrations, the results of which show the general superiority of ABIGX to other advanced explanation methods.