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.

翻译：针对可解释的故障检测与分类（FDC），本文提出了一种统一框架ABIGX（基于对抗性故障重建的集成梯度解释）。ABIGX源于先前成功故障诊断方法——贡献图（CP）与基于重建的贡献（RBC）的核心理念，是首个为通用FDC模型提供变量贡献的解释框架。其核心部分是对抗性故障重建（AFR）方法，该方法从对抗攻击视角重新审视故障重建，并借助新型故障指标将其推广至故障分类模型。针对故障分类，我们提出"故障类别混淆"这一新问题，该问题本质上阻碍了正确解释。我们证明ABIGX能有效缓解该问题，且性能优于现有基于梯度的解释方法。针对故障检测，我们通过证明CP与RBC是ABIGX的线性特例，在理论上将ABIGX与传统故障诊断方法建立了联系。实验通过量化指标与直观图示评估了FDC解释效果，结果表明ABIGX整体上优于其他先进解释方法。