An Explainable GNN Framework for Component-Level Anomaly Diagnosis

2026-08-10

AI Summary

This work addresses a critical limitation in anomaly diagnosis for industrial systems, where existing approaches often misattribute anomalies to individual sensors while overlooking disruptions in the dynamic interactions among system components. To overcome this sensor-level attribution paradigm, the authors propose an interpretable graph neural network framework that treats anomalies as symptoms of altered influence relationships between components, thereby enabling root-cause localization at the component level. By explicitly modeling sensor dependencies and integrating explainability techniques, the method identifies key influence pathways and pinpoints the true faulty components. Experimental results demonstrate that the proposed approach significantly outperforms state-of-the-art methods in both diagnostic accuracy and interpretability, achieving precise identification and prioritization of faulty components within complex industrial systems.

Abstract

Industrial processes are complex systems composed of multiple interacting sensors that generate multivariate time series (MTS). Detecting anomalies in such systems is critical for reliability and safety, yet understanding their origin is equally important. Existing Graph Neural Network (GNN)based methods for anomaly detection primarily focus on sensor-level deviations and either attribute anomalies directly to the deviating sensors. When diagnosis is attempted, generally, the most deviated sensor is identified as a root cause of a system fault. However, in many industrial systems, anomalies do not arise from faulty sensors but from disruptions in the influences governing the system dynamics. We propose an explainable GNN-based anomaly detection framework that shifts the perspective from sensor-level anomalies to component-level diagnosis, hypothesizing that anomalous measurements are symptoms of altered inter-sensor influences. Experiments show that the method effectively identifies and prioritizes the true faulty components, providing interpretable insights into system failures.

Problem

• anomaly diagnosis
• component-level
• graph neural network
• industrial systems
• multivariate time series

Innovation

• Explainable GNN
• Component-Level Diagnosis
• Anomaly Detection
• Multivariate Time Series
• Inter-Sensor Influence