Generalized Out-of-distribution Fault Diagnosis (GOOFD) via Internal Contrastive Learning

TL;DR

This paper introduces GOOFD, a unified framework for fault diagnosis in industrial machines that leverages internal contrastive learning and Mahalanobis distance to handle multiple fault detection tasks more effectively.

Contribution

It proposes a novel generalized fault diagnosis framework and a unified method based on internal contrastive learning and Mahalanobis distance, improving multi-task fault detection performance.

Findings

Outperforms existing single-task methods in fault diagnosis accuracy.

Effective on both benchmark and real-world datasets.

Demonstrates robustness across diverse fault types.

Abstract

Fault diagnosis is crucial in monitoring machines within industrial processes. With the increasing complexity of working conditions and demand for safety during production, diverse diagnosis methods are required, and an integrated fault diagnosis system capable of handling multiple tasks is highly desired. However, the diagnosis subtasks are often studied separately, and the current methods still need improvement for such a generalized system. To address this issue, we propose the Generalized Out-of-distribution Fault Diagnosis (GOOFD) framework to integrate diagnosis subtasks. Additionally, a unified fault diagnosis method based on internal contrastive learning and Mahalanobis distance is put forward to underpin the proposed generalized framework. The method involves feature extraction through internal contrastive learning and outlier recognition based on the Mahalanobis distance. Our proposed method can be applied to multiple faults diagnosis tasks and achieve better performance than the existing single-task methods. Experiments are conducted on benchmark and practical process datasets, indicating the effectiveness of the proposed framework.