Class Incremental Fault Diagnosis under Limited Fault Data via Supervised Contrastive Knowledge Distillation

TL;DR

This paper introduces SCLIFD, a framework combining supervised contrastive knowledge distillation, prioritized exemplar replay, and random forest classification to improve class-incremental fault diagnosis, especially under limited and imbalanced data conditions.

Contribution

The paper proposes a novel SCLIFD framework that enhances feature learning, mitigates catastrophic forgetting, and handles class imbalance in incremental fault diagnosis.

Findings

SCLIFD outperforms existing methods on simulated and real-world datasets.

The framework effectively reduces catastrophic forgetting.

It demonstrates robustness across various imbalance ratios.

Abstract

Class-incremental fault diagnosis requires a model to adapt to new fault classes while retaining previous knowledge. However, limited research exists for imbalanced and long-tailed data. Extracting discriminative features from few-shot fault data is challenging, and adding new fault classes often demands costly model retraining. Moreover, incremental training of existing methods risks catastrophic forgetting, and severe class imbalance can bias the model's decisions toward normal classes. To tackle these issues, we introduce a Supervised Contrastive knowledge distiLlation for class Incremental Fault Diagnosis (SCLIFD) framework proposing supervised contrastive knowledge distillation for improved representation learning capability and less forgetting, a novel prioritized exemplar selection method for sample replay to alleviate catastrophic forgetting, and the Random Forest Classifier to address the class imbalance. Extensive experimentation on simulated and real-world industrial datasets across various imbalance ratios demonstrates the superiority of SCLIFD over existing approaches. Our code can be found at https://github.com/Zhang-Henry/SCLIFD_TII.