Unlocking the power of knowledge for few-shot fault diagnosis: A review from a knowledge perspective

Abstract

Fault diagnosis has long been a topic of great interest, owing to a disaster that can result from the faults of safety-critical systems. In recent years, researchers have realized that fault diagnosis of real equipment, and more precisely the fault identification task, is not simply a pattern recognition problem but instead, a few-shot classification problem. Despite valuable publications on few-shot fault diagnosis (FSFD), these surveys have primarily focused on a methodological perspective. Furthermore, few articles have been published to provide a comprehensive summary of FSFD methods from a knowledge perspective. This paper proposes a comprehensive taxonomy for FSFD methods that classifies them into data-based and knowledge-based approaches, as knowledge and data represent different levels in the knowledge perspective. The paper focuses on the knowledge-based approaches, which include knowledge embedding and knowledge discovery. These approaches aim to leverage the knowledge available in limited datasets and auxiliary datasets. The paper examines various knowledge representations such as predefined rules, learning biases, network parameters, and feature representations. Furthermore, the study assesses potential challenges and future research directions from a knowledge perspective. Finally, some public datasets and code repositories are summarized. This paper can serve as a useful reference for advancing FSFD research.