Few-Shot Learning Approaches for Fault Diagnosis Using Vibration Data: A Comprehensive Review

Abstract

Fault detection and diagnosis play a crucial role in ensuring the reliability and safety of modern industrial systems. For safety and cost considerations, critical equipment and systems in industrial operations are typically not allowed to operate in severe fault states. Moreover, obtaining labeled samples for fault diagnosis often requires significant human effort. This results in limited labeled data for many application scenarios. Thus, the focus of attention has shifted towards learning from a small amount of data. Few-shot learning has emerged as a solution to this challenge, aiming to develop models that can effectively solve problems with only a few samples. This approach has gained significant traction in various fields, such as computer vision, natural language processing, audio and speech, reinforcement learning, robotics, and data analysis. Surprisingly, despite its wide applicability, there have been limited investigations or reviews on applying few-shot learning to the field of mechanical fault diagnosis. In this paper, we provide a comprehensive review of the relevant work on few-shot learning in mechanical fault diagnosis from 2018 to September 2023. By examining the existing research, we aimed to shed light on the potential of few-shot learning in this domain and offer valuable insights for future research directions.

A digital twin library of mechanical transmission system for the application of small sample fault diagnosis problem

“…one-stage and twostage gear systems, were constructed based on the TSDT module library. The dynamic parameters of the TSDT are detailed in table 2, and the characteristic frequencies (referring to [9]) are shown in table 3. The vibration response of the TSDT is determined by solving the model using the Dassl algorithm, with an error tolerance set to 10 −8 and a step size of 10 −5 .…”

“…The available small sample data cannot satisfy the data-hungry nature of intelligent fault diagnosis. Therefore, the small sample problem [9], with only a few samples for training, is gradually being focused on by researchers. Currently, the approaches to the small sample problem can be divided into two categories: (1) generating the augmented data based on existing data.…”

Enhancing Fault Diagnosis in Industrial Processes through Adversarial Task Augmented Sequential Meta-Learning

“…Despite their excellence, these methods commonly exhibit weaknesses such as poor generalization capabilities, sensitivity to adversarial examples and high algorithmic complexity, which can lead to suboptimal performance in industrial applications that demand rapid and accurate diagnostics. Recent studies have shifted focus to addressing FSL fault-diagnosis challenges through meta-learning [14][15][16], with a significant proportion of recent research in time-series signal fault diagnosis concentrating on this approach [17]. However, the practical utility of meta-learning is limited by its high dependency on data quality and distribution, which can adversely affect performance in industrial settings due to data noise and outliers [18].…”