Interpretable multi-domain meta-transfer learning for few-shot fault diagnosis of rolling bearing under variable working conditions

In recent years, research on the intelligent fault diagnosis of rotating machinery has made remarkable progress, bringing considerable economic benefits to industrial production. However, in the industrial environment, the accuracy and stability of the diagnostic model face severe challenges due to the extremely limited fault data. Data augmentation methods have the capability to increase both the quantity and diversity of data without altering the key characteristics of the original data, which is particularly important for the development of intelligent fault diagnosis of rotating machinery under limited data conditions (IFD-RM-LDC). Despite the abundant achievements in research on data augmentation methods, there is a lack of systematic reviews and clear future development directions. Therefore, this paper systematically reviews and discusses data augmentation methods for IFD-RM-LDC. Firstly, existing data augmentation methods are categorized into three groups: synthetic minority over-sampling technique (SMOTE)-based methods, generative model-based methods, and data transformation-based methods. Then, these three methods are introduced in detail and discussed in depth: SMOTE-based methods synthesize new samples through a spatial interpolation strategy; generative model-based methods generate new samples according to the distribution characteristics of existing samples; data transformation-based methods generate new samples through a series of transformation operations. Finally, the challenges faced by current data augmentation methods, including their limitations in generalization, real-time performance, and interpretability, as well as the absence of robust evaluation metrics for generated samples, have been summarized, and potential solutions to address these issues have been explored.

A systematic review of data augmentation methods for intelligent fault diagnosis of rotating machinery under limited data conditions

Ju,

Chen,

Qiang

et al. 2024

Deep transfer learning in machinery remaining useful life prediction: a systematic review

Chen,

Kong,

Cheng

et al. 2024

As a novel paradigm in machine learning, deep transfer learning (DTL) can harness the strengths of deep learning for feature representation, while also capitalizing on the advantages of transfer learning for knowledge transfer. Hence, DTL can effectively enhance the robustness and applicability of the data-driven RUL prediction methods, and has garnered extensive development and research attention in machinery RUL prediction. Although there are numerous systematic review articles published on the topic of the DTL-based approaches, a comprehensive overview of the application of DTL in the RUL prediction for different mechanical equipment has yet to be systematically conducted. Therefore, it is imperative to further review the pertinent literature on DTL-based approaches. This will facilitate researchers in comprehending the latest technological advancements and devising efficient solutions to address the cross-domain RUL prediction challenge. In this review, a brief overview of the theoretical background of DTL and its application in RUL prediction tasks are provided at first. Then, a detailed discussion of the primary DTL methods and their recent advancements in cross-domain RUL prediction is presented. Next, the practical application of the current research is discussed in relation to the research object and its open-source data. More importantly, several challenges and further trend are further presented to conclude this paper in the end. We have reason to hope this work can offer convenience and inspiration to researchers seeking to advance in the field of RUL prediction.

A systematic review on interpretability research of intelligent fault diagnosis models

Peng,

Shao,

Xiao

et al. 2024

Recent years have witnessed a surge in the development of intelligent fault diagnosis (IFD) mostly based on deep learning methods, offering increasingly accurate and autonomous solutions. However, they overlook the interpretability of models, and most models are black-box models with unclear internal mechanisms, thereby reducing users’ confidence in the decision-making process. This is particularly problematic for critical decisions, as a lack of clarity regarding the diagnostic rationale poses substantial risks. To address these challenges, a more reliable, transparent, and interpretable system is urgently demanded. Research on the interpretability of IFD has gained momentum and stands today as a vibrant area of study. To promote in-depth research and advance the development of this field, a thorough examination of existing journal articles on interpretable fault diagnosis models is essential. Such a review will demystify current technologies for readers and provide a foundation for future investigation. This article aims to give a systematic review of the state-of-the-art interpretability research in the field of IFD. We present a systematic review of recent scholarly work on interpretable models in this domain, categorizing them according to their methodologies and structural attributes. In addition, we discuss the challenges and future research directions for the interpretability of IFD.