A Novel Multiview Sampling-based Meta Self-Paced Learning Approach for Class-imbalanced Intelligent Fault Diagnosis


In practical machine fault diagnosis, the obtained data samples under faulty conditions are usually far less than those under normal conditions, resulting in a class-imbalanced dataset issue. The existing solutions for class-imbalanced scenarios include data-level and model-level strategies, which are either subject to overgeneralization or time-consuming. To address it, this article proposes a novel multiview sampling-based meta self-spaced learning approach. First, the signal processing methods, such as time-domain (TD), frequency-domain (FD), and time-frequency domain (TFD), are used to extract statistical features from the original data to form diverse views. Next, the meta self-paced learning technology is applied to select high-quality samples from multiview feature data to generate a class-balanced dataset. Finally, a fault diagnosis model is trained with the obtained class-balanced dataset. The main contribution of this research has twofold: 1) the introduced multiview sampling method adaptively learns the weight in the sampling process and automatically deletes the noise samples with large loss value to improve the performance of the fault diagnosis model; and 2) the proposed meta self-spaced learning approach eliminates the error caused by setting parameters manually and ensures the quality of the extracted samples. To validate its performance, a comparative study is conducted on a public dataset and the one collected from an industrial motor test platform. Five baseline methods are compared with the proposed one based on the convolutional neural network (CNN) model. Moreover, three traditional machine learning models are to verify the sample quality generated. The experimental results achieve above 90% diagnosis accuracy, which provides a new intelligent manner for the modular service application of class-imbalance fault diagnosis.

Publication DOI: https://doi.org/10.1109/TIM.2022.3214628
Divisions: College of Engineering & Physical Sciences > School of Engineering and Technology > Mechanical, Biomedical & Design
Additional Information: © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Uncontrolled Keywords: Adaptation models,Biological system modeling,Fault diagnosis,Feature extraction,Generative adversarial networks,Support vector machines,Training,class-imbalanced data,meta self-paced learning,multiview sampling,self-paced learning,fault diagnosis,Class-imbalanced data,Instrumentation,Electrical and Electronic Engineering
Publication ISSN: 1557-9662
Last Modified: 11 Jul 2024 07:13
Date Deposited: 25 Nov 2022 18:50
Full Text Link:
Related URLs: https://ieeexpl ... cument/9919172/ (Publisher URL)
http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Article
Published Date: 2022-10-13
Accepted Date: 2022-09-27
Authors: Lyu, Pin
Zheng, Pai
Yu, Wenbing
Liu, Chao (ORCID Profile 0000-0001-7261-3832)
Xia, Min



Version: Accepted Version

License: ["licenses_description_other" not defined]

| Preview

Export / Share Citation


Additional statistics for this record