A novel model-independent data augmentation method for fault diagnosis in smart manufacturing

Abstract

With the rapid development of information technology, data-driven fault diagnosis has gained more and more attention because it provides a new way for enterprises to save costs. Considering that there are few abnormalities in equipment operation in actual industrial applications, it is still a challenge to implement data-driven fault diagnosis that requires a large amount of fault data. To tackle the challenge, this paper proposes a model-independent data augmentation method, which is a weighted combination of the two time series data augmentation methods, i.e. Gaussian noise and signal stretching. The experimental dataset is collected from an intelligent motor test platform. The fault diagnosis model based on support vector machine and feedforward neural network are applied to study the ability of the proposed data augmentation method in terms of model independence. Experimental results show that the proposed data augmentation methods can significantly improve the accuracy of fault diagnosis.

Publication DOI: https://doi.org/10.1016/j.procir.2022.05.090
Divisions: College of Engineering & Physical Sciences > School of Engineering and Technology > Mechanical, Biomedical & Design
Funding Information: This research work was partially supported by the National Natural Science Foundation of China (No. 52105534) and Shanghai Science and technology program (Project No. 22010500900).
Additional Information: © 2022 The Authors. CC BY-NC-ND 4.0 Funding Information: This research work was partially supported by the National Natural Science Foundation of China (No. 52105534) and Shanghai Science and technology program (Project No. 22010500900).
Uncontrolled Keywords: data augmentation,fault diagnosis,smart manufacturing,time series,Control and Systems Engineering,Industrial and Manufacturing Engineering
Publication ISSN: 2212-8271
Last Modified: 28 Feb 2024 08:18
Date Deposited: 13 Jul 2022 10:33
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
https://www.sci ... 3742?via%3Dihub (Publisher URL)
PURE Output Type: Conference article
Published Date: 2022-05-26
Accepted Date: 2022-05-01
Authors: Lyu, Pin
Zhang, Hanbin
Yu, Wenbing
Liu, Chao (ORCID Profile 0000-0001-7261-3832)

Export / Share Citation


Statistics

Additional statistics for this record