Journal
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
Volume 357, Issue 11, Pages 7286-7307Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.jfranklin.2020.04.024
Keywords
-
Categories
Funding
- National Natural Science Foundation of China [61773181, 61203092]
- Funda-mental Research Funds for the Central Universities [JUSRP51733B]
- National Science Centre in Poland [2014/15/B/ST7/03208]
- Serbian Ministry of Education, Science and Technological Development [451-03-68/202014/200108]
Ask authors/readers for more resources
In recent years, the technique of machine learning or deep learning has been employed in intelligent fault diagnosis methods to achieve much success using massive labeled data. However, it is generally difficult or expensive to label the monitoring data in practical engineering due to its complex working conditions. Therefore, an unsupervised fault diagnosis method is proposed in this paper for rolling bearings, which incorporates short-time Fourier transform (STFT) as well as categorical generative adversarial networks (CatGAN). The proposed method first adopts STFT to transform raw 1-D vibration signals into 2-D time-frequency maps to serve as the input of CatGAN. Then, it obtains a CatGAN model via an adversarial training process to generate fake samples with a similar distribution to the maps extracted by STFT and cluster the input samples into certain categories. Furthermore, the performance of the proposed ST-CatGAN method is verified using a classic rotating machinery dataset, and the experimental results demonstrate its high diagnosis accuracy and strong robustness against the motor load changes. (C) 2020 The Franklin Institute. Published by Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available