Abstract
Signal acquisition from mechanical systems working in faulty conditions is normally expensive. As a consequence, supervised learning-based approaches are hardly applicable. To address this problem, a one-shot learning-based approach is proposed for multiclass classification of signals coming from a feature space created only from healthy condition signals and one single sample for each faulty class. First, a transformation mapping between the input signal space and a feature space is learned through a bidirectional generative adversarial network. Next, the identification of different health condition regions in this feature space is carried out by means of a single input signal per fault. The method is applied to three fault diagnosis problems of a three-dimensional printer and outperforms other methods in the literature.
Original language | English |
---|---|
Article number | 9161402 |
Pages (from-to) | 8768-8776 |
Number of pages | 9 |
Journal | IEEE Transactions on Industrial Electronics |
Volume | 68 |
Issue number | 9 |
DOIs | |
State | Published - Sep 2021 |
Bibliographical note
Funding Information:Manuscript received March 3, 2020; revised May 28, 2020; accepted July 11, 2020. Date of publication August 6, 2020; date of current version June 16, 2021. This work was supported in part by GIDTEC Research Group of Universidad Politecnica Salesiana, in part by the National Natural Science Foundation of China under Grant 51775112, in part by the Science and Technology Partnership Program under Grant KY201802006, in part by the Chongqing Natural Science Foundation under Grant cstc2019jcyj-zdxmX0013, and in part by the CTBU Project under Grant KFJJ2018107 and Grant KFJJ2018075. (Chuan Li and Diego Cabrera are co-first authors.) (Corresponding author: Diego Cabr-era.) Chuan Li is with the National Research Base of Intelligent Manufacturing Service, Chongqing Technology and Business University, Chongqing 400067, China (e-mail: chuanli@ctbu.edu.cn).
Publisher Copyright:
© 1982-2012 IEEE.
Keywords
- Deep learning
- fault diagnosis
- one-shot learning
- three-dimensional (3-D) printer