Journal
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Volume 17, Issue 9, Pages 6282-6293Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.3030967
Keywords
Feature extraction; Generative adversarial networks; Gallium nitride; Fault detection; Generators; Training; Convolution; Deep learning; fault detection; rolling bearing
Categories
Funding
- National Natural Science Foundation of China [U1933101, 51875436, 91960106, 61633001, 51421004, 51965013]
- China Postdoctoral Science Foundation [2020T130509, 2018M631145]
- Natural Science Foundation of Shaanxi Province [2019JM-041]
- Guangxi Natural Science Foundation Program [2019JJA160025, TII-20-1489]
Ask authors/readers for more resources
This article introduces a two-stage method for zero-shot fault detection of rolling bearings, including a feature generation network and an improved deep neural network classifier, trained with synthetic pseudofault features to recognize unseen fault samples. Experimental results demonstrate the practicality of the method for industrial applications.
Class imbalance issue has been a major problem in mechanical fault detection, which exists when the number of instances presenting in a class is significantly fewer than that in another class. This article focuses on the problem of zero-shot fault detection of rolling bearing, which is the extreme case of class imbalance. Aiming at this problem, a two-stage zero-shot fault recognition method is proposed. First, inspired by the conditional generative adversarial network, a novel feature generating network which is composed of a feature extractor, a discriminator, and a generator is designed to capture the potential distribution of normal samples. Then, the generator will generate abundant pseudofault features by adding an additional sequence to the condition. Second, an improved deep neural network is trained with these synthetic pseudofault features as the classifier. Specially, a condition index is designed to represent different fault classes so that it can recognize the unseen fault samples. Finally, the effectiveness of the proposed method is verified by three datasets and a comparison method is also given to show the superiority. Results show that the feature generation network can effectively detect the typical faults even though the fault data are unavailable during training, which is practical for industrial application.
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