EnvelopeNet: A robust convolutional neural network with optimal kernels for intelligent fault diagnosis of rolling bearings. (August 2021)

• Record Type: Journal Article
• Authors: Tang, Lv; Xuan, Jianping; Shi, Tielin; Zhang, Qing
• Is Part Of: Measurement. Volume 180(2021)
• Publication Date: 2021-08
• Subjects: Intelligent fault diagnosis -- Convolutional neural networks -- Industrial inspection -- Rolling bearings -- Domain generalization -- Fluctuating working conditions; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2021.109563
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: The optimal band selection is applied to design a network module. A method is proposed for evaluating and optimizing the convolutional kernel. The optimal kernels and features show semantics and make the network robust. The impulsiveness or cyclostationarity can be used as semantics. An improvement of 4% and 3% is achieved under two scenarios, respectively. Abstract: Deep data-driven methods for fault diagnosis, as an engineering-oriented approach, rely heavily on target data. For engineering applications, the working conditions of rotating machinery fluctuate from time to time and a collection for any working conditions is impossible. To tackle this problem, a robust network with optimal kernels named EnvelopeNet is proposed for extracting solid information and eliminating the influence of fluctuations. In the EnvelopeNet, a feature evaluation building block named envelope module is constructed based on optimal band selection theory to optimize the kernels. Compared with the kurtogram, the learned optimal kernels and features show strong semantics which helps the network become robust. The EnvelopeNet is validated under the approximate speed and mixed speed scenarios. The results show that the EnvelopeNet could provide admirable generalization ability for fluctuating working conditions and an average improvement of about 4% and 3% over existing approaches under two scenarios respectively.