Intelligent Diagnosis Using Continuous Wavelet Transform and Gauss Convolutional Deep Belief Network

• Published in: IEEE transactions on reliability Vol. 72; no. 2; pp. 692 - 702
• Main Authors: Zhao, Huimin, Liu, Jie, Chen, Huayue, Chen, Jie, Li, Yang, Xu, Junjie, Deng, Wu
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.06.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Belief networks; Classification; Continuous wavelet transform; Continuous wavelet transform (CWT); Continuous wavelet transforms; Convolution; Convolutional neural networks; Deep learning; fault classification; Fault diagnosis; Feature extraction; Gauss convolutional deep belief network (CDBN); image processing; Image segmentation; Machine learning; multiple faults; Normal distribution; rolling bearings; Signal to noise ratio; Vibrations; Visualization
• ISSN: 0018-9529; 1558-1721
• DOI: 10.1109/TR.2022.3180273

Bearing fault diagnosis is of significance to ensure the safe and reliable operation of a motor. Deep learning provides a powerful ability to extract the features of raw data automatically. A convolutional deep belief network (CDBN) is an effective deep learning method. In this article, a novel vibration amplitude spectrum imaging feature extraction method using continuous wavelet transform and image conversion is proposed, which can extract the image features with two-dimensional and eliminate the effect of handcrafted features under low signal-to-noise ratio conditions, different operating conditions, and data segmentation. Then, a novel CDBN with Gaussian distribution is constructed to learn the representative features for bearing fault classification. The proposed method is tested on motor bearing dataset with four and ten classifications. The results have been compared with other methods. The experiment results show that the proposed method has achieved significant improvements and is more effective than the traditional methods.