A motor bearing fault voiceprint recognition method based on Mel-CNN model. (15th February 2023)

• Record Type: Journal Article
• Authors: Shan, Shuaijie; Liu, Jianbao; Wu, Shuguang; Shao, Ying; Li, Houpu
• Is Part Of: Measurement. Volume 207(2023)
• Publication Date: 2023-02-15
• Subjects: Bearing fault diagnosis -- Voiceprint feature -- Mel spectrum -- Convolution neural network (CNN) -- Deep learning; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2022.112408
• Languages: English
• ISSNs: 0263-2241

Abstract

Graphical abstract: Highlights: Noise signal has the advantage of non-contact acquisition in acquisition mode. Apply voiceprint recognition technology to the research of bearing fault diagnosis. Mel spectrum voiceprint feature can characterize the type of bearing fault. Mel spectrum has the characteristic of continuity and is suitable for training CNN. CNN has a strong ability to recognize the voiceprint features of Mel spectrum. Abstract: The occurrence of bearing faults is often accompanied by noise signals, and noise sensors have the characteristics of non-contact and flexible arrangement; hence, this paper proposes a bearing fault diagnosis method based on voiceprint features and deep learning. First, the high-frequency component of the motor noise is removed with the help of variational mode decomposition (VMD) to extract the Mel spectrum voiceprint features. Secondly, the Mel voiceprint features are re-extracted with the help of convolutional neural networks (CNN) to fully obtain the high-dimensional abstract features characterizing the bearing faults. Finally, the Mel-CNN model is exploited to achieve bearing fault diagnosis. Applying the Mel-CNN model proposed in this paper to motor noise data with bearing faults, the results show that the Mel spectral features can accurately characterize bearing faults and that the Mel-CNN model outperforms ACDIN, WDCNN, TICNN, the improved LeNet-5 model, and four CNN-derived models.