An Investigation Into Fault Diagnosis of Planetary Gearboxes Using A Bispectrum Convolutional Neural Network

• Published in: IEEE/ASME transactions on mechatronics Vol. 26; no. 4; pp. 2027 - 2037
• Main Authors: Pang, Xinyu, Xue, Xuanyi, Jiang, Wangwang, Lu, Kaibo
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.08.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Artificial neural networks; Bispectrum (BSP) analysis; Breakage; Classification; Computing time; Convolution; Convolutional neural networks; deep convolutional neural network (CNN); Evaluation; Fault detection; Fault diagnosis; Feature extraction; Gear teeth; Gear trains; Gearboxes; Gears; Learning; Neural networks; planetary gearbox; Training; transfer learning (TL); Vibration; Vibrations

To improve the efficiency and accuracy of fault diagnostics of planetary gearboxes, an intelligent diagnosis approach is proposed based on deep convolutional neural networks (CNNs) and vibration bispectrum (BSP). Rather than using raw vibration signals, BSP is appreciated as the input for the CNN mo...