Mechanical rotating part fault diagnosis method based on stack form convolutional network

• Main Authors: LIU HONGXIAO, YANG CHENG, YAN GE, LI HANZHI, LI ZHAN, WU MEIXI
• Format: Patent
• Language: Chinese; English
• Published: 15.07.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; MEASURING; PHYSICS; TESTING; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR

The invention provides a mechanical rotating part fault diagnosis method based on a stack form convolutional network. The method comprises the following steps: receiving vibration acceleration signals when a rated number of mechanical rotating parts break down, and identifying different fault types corresponding to the vibration acceleration signals; randomly selecting a rated number of vibration acceleration signals to obtain a random vibration acceleration signal sample; performing pulse enhancement and noise reduction on the random vibration acceleration signal sample through a stacking form convolution module, and extracting a fault feature sample; and training according to the fault feature sample to obtain a fault diagnosis model for fault diagnosis. And pulse enhancement and noise reduction are performed through the stacking form convolution module, and the fault feature sample is extracted to train the fault diagnosis model, so that the technical problem of lack of a mechanical part fault diagnosis me