Bearing noise pattern recognition and mute optimization method

• Main Authors: ZHANG SHANLIN, ZHENG JIAKUN, XU YUZHEN, XU YUXING, DONG CHUNCHAO, CHEN NAIJIAN
• Format: Patent
• Language: Chinese; English
• Published: 05.08.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; MEASURING; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; TESTING; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR

The invention relates to a bearing noise pattern recognition and mute optimization method, which comprises the following steps of: acquiring an original sound signal and a vibration signal of a bearing, and performing time domain analysis and frequency domain analysis; extracting a feature vector of the bearing signal through a feature extraction algorithm; a deep learning algorithm of a vibration and noise source part recognition system is used for carrying out vibration and noise mode recognition and principal component analysis, a bearing noise classification model is obtained, and vibration and noise source parts are recognized; vibration and noise of noise source parts of the bearing are reduced through the mute optimization technology, and mute optimization of the bearing is achieved. According to the method, the bearing noise can be subjected to pattern recognition and mute optimization, the recognition speed is high, the recognition efficiency is high, meanwhile, the labor cost is reduced, and the dam