Method for predicting residual service life of urban rail train bearing

• Main Authors: LIU QIYANG, DENG JIANXIN, LIU CHANG, HE DEQIANG, YAN JINGREN, LAO ZHENPENG, XIANG ZAIYU, LI XIANWANG
• Format: Patent
• Language: Chinese; English
• Published: 04.11.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses a method for predicting the remaining service life of an urban rail train bearing, and the method comprises the following steps: setting the rotating speed and sampling frequency of the bearing, collecting the original vibration signals of the whole life cycle from the operation of the bearing to the failure, extracting the time domain features of the original vibration signals of the bearing, and calculating the remaining service life of the bearing; a similarity measurement method is adopted to measure the similarity degree between the features; carrying out variational mode decomposition on the original vibration signal of the bearing to obtain mode component characteristics, and adopting an energy entropy discrimination method according to the principle that the larger the energy entropy is, the information is uncertain; combining the time domain features with the obtained modal component features, and dividing into a training set and a verification set; and establishing an LSTM pr