Bearing slip monitoring method based on knowledge graph and distributed transfer learning

• Main Authors: LU NINGYUN, XIAO LINGFEI, JIANG BIN, GUO QINTAO, MA LEIMING
• Format: Patent
• Language: Chinese; English
• Published: 22.08.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MEASURING; PHYSICS; TESTING; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR

The invention discloses a bearing slip monitoring method based on a knowledge graph and distributed transfer learning. Firstly, typical slip work is divided according to expert experience, and a bearing slip knowledge graph is constructed by using Neo4j software; secondly, bearing vibration acceleration data and retainer and inner ring rotating speed data under different typical work conditions are collected, and obtained slip rates are graded; then, training a distributed transfer learning model according to the collected bearing vibration and slip rate data under different work conditions, and constructing a slip diagnosis model set; according to the collected vibration data corresponding to the known working parameters, selecting a slip diagnosis model under the corresponding typical work to monitor the slip rate of the bearing; and finally, for vibration data corresponding to unknown working parameters, matching is carried out according to the constructed knowledge graph and vibration data of known workin