High-speed bearing fault diagnosis method for adaptive parameter multi-scale entropy

• Main Authors: HUANG LIPING, ZHANG YUJIAN, LYU FANGLEI, LIAO ZIYANG
• Format: Patent
• Language: Chinese; English
• Published: 16.08.2024
• 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 high-speed bearing fault diagnosis method for adaptive parameter multi-scale entropy. The method specifically comprises the following steps: step (1), obtaining a high-speed bearing fault data set; (2) setting related parameters; (3) acquiring multi-scale range entropy information of the fault features; (4) inputting the obtained multi-scale range entropy feature information into a deep extreme learning machine, and constructing a high-speed bearing fault diagnosis model; (5) through a least square solution # imgabs0 #; (6) applying an automatic encoder AE to an ELM; and step (7), diagnosing the high-speed bearing fault test set to realize accurate classification of fault types. Compared with a traditional method, the fault diagnosis method provided by the invention takes the minimum margin factor as a target function, adaptively selects MRE related parameters, can effectively screen fault feature signals, ensures the accuracy of fault feature information after subsequent processing,