STLBO motor bearing fault diagnosis method based on kurtosis FastICA and approximation solution domain

Abstract

The invention relates to a STLBO motor bearing fault diagnosis method based on a kurtosis FastICA and an approximation solution domain. The method comprises: firstly, by adopting a FastICA separation signal based on kurtosis and a Mel-frequency cepstral coefficient, carrying out feature extraction on a motor bearing vibration signal; secondly, determining network structure parameters and an upper bound and a lower bound of a TLBO initialization population by combining initial training of a BPNN through a method of approaching a solution domain; and finally, fusing a TLBO correction algorithm of a self-adaptive dynamic learning factor, iteratively searching an optimal weight and a threshold value, and inputting the optimal weight and the threshold value into the BPNN. Signal features can be enhanced, noise interference can be reduced, and the recognition rate of fault diagnosis can be improved; for an unknown source, excessive prior knowledge and theoretical reserve are not needed, and the method has very strong generalization; and compared with various optimization algorithms, specific parameters do not need to be set, meanwhile, learning factors are dynamically changed according to the current iteration number, and the convergence speed of the algorithm can be increased; and local convergence is avoided, debugging is convenient, and calculation is simple.

Description

technical field [0001] The invention relates to a motor fault diagnosis method, in particular to a kurtosis-based FastICA and an STLBO motor bearing fault diagnosis method approaching the solution domain. Background technique [0002] The motor is the core equipment that converts electrical energy into mechanical energy. With the development of science and technology, the normal operation of various fields is inseparable from the motor. However, in a complex industrial environment where the motor operates for a long time, it is prone to the influence of its own factors such as aging of parts and excessive load pressure, coupled with the influence of various external environmental factors, it is prone to various failures. Once a fault occurs, if it is not diagnosed and repaired in time, it will cause unpredictable damage to production, life, and even life. Therefore, it is of great significance to deeply study the method of motor fault diagnosis and find a more accurate and ...

AI Technical Summary

Problems solved by technology

However, in actual research, most algorithms rely largely on the researchers' prior knowledge and practical experience as support, and the many parameters involved in the algorithm require a huge workload during the debugging process, and the generalization ability is low. There are also disadvantages of slow algorithm convergence, low reliability and practicability

Images