A multi-population state optimization algorithm for rail crack fault diagnosis

Abstract

Abstract The rails usually work in complex environments, which makes them more prone to mechanical failures. In order to better diagnose the crack faults, a multi-population state optimization algorithm (MPVHGA) is proposed in this paper, which is used to solve the problems of low efficiency, easy precocity, and easy convergence of local optimal solutions in traditional genetic algorithms. The detection results of fault signals show that MPVHGA has the advantages of fast convergence rate, high stability, no stagnation, and no limitation of fixed iterations number. The average iterations number of MPVHGA in 100 independent iterations is about 1/5 of the traditional genetic algorithm (SGA for short) and about 1/3 of the population state optimization algorithm (VHGA for short), and the total convergence number of MPVHGA converges to 55 and 10 more than SGA and VHGA respectively, and the accuracy of fault diagnosis can reach 95.04%. On the basis of improving the performance of simple genetic algorithm, this paper provides a new detection method for rail crack fault diagnosis, which has important engineering practical value.