Fault diagnosis of rolling bearings based on ISSA - SVM

Aiming at the problems that the swarm intelligence algorithm optimization support vector machine (SVM) model is easy to fall into local optimum and is of low accuracy in the field of rolling bearing fault diagnosis，a method for optimizing the support vector machine based on an improved sparrow search algorithm ( SSA) was proposed for fault diagnosis of rolling bearings. First, the evenly distributed Chebyshev chaotic map was introduced to initialize the sparrow population in order to improve the spatial distribution uniformity of the population. Then, the adaptive inertia weights were integrated into the location updating of the discoverer of the sparrow algorithm. Finally, the optimal sparrow with the updated position was randomly disturbed to improve the global and local search ability of the algorithm and avoid falling into the local optimization. The algorithm was applied to the parameter optimization of the support vector machine, and a ISSA - SVM fault diagnosis model was constructed to realize the classification and diagnosis of bearing fault signals. The analysis results of the rolling bearing fault diagnosis tests show that the fault classification effect of the ISSA - SVM model is obviously better than that of the PSO - SVM，GA - SVM and SSA - SVM models，which can effectively identify the types of faults of rolling bearings. © 2023 Chinese Vibration Engineering Society. All rights reserved.