SVM Multiclass Fault Diagnosis Based on Scaled Convex Shell and Parameter Optimization

Rolling bearings are important components of rail transit trains, and their operating status is of great significance for ensuring the safety of vehicles. Therefore, accurate and efficient diagnosis of rolling bearing faults in rail vehicles is an urgent problem to be solved. To solve this problem, a support vector machine (SVM) bearing fault diagnosis method based on scaled convex hull (SCH) and differential mutation particle swarm optimization (DMPSO) is proposed in this study. Firstly, to address the issue of SVM being unable to effectively handle multi classification faults, a scaled convex hull is proposed to construct an effective SVM multi classification model. Then, to avoid the SVM parameter optimization process falling into local optima, the optimal kernel function parameters and penalty factors of the SVM model are identified through the global search ability of the differential mutation particle swarm optimization algorithm. Finally, the optimal parameter SVM model is applied to the fault diagnosis of rolling bearings. The experimental results show that the proposed SVM fault diagnosis model has better performance compared to other methods.