Because they support the entire weight of the train and carry substantial safety consequences, rail train wheels are vital bogie components. As a result, it is crucial to predict tire wear so that early wheel turning or replacement may effectively improve the stability of train operation and the economy of railroad operation. A substantial percentage of wheel wear will occur during travel, impacting safety. Data intelligence may be able to anticipate tire wear more precisely and timely than traditional prediction based on historical experience. As data-driven analysis advances, numerous intelligent algorithms are being employed to the prediction of tire wear. Despite the rapid advancement of data-driven technology, predicting wheel and rail.
Regression is used in this paper to forecast wheel wear using complex algorithms. In order to better accurately predict future wheel wear data, this study is based on data-driven technologies for wheel data collection, analysis, filtering, and acquisition. The Particle Swarm Optimization Support Vector Machine (PSO-SVM) model is improved by employing the grid search strategy to minimize the two parameters of the support vector machine's kernel parameter g and the punishment function C.
while employing the cross-validation method to prevent overfitting and achieve the regression prediction of wheel wear data. The results of the experiments demonstrate that the improved model generates more reliable results for each prediction. In order to demonstrate how the model affects optimization, the Genetic algorithm for optimization of support vector machines (GA-SVM) mathematical model is optimized for comparative analysis in terms of iteration rate, fitness, and mathematical metrics.