A Genetic Algorithm and PCA-Based Feature Selection to Improve the Failure Diagnosis Performance of Railway Vehicle Doors

The failure diagnosis of railway vehicle door system is carried out using a test bench and machine learning software for the fast accurate classification. signal length deviation exists in actual collected data normal operation abnormal failures with time delay. traditional multi-segmentation technique feature extraction has shortcomings by assuming that measured time-based signals have same operating time. However, uniform segmentation difficulty due to length. A method converting into position-based was performed overcome problem. optimized single-zone genetic algorithm proposed improve classification performance reduce computation time, instead existing technique. principal component analysis-based dimensional reduction explained variance ratio used effect from multi-collinearity features. Finally, combination methods compared individual validate support vector other classifiers. It confirmed shows highest accuracy 99.84%.