A SVM-based framework for fault detection in high-speed trains

Abstract

High-Speed Trains (HSTs) demand high reliability, maintainability and availability of their installed equipment. The braking system, in particular, is a safety-critical system in HSTs. Accurately and efficiently detecting any ongoing faults in such a system is very important to ensure safety, facilitate maintenance and reduce downtime of HSTs. Data-driven approaches have become very popular for fault detection with the implemented built-in monitoring systems and the artificial intelligence. Due to the high reliability of the HSTs, most of the monitoring data are on the normal conditions and only a small part concerns the faulty conditions. Such imbalanced data may reduce the fault detection rate of a data-driven model. Along with the between-class imbalance problem, the fusion of various continuous and discrete signals is also an obstacle in building an efficient fault detection model. In this paper, the weighted-feature strategy and the cost-sensitive learning are integrated effectively in a multi-kernel support vector machine model, to solve the problems brought by between-class imbalance and heterogeneous signals. The experiments on real datasets concerning faults in braking systems of a HST and fourteen public imbalanced datasets are carried out to verify the effectiveness and generalizability of the proposed method. With respect to both F-measure and G-mean, the proposed method outperforms the benchmark methods in the experiments, showing the potential of the combination of weighted feature strategy, multiple kernel learning and support vector machine in fault detection.