Research on Fault Diagnosis Method for Speed Sensor of High-Speed Train

Abstract

Speed sensors installed on the axes of high-speed train will lead to faults due to the vibration and electromagnetic interference during train operation. At present the braking system can't detect all faults of speed sensor but misdirect the axle lock fault, which affects the safety of train operation. Therefore, this paper proposes an integral intelligent fault diagnosis method for speed sensor of high-speed train brake system, which realizes real-time detection of speed sensor anomalies and accurate location of the axis of the speed sensor fault. Firstly, the traditional principal component analysis method is improved by proposing a comprehensive monitoring statistic to realize real-time fault detection of speed sensor. Then, the modified reconstruction based contribution plot based on the idea of combination maximization is adopted to achieve accurate fault location of speed sensor. In addition, the fault injection experiments are conducted, the results prove the method can diagnose the fault of speed sensor accurately and effectively, and solve the hidden trouble of high-speed train operation.