Fault Diagnosis of Track Circuit Compensation Capacitor Based on GWO Algorithm

Abstract

Track circuit (TC) is an important equipment in China Train Control System (CTCS). But its failure rate has been high. The predictive maintenance mechanism of TC can further ensure the safe operation of train. While the fault diagnosis and realization of TC status is the premise to achieve prediction maintenance. With regards to this, a fault diagnosis method for TC based on Grey Wolf Optimizer (GWO) algorithm is put forward in this paper. A Uniform Transmission Line (UTL) Model of TC is established and the impact on the Locomotive Signal Amplitude Envelope (LSAE) by ballast resistance, compensation capacitor is analyzed. The above parameters are chosen as the decision variables. To minimum the difference between the real LSAE and the one calculated using the UTL model as the objective to form the fitness function. GWO algorithm has the characteristic of insensitivity to initial solution values, higher optimization efficiency and global optimization ability and it is employed to iteratively search for the optimum solution of TC parameters. Experiment results show that the method proposed in this paper can realize the diagnosis of important parameters of TC and it has high adaptability and excellent accuracy.