A Comprehensive Fault Diagnosis Method for Jointless Track Circuit Based on Genetic Algorithm
Jiancheng Mu · Zhongguo tiedao kexue · 2010
A transmission-line theory based simulation model of the induced voltage envelope of the cab signal was proposed.The influence law of the compensation capacitor failure on the induced voltage envelope of the cab signal was analyzed,and the comprehensive fault diagnosis method for track circuit based on genetic algorithm was proposed by utilizing the linear mapping relationship between the inductive voltage of the cab signaling and the current of the track circuit signal.In this method,with the compensation capacitor and the ballast resistance chosen as the decision variables,with the minimum difference between the envelop of the real inductive voltage of the cab signal and the envelop of the simulated signal current of the corresponding track circuit as the objective to form the fitness function,by genetic operations such as selection,crossover and mutation,the optimum value of each decision variable under current state was obtained,thus the comprehensive diagnosis of the track circuit was realized.Experiment results show that the GA method,which is firstly introduced into the diagnosis of track circuit,can give correct and comprehensive judgement by means of the actual record data of the cab signaling under the condition of multiple compensation capacitor failure and unstable ballast resistance,make up the shortage of current methods,and provide a new and effective method for track circuit diagnosis.