Surface defects detection of railway turnouts

As the turnout is a critical part of railway tracks, its surface defects are directly related to the operation safety. The defects detection of turnout is an effect way to ensure the safety and comfort of urban transit railway. In this paper, the feature extraction of the turnout defects is investigated based on the bogie acceleration measurements. The normal turnout model and faulty turnout model based on SIMPACK are established first, from which the vehicle vibration acceleration is obtained. Then, the acceleration signal is analyzed in time-frequency domain. The results show that the power spectral density (PSD) and all the frequency-domain features are useful for detecting the poor fit defect of the switch point. And the peak and PSD features can be used to detect the curve opposite super-elevation. The proposed method provides alternative for the detection of turnout defects by using in-service vehicle.