Electric doors have been applied in urban trains since 2007 and operated for a long time. Recently, the failure of mechanical devices in electric doors have been increasing. The door is a device that is directly related to the safety of passengers. The rivet breakage of a ball/nut assembly may occur to an accident during train operation. In this study, the operating voltage and acceleration data of the door were collected for rivet condition monitoring, and 4 features were extracted in the frequency domain using the acceleration data. The classification performance of the rivet condition according to the axial direction of the acceleration data and 4 kernel functions was evaluated using SVM algorithm. When the X-axis data and Gaussian kernel function were used, the highest classification performance was shown for the electric door’s rivet with 90% accuracy.

• 김준우(서일대학교) | Jun-Woo Kim
• 박성천(서일대학교) | Park Sung-cheon Corresponding author