Study on fracture fault diagnosis online method of bogie of maglev train

It will be realized that automatic alarm and prediction for abnormal conditions such as structural cracks, if the state of bogie structure can be monitored during the operation of Maglev train, which can improve the safety performance of maglev train. The inherent characteristics of the structure are unaffected by the environment, such as modal frequency and damping. When the structure changes, the inherent characteristics change, so these changes can be used to diagnose structural cracks. Due to the system and measurement error existed, the sensitivity coefficient of each order modal frequency of the crack is different, so it is difficult to identify the fault by using the traditional threshold method. In view of this problem, the Principal Component Analysis (PCA) is introduced to extract the feature, and then the pattern classification is carried out by support vector machine (SVM). Simulation results show that this method is feasible.