Study On The Straddle-type Monorail Cast Steel Pedestal Health Status Detection Based On Vibration Test Technology

As the key research object of this paper, the cast steel pedestal is the most important part to connect pier and girder of Chongqing straddle-type monorail. The health condition of which plays vital function to the straddle-type monorail's safe running. However, due to the machining defects, rust caused by climate factors, long-term service's influence and complicated effect of time-varying load, the health condition of those cast steel pedestals will be changed. For the safe running of the straddle-type monorail traffic, a monitoring operation must be taken to make sure that all those cast steel pedestals are in normal. The cast steel pedestals are usually fixed on the high piers and girders, whose big cubage, special location and complex shape make those common nondestructive testing ways such as radioactive ray, ultrasonic, microwave can't detect its health condition.With financial assistance of the national science and technology support projects: 2007BAG06B06, according to the topic requests and combined actual situations of the second line of Chongqing rail transit, the author presents the vibration testing technology to detection the health condition of the cast steel pedestal. At first, using industry control computer, force hammer, vibration sensor and data acquisition card, and programming the software to form the vibration data acquisition system. Then find the right vibration sensors'position and the hit position according to many times'trials. Then put the sensors on the cast steel pedestal, and exciting the cast steel pedestal with the force hammer, and acquiring the vibration pulse signals.The scarcity of fault samples often occurs in the fault diagnosis of Chongqing straddle-type monorail cast steel pedestal system. In the case of this situation, this paper first puts forward a fault diagnosis method based on One-class Support Vector Machine (One-class SVM). This method can build up one-class classifier to distinguish between normal condition and abnormal condition as long as the normal data samples are provided. In the process of test, Kernel Principal Component Analysis (KPCA) is used as data preprocessing to extract the features from vibration impulse response signal as the input of One-class SVM classifier and the accuracy rate of classifier is 98%.The test result shows that the feature extraction based on KPCA can concentrate fault information more effectively and make the the One-class SVM classifier identify the fault samples more accurately. The result of the experiments indicates that the method above providing a scientific way for health diagnosis of the straddle-type monorail cast steel pedestal, which have some value for reference.