Research On Principle Component Analysis For Motor State Monitoring

The state monitoring of train operating equipment is a key point of train traveling process.For the complex operating equipment,it is difficult to achieve the exact mathematical model of traveling process.So this will limit the application of process monitoring methods based on system theory.With the application of the computer technology,different kinds of sensors and intelligent meters,large amount of data are sampled and collected.It is one of the most active research areas in the field of process control that how to transform these collected data into valuable information,and mine deep-level information about process operation to improve the performance of monitoring.Statistical process monitoring(SPM)is a data-driven method,which is based on multivariate statistical methodologies for online process malfunction detection and diagnosis through analysis and interpretation of collected measurement.In order to realize state monitoring of train operating equipment,a detective experiment system was set up in lab,using asynchronous motor as the simulation object of traction motor.The main works of this dissertation is stated as follows:1,Principal component analysis(PCA)was used to process multivariate data of motor to achieve state monitoring.This method can reduce the dimension of motor index and make state monitoring easier.And traditional PCA was improved in this paper,which was proved to be effective on theory and experiment.2,A lot of state monitoring experiments were carried out on experiment system,and PCA model was established by historical data.The experiment results validated that the approach can build an accurate monitoring model and detect abnormal state of motor effectively.3,A software system of state monitoring was developed for the experiment system in lab.This system can achieve data collection,data storage,real-time data display and state monitoring with two statistics.