Prediction And Assessment Method Of Fan Bearing Life In Traction Motor Of EMU

The rapid development of the high-speed rail business has caused people to increasingly increase the reliability of traction motor fans.Rolling bearings are important rotating parts to support the operation of fans.Accurate assessment of their service life is of great significance for the safety of the entire EMU and the reduction of enterprise operating costs.The rolling bearing improves the supporting force of the shaft by converting the sliding friction between the structures into rolling friction.There are many factors that lead to the failure of rolling bearings.In most cases,the bearings are stuck and broken due to fatigue spalling,high temperature burns,and improper installation.But no matter which type of failure,it will eventually be characterized by the abnormal change of the bearing vibration signal.Therefore,this paper takes the fan bearing of the traction motor replaced by the CRH380 BL EMU as the research object,and establishes its life assessment model based on the vibration signal of the bearing,and then predicts the remaining life of the fan bearing.By analyzing the structure and vibration mechanism of the rolling bearing,the vibration signal of the rolling bearing is related to its working state;the accelerated life test platform of the rolling bearing is built,and the vibration signal and life data of the rolling bearing's entire life span are collected;according to the collected vibration The amplitude characteristics of the signal change law,and it is found that the vibration signal will change correspondingly in the different life spans of the bearing;according to the extraction and analysis of the time-domain characteristics of the bearing,it is found that the RMS of acceleration can accurately describe the decline trend of the bearing,can be used as a predictive label for the bearing life evaluation model,so this paper turns the problem of predicting the life of the bearing into a problem of predicting the decay threshold of its RMS of acceleration.Aiming at the problem that the traditional time domain analysis or frequency domain analysis methods cannot fully describe the running state of rolling bearings,a time-frequency decomposition method of bearing vibration signals based on empirical mode decomposition(EMD)algorithm is proposed.The decomposed inherent modal function(IMF)contains both the time domain information and the frequency domain information of the bearing.The algorithm does not need to set the windowing function and wavelet basis function in advance.It can describe the decline performance of the bearing according to the change of the IMF component.It is fast and clear in physical meaning.After completing the extraction and analysis of the feature of the bearing vibration signal,it is proposed to input the IMF component decomposed by the EMD algorithm as the feature of the bearing and input it into the support vector regression(SVR)model,and construct the EMD-SVR model.The SVR model predicts the remaining service life of the rolling bearing.After comparison with the actual test data,the results show that the prediction accuracy of the model reaches 97.85%,while the prediction accuracy of the SVR model based on time feature is only 87.14%.It is proved that the EMD-SVR model can improve the accuracy of prediction and assessment of bearing service life.Using the EMD-SVR model to predict the remaining service life of unfailed bearings under test conditions,the result is 301 hours;the calculation method of the acceleration coefficient of rolling bearings under test conditions and actual conditions is derived;After calculation,the remaining service life of the fan bearing in the traction motor replaced by the third-level repair of the EMU is about 25293.03 hours.According to the field running time data of CRH380 BL EMU provided by the company,the actual remaining service life of the bearing after the third-level repair is 25310.3 hours,which is 17.27 hours different from the predicted life of this article,which meets the requirements of the company,so it can meet vehicle safety driving demand.