Research On Temperature Warning Of Axle Box Bearing Of High-speed Train Based On NSET

Axle box bearings are one of the key parts in the running process of high-speed trains.Studying the temperature warning of axle box bearings of high-speed trains is of great significance to ensure the safe and efficient operation of trains.In view of the fact that the current high-speed train axle temperature detection system cannot find the early abnormal temperature rise of the axle box bearing in time,in this paper,the temperature of the axle box bearing of a certain high-speed train is taken as the research object,and the NSET bearing temperature prediction model is established based on the nonlinear state estimation(NSET)theory.Based on the model,using LabVIEW and MATLAB for mixed programming,a temperature warning system for the axle box bearing of a specific running route of a high-speed train is designed.The system has an early warning effect on the early abnormal temperature rise of the bearing,which can reduce the incidence of bearing failure and help the bearing operation and maintenance.Initially,the structure of the axle box bearing of a high-speed train is introduced in this paper,and the temperature detection method of the axle box bearing is summarized,including the principle of the bearing temperature detector(shaft temperature sensor)and the principle of the real-time detection system of the shaft temperature.Then,the thermal model of the bearing is established from the perspective of heat transfer,and the correlation analysis of the bearing temperature of the axle box is carried out by SPSS software.The influencing factors of the bearing temperature are summarized by combining two methods.It provides a basis for the selection of the feature data of NSET model.Secondly,the principle of nonlinear state estimation,the modeling principle and modeling process based on NSET,and the process of temperature warning system based on NSET model are studied.Taking the temperature data of the axle box bearing of a certain high-speed train as an example,select reasonable feature data and preprocess,then establish NSET bearing temperature prediction model based on fixed distance and Mahalanobis distance,respectively,and temperature prediction model based on BP neural network,temperature prediction model based on PSO-BP neural network.Then validate the above four models and analyze and compare the prediction results of each model,proving the superiority of the NSET modeling method based on the Mahalanobis distance in the prediction of the axle box bearing temperature of high-speed trains.Ultiamtely,based on the NSET algorithm of Mahalanobis distance,using LabVIEW and MATLAB for mixed programming,a temperature warning system for the axle box bearing of a specific running route of a high-speed train is designed.After verification of the data collected on site,the system can realize early warning of abnormal temperature rise of the axle box bearings of each car box of high-speed trains.which has a positive effect on the safe operation and maintenance of axle box bearings.