Remote Fault Diagnosis Methods Research And System Development Of Locomotive Running Gear Rolling Bearing

Along with the development of the technology,the locomotive is developing towards high-speed,intelligence and complication.At the same time,the importance of the maintenance of locomotive becomes more prominent.As a key component of the locomotive,the rolling bearings play a important role of bearing gravity,transmitting torque,and reducing the wear.As it works in the environment with strong vibration,and load imbalance for an extended period,it has a higher failure rate of components for locomotive running gear.So in view of the research in fault diagnosis method for locomotive rolling bearing and system development,it is of great significance to ensure running safety and reliable operation,improve the safety of railway transportation.At the same time,it lays the foundation for the development of the condition monitoring and fault diagnosis system in the locomotive running gear.According to the vibration signal of rolling bearing which presents the strong nonlinear and non-stationary characteristics,this paper firstly combines with the wavelet analysis to reduce the noise and extract the energy feature information from the vibration signal of the rolling bearing and it is used to form the rolling bearing fault feature set.Then using the method of principal component analysis to extract the fault feature from the fault feature set and eliminate the redundant information,to improve the validity of the fault feature set.Secondly,research on the multi classification algorithm and the model for the fault diagnosis of the rolling bearing is made,which is based on the least squares support vector machine.Aiming at the problem that the parameters of the fault diagnosis model are selected hardly,this paper raises the fault diagnosis model of rolling bearing for the locomotive running gear based on the least squares support vector machine of the particle swarm optimization by means of particle swarm optimization algorithm for iterative optimization and the study on the characteristics of fault samples.It achieves accurate diagnosis and classification of the locomotive rolling bearing fault mode.In the end,this paper develops the remote fault diagnosis system for the locomotive rolling bearing combined with the technology of the ASP.NET and MATLAB.Preliminary realized the diagnosis with remote and intelligent,which solves the problem of "over-maintain" and "ill-maintain" of the bearing.It will further to ensure the safety,reliable operation of the locomotive running gear,and to reduce the cost of the maintenance.In the meantime it will provide technical support for locomotive online maintenance and revamping optimization of the 6A system.