Research On Fault Diagnosis Of Vibration Mechanical Rolling Bearing

As the core components of vibration machinery,rolling bearings play an important role in the normal operation of vibration machinery.Studying the fault diagnosis of vibration mechanical rolling bearing is of great significance to improving the working efficiency of the vibration machinery,saving maintenance costs and reducing economic losses.Fault feature extraction and fault pattern recognition are the most critical steps in fault diagnosis,and they are also the focus of this study.In this paper,rolling bearing used in vibrating screen is taken as the research object,modern signal processing technology is used to introduce and research the fault feature extraction method and failure mode identification method of rolling bearing.The main research content of this paper is as follows:(1)In this paper,the fault feature extraction method based on time-frequency domain analysis is studied.According to the characteristics of strong background noise of vibration signal of vibration mechanical rolling bearings,a minimal entropy deconvolution(MED)and variational mode decomposition(VMD)phase are proposed.Based on the fault feature extraction method,the modal component with the largest kurtosis value is selected as the optimal modal component according to the characteristics of the fault signal.The Hilbert envelope is used to obtain the fault characteristic information of the vibration mechanical rolling bearing.(2)The application of neural network in fault pattern recognition is studied.Self organizing competitive neural network(SOM)and probabilistic neural network(PNN)are studied.According to the uncertainty characteristic of vibration signal of rolling bearing,the fault feature vector is constructed by variational mode decomposition and multi-scale arrangement entropy,and the fault characteristic vector of the rolling bearing is simulated in the neural network.The validity of fault feature vectors and the practicability of PNN and SOM in fault pattern recognition are proved.(3)Using Visaul Studio C# and MATLAB for mixed programming technology,developed a fault diagnosis system for vibration mechanical rolling bearing,which improved the efficiency and intelligent effect of fault diagnosis of rolling bearings.