Research On Fault Diagnosis Of Rolling Bearing Based On Compressed Sensing Noise Reduction And Spectral Kurtosis Method

With the continuous advancement of science and technology,intelligent manufacturing will become the mainstream of industrial production in the future.At the same time,in order to meet the needs of intelligent manufacturing,mechanical equipment is constantly developing in the direction of large-scale,integrated,high-speed and intelligent,which puts more stringent requirements on the safety of mechanical equipment.Rolling bearings are the most important components of mechanical equipment,especially rotating machinery.and their operating state is essential for the normal operation of the whole mechanical equipment.However,rolling bearing is one of the most vulnerable components in mechanical equipment.Therefore,its condition monitoring and early fault diagnosis are critical to the entire mechanical equipment.In this paper,the fault diagnosis technology of rolling bearing is firstly studied.The vibration mechanism and vibration characteristics of rolling bearing are researched based on the basic structure and running state of rolling bearing.On this basis,a comprehensive test of rolling bearing faults was designed and carried out by pre-setting faults.The Coinv DASP V11 intelligent data acquisition and analysis system was used to collect the vibration signals of various state bearings in the experiment,and then the MATLAB software platform was utilized for fault analysis and diagnosis.The diagnosis results are basically corresponding to the preset fault conditions,which proves the accuracy of the relevant analysis method in the fault diagnosis of rolling bearings.And by comparison.It can be also obtained that the impact of the vibration signal can become stronger with the deepening of the fault degree,when the rolling bearing fails.Secondly,the theory of compressed sensing is introduced into the fault diagnosis of rolling bearings.With its complex structure and working environment,rolling bearings are often affected by a variety of interference noise,which will have a great impact on fault diagnosis,especially early weak fault diagnosis.In this paper,the signal reconstruction technology based on compressed sensing theory is introduced into the vibration reduction of rolling bearing vibration signal.The key technology of vibration signal denoising is studied.The combination of simulation signal and experimental analysis proves that the compression sensing theory is in the rolling bearing fault vibration signal drop.Finally,a fault diagnosis method for rolling bearing is proposed based on compressed sensing theory and noise spectroscopy.With the sensitivity of the kurtosis of the vibration signal to the weak fault,the fault diagnosis technique is studied based on the spectral kurtosis method in rolling bearings.Combining the compressedsensing theory reconstruction with spectral kurtosis method,the fault diagnosis technology of rolling bearing is proposed based on compressed sensing theory and spectral kurtosis method.The technology is applied to diagnose the rolling bearing fault experimental data.The results show that the technology is complex and the diagnosis of weak faults in rolling bearings has good accuracy and reliability under background noise.