Research On Recognition Method Of Acoustic Emission Characteristics Of Rolling Bearing Fault

Rotating machinery is the most common mechanical system in mechanical equipment.Fault diagnosis of rotating machinery is a hot research direction.Since China proposed the era of industrial 4.0 and made in China 2025,the online detection of equipment health monitoring and fault diagnosis has become a key point.In this paper,rolling bearing,the core component of rotating machinery,is used as the research object for fault diagnosis.Acoustic emission detection technology is used to collect the normal and 4 kinds of faulty bearing acoustic emission signals from the OPZZ-II rotating machinery fault simulation experiment platform in real time.Aiming at the shortcomings of the existing fault diagnosis methods for rolling bearings,some improved methods are proposed to accurately diagnose and identify the fault characteristics of acoustic emission signals.The research content of this paper are as follows:(1)This paper describes the connection between metal materials and acoustic emission,explains how the faulty rolling bearing produces acoustic emission signal,and specifically describes the collective test of faulty rolling bearing.(2)A new information processing method,APFFT/FFT-EMD algorithm,is proposed,which solves the problem that it is difficult to obtain the characteristics of the acoustic emission signal of the rolling bearing failure due to the large number of IMF components that cannot be effectively selected after EMD algorithm.This method uses the combination of APFFT/FFT algorithm and EMD algorithm.After merging the idea of APFFT/FFT comprehensive phase difference correction with EMD algorithm,the first two IMF components are used for signal reconstruction.The signal is verified by Hilbert spectrum.The analysis results of simulated and measured acoustic emission signal show that the method can effectively extract the rolling bearing outer ring fault information.(3)For the acoustic emission characteristic parameters of rolling bearing failure,three kinds of three-dimensional characteristic diagrams are drawn and analyzed by selecting eight characteristic parameters.By analyzing the changes of acoustic emission characteristic parameters,normal bearing and faulty rolling bearing can be better identified.(4)Aiming at the problem of rolling bearing fault recognition,a fault recognition algorithm based on Cuckoo search algorithm and BP neural network is proposed.The cuckoo search algorithm is a parasitic and Levi's flight parallel mechanism,which has an efficient optimization mode and can achieve global optimization.The CS-BP algorithm has the advantages of high accuracy compared with BP,GA-BP,PSO-BP and APSO-BP recognition algorithm by training and testing the acoustic emission characteristic parameters of rolling bearing fault.