Rolling Bearing Fault Diagnosis Method Based on FFT-VMD Multiscale Information Fusion and SE-TCN Model  

作　　者：Chaozhi Cai Yuqi Ren Yingfang Xue Jianhua Ren 

机构地区：[1]School of Mechanical and Equipment Engineering,Hebei University of Engineering,Handan,056038,China

出　　处：《Structural Durability & Health Monitoring》2025年第3期665-682,共18页结构耐久性与健康监测(英文)

基　　金：supported by Handan Science and Technology Research and Development Plan Project under Grant no.23422901031;Key Laboratory of Intelligent Industrial Equipment Technology of Hebei Province(Hebei University of Engineering)under Grant no.202206.

摘　　要：Rolling bearings are important parts of industrial equipment,and their fault diagnosis is crucial to maintaining these equipment’s regular operations.With the goal of improving the fault diagnosis accuracy of rolling bearings under complex working conditions and noise,this study proposes a multiscale information fusion method for fault diagnosis of rolling bearings based on fast Fourier transform(FFT)and variational mode decomposition(VMD),as well as the Senet(SE)-TCNnet(TCN)model.FFT is used to transform the original one-dimensional time domain vibration signal into a frequency domain signal,while VMD is used to decompose the original signal into several inherent mode functions(IMFs)of different scales.The center frequency method also determines the number of mode decompositions.Then,the data obtained by the two methods are fused into data containing the bearing fault information of different scales.Finally,the fused data are sent to the SE-TCN model for training.Experimental tests are conducted to verify the performance of this method.The findings reveal that an average accuracy of 98.39%can be achieved when noise is added and can even reach 100%when the signal-to-noise ratio is 6 dB.When the load changes,the accuracy of the model can reach 97.45%.The proposed method has the characteristics of high accuracy and strong generalization ability in bearing fault diagnosis.Furthermore,it can effectively overcome the effects of noise and variable working conditions in actual industrial environments,thus providing some ideas for future practical applications of bearing fault diagnosis.

关 键 词：Fault diagnosis rolling bearing vibrational mode decomposition fast Fourier transform SE-TCN 

分 类 号：P31[天文地球—固体地球物理学]