基于VMD-FFT与轻量化CNN的滚动轴承故障诊断方法研究OA

Aiming at the difficulties in extracting fault features of rolling bearings under strong noise interference and the problems of traditional Convolutional Neural Network(CNN)models such as large parameter volumes and susceptibility to overfitting,this paper proposes a fault diagnosis method based on Variational Mode Decomposition-Fast Fourier Transform(VMD-FFT)and a lightweight convolutional neural network.The proposed method employs VMD-FFT to achieve noise suppression,fault information enhancement,and input data compression,and incorporates a high dropout rate along with a compressed fully connected layer design to construct a lightweight CNN.Test results show that the proposed method significantly outperforms the baseline CNN in diagnostic accuracy,exhibits better intra-class compactness and clearer inter-class decision boundaries,and demonstrates strong robustness against noise.This approach provides a reliable solution for intelligent fault diagnosis of rolling bearings.