Fault Diagnosis of Rolling Bearings Based on Variational Mode Decomposition and Genetic Algorithm-Optimized Wavelet Threshold Denoising

Fault diagnosis of rolling bearings can be a serious challenge, as often work under complex conditions and their vibration signals are typically nonlinear nonstationary. This paper proposes novel approach to diagnosing faults based on variational mode decomposition (VMD) genetic algorithm-optimized wavelet threshold denoising. First, VMD was used decompose the faulty into series band-limited intrinsic functions (BLIMFs). During decomposition, parameters were selected by Kullback–Leibler (K–L) divergence. Then, effective BLIMFs determined analysis correlation coefficients variance contributions. Finally, denoising proposed optimize selection important parameters, optimized function not only ensures continuity but also avoids fixed deviation soft threshold. The validity superiority verified theoretical calculations, numerical simulations application studies. results indicate that is promising in fault rotary machinery.