Abstract: In order to effectively remove the noise interference in the partial discharge signal, a denoising method based on improved VMD algorithm and L-M neural network is proposed. The optimal mode decomposition levels of VMD algorithm were adaptively determined by noise preprocessing and decomposition energy error. The normal distribution histogram was introduced to distinguish the partial discharge signal from the narrowband interference signal and reconstruct the partial discharge signal. L-M neural network was used to fit and filter the residual white noise. The proposed method was used to denoise the simulated and measured signals, and was compared with the traditional denoising methods. The results show that the denoising evaluation index of the proposed method is more obvious and the removal effect of noise interference is better.