A novel patch-matching 2D denoising method for fault diagnosis of roller bearings

The vibration signal of roller bearings contains important information, but the strong background noise makes fault diagnosis difficult. In this paper, inspired by the idea of block matching 3D (BM3D) algorithm, using local and nonlocal correlation of vibration signal, a patch-matching 2 dimensional (PM2D) denoising method is proposed firstly to suppress noise in vibration signals. The proposed denoising method constructs similarity matrices of component modules, which are used for threshold processing to determine the coefficients of the two-dimensional discrete cosine transform, so as to achieve optimal denoising performance. Then empirical mode decomposition (EMD) and envelope analysis are employed to perform fault diagnosis. The proposed PM2D denoising method and fault diagnosis strategies are applied to both simulated and measured signals. A comparison study shows the superiority of the proposed method over the other existing denoising methods.