IFD-MDCN: Multibranch denoising convolutional networks with improved flow direction strategy for intelligent fault diagnosis of rolling bearings under noisy conditions

Abstract

Rolling bearings are the core components of rotating machinery, and their normal operation is crucial to the entire industrial production. Most existing condition monitoring methods have been devoted to extracting discriminative features from vibration signals that reflect bearing health status information. However, the complex working conditions of rolling bearings often make the periodic impulsive characteristics related to fault information easily buried in noise interferences. Therefore, it is challenging for existing approaches to learning discriminative fault-related features in these scenarios. To address this issue, a novel multibranch CNN named IFD-MDCN is developed in this paper, which represents multibranch denoising convolutional networks (MDCN) with an improved flow direction (IFD) strategy. The main contributions of this research work include: 1) designing a multiscale denoising branch to extract multi-level information and reduce noise information. More specifically, the multiscale denoising branch adopts a Gaussian multi-level noise reduction procedure to represent vibration signals at multiple levels and filter out the noise components, and then it uses a multiscale convolutional module to extract abundant features from these denoised signal representations; 2) establishing an improved flow direction strategy-based adaptive resonance branch to learn periodic impulsive features associated with fault information from vibration signals. Extensive experimental results reveal that the IFD-MDCN outperforms five state-of-the-art approaches, especially in strong noise scenarios.