Search

• A multiscale denoising branch is developed to extract multi-level information and reduce noise interference. • An improved flow direction strategy-based adaptive resonance branch is introduced to learn fault-related periodic impulsive features. • Case studies are conducted to validate the efficacy of the developed IFD-MDCN. 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 work include: (1) designing a multiscale denoising branch to extract multi-level information and reduce noise impact. 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. [ABSTRACT FROM AUTHOR]

Fault diagnosis of rolling bearings has attracted extensive attention in industrial fields, which plays a vital role in guaranteeing the reliability, safety, and economical efficiency of mechanical systems. Traditional data-driven fault diagnosis methods require obtaining a dataset of full failure modes in advance as the training data. However, this kind of dataset is not always available in some critical industrial scenarios, which impairs the practicability of the data-driven fault diagnosis methods for various applications. A digital twin, which establishes a virtual representation of a physical entity to mirror its operating conditions, would make fault diagnosis of rolling bearings feasible when the fault data are insufficient. In this paper, we propose a novel digital twin-driven approach for implementing fault diagnosis of rolling bearings with insufficient training data. First, a dynamics-based virtual representation of rolling bearings is built to generate simulated data. Then, a Transformer-based network is developed to learn the knowledge of the simulated data for diagnostics. Meanwhile, a selective adversarial strategy is introduced to achieve cross-domain feature alignments in scenarios where the health conditions of the measured data are unknown. To this end, this study proposes a digital twin-driven fault diagnosis framework by using labeled simulated data and unlabeled measured data. The experimental results show that the proposed method can obtain high diagnostic performance when the real-world data is unlabeled and has unknown health conditions, proving that the proposed method has significant benefits for the health management of critical rolling bearings. • A digital twin-driven intelligent diagnosis method is developed. • A high-fidelity digital twin model is built for the rolling bearing. • A partial domain adaptation algorithm is introduced for bearing condition assessment. • One test is conducted to validate the effectiveness of the proposed methodology. [ABSTRACT FROM AUTHOR]