TY - JOUR

T1 - Dconformer

T2 - A denoising convolutional transformer with joint learning strategy for intelligent diagnosis of bearing faults

AU - Li, Sheng

AU - Ji, J. C.

AU - Xu, Yadong

AU - Feng, Ke

AU - Zhang, Ke

AU - Feng, Jingchun

AU - Beer, Michael

AU - Ni, Qing

AU - Wang, Yuling

N1 - Funding Information: This work was partly supported by the Postgraduate Research & Practice Innovation Program of Jiangsu Province (Grant No. KYCX23_0647) and partly by the China Scholarship Council (CSC).

PY - 2024/3/15

Y1 - 2024/3/15

N2 - Rolling bearings are the core components of rotating machinery, and their normal operation is crucial to entire industrial applications. Most existing condition monitoring methods have been devoted to extracting discriminative features from vibration signals that reflect bearing health status. However, the complex working conditions of rolling bearings often make the fault-related information easily buried in noise and other interference. Therefore, it is challenging for existing approaches to extract sufficient critical features in these scenarios. To address this issue, this paper proposes a novel CNN-Transformer network, referred to as Dconformer, capable of extracting both local and global discriminative features from noisy vibration signals. The main contributions of this research include: (1) Developing a novel joint-learning strategy that simultaneously enhances the performance of signal denoising and fault diagnosis, leading to robust and accurate diagnostic results; (2) Constructing a novel CNN-transformer network with a multi-branch cross-cascaded architecture, which inherits the strengths of CNNs and transformers and demonstrates superior anti-interference capability. Extensive experimental results reveal that the proposed Dconformer outperforms five state-of-the-art approaches, particularly in strong noisy scenarios.

AB - Rolling bearings are the core components of rotating machinery, and their normal operation is crucial to entire industrial applications. Most existing condition monitoring methods have been devoted to extracting discriminative features from vibration signals that reflect bearing health status. However, the complex working conditions of rolling bearings often make the fault-related information easily buried in noise and other interference. Therefore, it is challenging for existing approaches to extract sufficient critical features in these scenarios. To address this issue, this paper proposes a novel CNN-Transformer network, referred to as Dconformer, capable of extracting both local and global discriminative features from noisy vibration signals. The main contributions of this research include: (1) Developing a novel joint-learning strategy that simultaneously enhances the performance of signal denoising and fault diagnosis, leading to robust and accurate diagnostic results; (2) Constructing a novel CNN-transformer network with a multi-branch cross-cascaded architecture, which inherits the strengths of CNNs and transformers and demonstrates superior anti-interference capability. Extensive experimental results reveal that the proposed Dconformer outperforms five state-of-the-art approaches, particularly in strong noisy scenarios.

KW - Complex working conditions

KW - Dconformer

KW - Fault diagnosis

KW - Noisy scenarios

KW - Rolling bearing

KW - Vibration signal

UR - http://www.scopus.com/inward/record.url?scp=85183457921&partnerID=8YFLogxK

U2 - 10.1016/j.ymssp.2024.111142

DO - 10.1016/j.ymssp.2024.111142

M3 - Article

AN - SCOPUS:85183457921

VL - 210

JO - Mechanical Systems and Signal Processing

JF - Mechanical Systems and Signal Processing

SN - 0888-3270

M1 - 111142

ER -