Multi-Scale Channel Mixing Convolutional Network and Enhanced Residual Shrinkage Network for Rolling Bearing Fault Diagnosis

Li, Xiaoxu; Chen, Jiaming; Wang, Jianqiang; Wang, Jixuan; Wang, Jiahao; Li, Xiaotao; Kan, Yingnan

doi:10.3390/electronics14050855

Open AccessArticle

Multi-Scale Channel Mixing Convolutional Network and Enhanced Residual Shrinkage Network for Rolling Bearing Fault Diagnosis

by

Xiaoxu Li

¹,

Jiaming Chen

¹,

Jianqiang Wang

¹,

Jixuan Wang

¹,

Jiahao Wang

¹,

Xiaotao Li

^2,* and

Yingnan Kan

¹

School of Mechanical and Vehicle Engineering, Changchun University, Changchun 130022, China

²

School of Mechanical and Aeronautical Engineering, Jilin University, Changchun 130025, China

^*

Author to whom correspondence should be addressed.

Electronics 2025, 14(5), 855; https://doi.org/10.3390/electronics14050855

Submission received: 14 January 2025 / Revised: 19 February 2025 / Accepted: 20 February 2025 / Published: 21 February 2025

(This article belongs to the Section Artificial Intelligence)

Download

Browse Figures

Versions Notes

Abstract

Rolling bearing vibration signals in rotating machinery exhibit complex nonlinear and multi-scale features with redundant information interference. To address these challenges, this paper presents a multi-scale channel mixing convolutional network (MSCMN) and an enhanced deep residual shrinkage network (eDRSN) for improved feature learning and fault diagnosis accuracy in industrial settings. The MSCMN, applied in the initial and intermediate network layers, extracts multi-scale features from vibration signals, providing detailed information. By incorporating 1 × 1 convolutional blocks, the MSCMN mixes and reduces the feature dimensions, generating attention weights to suppress the interference from redundant information. Due to the high noise and nonlinear nature of industrial vibration signals, traditional linear layer representation is often inadequate. Thus, we propose an eDRSN with a Kolmogorov–Arnold Network–linear layer (KANLinear), which combines linear transformations with B-spline interpolation to capture both linear and nonlinear features, thereby enhancing threshold learning. Experiments on datasets from Case Western Reserve University and our laboratory validated the efficacy of the MSCMN-eDRSN model, which demonstrated improved diagnostic accuracy and robustness under noisy, real-world conditions.

Keywords: fault diagnosis; nonlinear features; feature fusion; enhanced residual shrinkage network

Share and Cite

MDPI and ACS Style

Li, X.; Chen, J.; Wang, J.; Wang, J.; Wang, J.; Li, X.; Kan, Y. Multi-Scale Channel Mixing Convolutional Network and Enhanced Residual Shrinkage Network for Rolling Bearing Fault Diagnosis. Electronics 2025, 14, 855. https://doi.org/10.3390/electronics14050855

AMA Style

Li X, Chen J, Wang J, Wang J, Wang J, Li X, Kan Y. Multi-Scale Channel Mixing Convolutional Network and Enhanced Residual Shrinkage Network for Rolling Bearing Fault Diagnosis. Electronics. 2025; 14(5):855. https://doi.org/10.3390/electronics14050855

Chicago/Turabian Style

Li, Xiaoxu, Jiaming Chen, Jianqiang Wang, Jixuan Wang, Jiahao Wang, Xiaotao Li, and Yingnan Kan. 2025. "Multi-Scale Channel Mixing Convolutional Network and Enhanced Residual Shrinkage Network for Rolling Bearing Fault Diagnosis" Electronics 14, no. 5: 855. https://doi.org/10.3390/electronics14050855

APA Style

Li, X., Chen, J., Wang, J., Wang, J., Wang, J., Li, X., & Kan, Y. (2025). Multi-Scale Channel Mixing Convolutional Network and Enhanced Residual Shrinkage Network for Rolling Bearing Fault Diagnosis. Electronics, 14(5), 855. https://doi.org/10.3390/electronics14050855

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Multi-Scale Channel Mixing Convolutional Network and Enhanced Residual Shrinkage Network for Rolling Bearing Fault Diagnosis

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI