KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis

Shu, Shimin; Xu, Muchen; Liu, Peifeng; Yang, Peize; Wu, Tianyi; Yang, Jie

doi:10.3390/app15147932

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis

by

Shimin Shu

,

Muchen Xu

,

Peifeng Liu

,

Peize Yang

,

Tianyi Wu

and

Jie Yang

^*

School of Mechanical & Electrical Engineering, China University of Mining and Technology—Beijing, Beijing 100083, China

^*

Author to whom correspondence should be addressed.

Appl. Sci. 2025, 15(14), 7932; https://doi.org/10.3390/app15147932

Submission received: 17 June 2025 / Revised: 9 July 2025 / Accepted: 14 July 2025 / Published: 16 July 2025

Download Versions Notes

Featured Application

The proposed cross-individual diagnosis framework enables bearing fault detection across different bearing types without requiring target domain data, offering a plug-and-play solution for predictive maintenance in renewable energy systems that is particularly suitable for wind turbine maintenance and other industrial applications where labeled fault samples are scarce.

Abstract

Fault diagnosis methods based on deep learning have been widely applied to bearing fault diagnosis. However, current methods usually diagnose on the same individual device, which cannot guarantee reliability in real industrial scenarios, especially for new individual devices. This article explores a practical cross-individual scenario and proposes a Kolmogorov–Arnold enhanced convolutional transformer (KACFormer) model to improve both general feature representation and cross-individual capabilities. Specifically, the Kolmogorov–Arnold representation theorem is embedded into convolution and multi-head attention mechanisms to develop novel Kolmogorov–Arnold enhanced convolution (KAConv) and Kolmogorov–Arnold enhanced attention (KAA). The adaptive activation function enhances its nonlinear modeling ability. Comprehensive experiments are performed on two public datasets, demonstrating the superior generalization of the proposed KACFormer model with a higher accuracy of 95.73% and 91.58% compared to existing advanced models.

Keywords: bearing; fault diagnosis; transformer; cross-individual; Kolmogorov–Arnold

Share and Cite

MDPI and ACS Style

Shu, S.; Xu, M.; Liu, P.; Yang, P.; Wu, T.; Yang, J. KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis. Appl. Sci. 2025, 15, 7932. https://doi.org/10.3390/app15147932

AMA Style

Shu S, Xu M, Liu P, Yang P, Wu T, Yang J. KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis. Applied Sciences. 2025; 15(14):7932. https://doi.org/10.3390/app15147932

Chicago/Turabian Style

Shu, Shimin, Muchen Xu, Peifeng Liu, Peize Yang, Tianyi Wu, and Jie Yang. 2025. "KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis" Applied Sciences 15, no. 14: 7932. https://doi.org/10.3390/app15147932

APA Style

Shu, S., Xu, M., Liu, P., Yang, P., Wu, T., & Yang, J. (2025). KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis. Applied Sciences, 15(14), 7932. https://doi.org/10.3390/app15147932

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

Article Menu

KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis

Featured Application

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI