KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis
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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/14/7932 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849406626481569792 |
|---|---|
| author | Shimin Shu Muchen Xu Peifeng Liu Peize Yang Tianyi Wu Jie Yang |
| author_facet | Shimin Shu Muchen Xu Peifeng Liu Peize Yang Tianyi Wu Jie Yang |
| author_sort | Shimin Shu |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-4eec646570a04f2bb13ccfeb928b76d2 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-4eec646570a04f2bb13ccfeb928b76d22025-08-20T03:36:19ZengMDPI AGApplied Sciences2076-34172025-07-011514793210.3390/app15147932KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault DiagnosisShimin Shu0Muchen Xu1Peifeng Liu2Peize Yang3Tianyi Wu4Jie Yang5School of Mechanical & Electrical Engineering, China University of Mining and Technology-Beijing, Beijing 100083, ChinaSchool of Mechanical & Electrical Engineering, China University of Mining and Technology-Beijing, Beijing 100083, ChinaSchool of Mechanical & Electrical Engineering, China University of Mining and Technology-Beijing, Beijing 100083, ChinaSchool of Mechanical & Electrical Engineering, China University of Mining and Technology-Beijing, Beijing 100083, ChinaSchool of Mechanical & Electrical Engineering, China University of Mining and Technology-Beijing, Beijing 100083, ChinaSchool of Mechanical & Electrical Engineering, China University of Mining and Technology-Beijing, Beijing 100083, ChinaFault 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.https://www.mdpi.com/2076-3417/15/14/7932bearingfault diagnosistransformercross-individualKolmogorov–Arnold |
| spellingShingle | Shimin Shu Muchen Xu Peifeng Liu Peize Yang Tianyi Wu Jie Yang KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis Applied Sciences bearing fault diagnosis transformer cross-individual Kolmogorov–Arnold |
| title | KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis |
| title_full | KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis |
| title_fullStr | KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis |
| title_full_unstemmed | KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis |
| title_short | KACFormer: A Novel Domain Generalization Model for Cross-Individual Bearing Fault Diagnosis |
| title_sort | kacformer a novel domain generalization model for cross individual bearing fault diagnosis |
| topic | bearing fault diagnosis transformer cross-individual Kolmogorov–Arnold |
| url | https://www.mdpi.com/2076-3417/15/14/7932 |
| work_keys_str_mv | AT shiminshu kacformeranoveldomaingeneralizationmodelforcrossindividualbearingfaultdiagnosis AT muchenxu kacformeranoveldomaingeneralizationmodelforcrossindividualbearingfaultdiagnosis AT peifengliu kacformeranoveldomaingeneralizationmodelforcrossindividualbearingfaultdiagnosis AT peizeyang kacformeranoveldomaingeneralizationmodelforcrossindividualbearingfaultdiagnosis AT tianyiwu kacformeranoveldomaingeneralizationmodelforcrossindividualbearingfaultdiagnosis AT jieyang kacformeranoveldomaingeneralizationmodelforcrossindividualbearingfaultdiagnosis |