An adaptive hierarchical hybrid kernel ELM optimized by aquila optimizer algorithm for bearing fault diagnosis
Abstract As a critical component of rotating machinery, the operating status of rolling bearings is not only related to significant economic interests but also has a far-reaching impact on social security. Hence, ensuring an effective diagnosis of faults in rolling bearings is paramount in maintaini...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-04-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-94703-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849737471155240960 |
|---|---|
| author | Hao Yan Liangliang Shang Wan Chen Mengyao Jiang Tianqi lu Fei Li |
| author_facet | Hao Yan Liangliang Shang Wan Chen Mengyao Jiang Tianqi lu Fei Li |
| author_sort | Hao Yan |
| collection | DOAJ |
| description | Abstract As a critical component of rotating machinery, the operating status of rolling bearings is not only related to significant economic interests but also has a far-reaching impact on social security. Hence, ensuring an effective diagnosis of faults in rolling bearings is paramount in maintaining operational integrity. This paper proposes an intelligent bearing fault diagnosis method that improves classification accuracy using a stacked denoising autoencoder (SDAE) and adaptive hierarchical hybrid kernel extreme learning machine (AHHKELM). First, a hybrid kernel extreme learning machine (HKELM) is initially constructed, leveraging SDAE’s deep network architecture for automatic feature extraction. The hybrid kernel functions address the limitations of single kernel functions by effectively capturing both linear and nonlinear patterns in the data. Subsequently, the hierarchical hybrid kernel extreme learning machine (HHKELM) is refined through an enhanced Aquila Optimizer (AO) algorithm, which iteratively optimizes the kernel hyperparameter combination. The AO algorithm is further enhanced by incorporating chaos mapping, implementing a refined balanced search strategy, and fine-tuning parameter $$G_2$$ , which collectively improve its ability to escape local optima and conduct global searches, thus strengthening the robustness of the model during parameter optimization. Experimental results on the CWRU , MFPT and JNU datasets demonstrate that stacked denoising autoencoder-adaptive hierarchical hybrid kernel extreme learning machine (SDAE-AHHKELM) has better fault classification accuracy, robustness, and generalization than KELM and other methods. |
| format | Article |
| id | doaj-art-bda5bbb272354164a8ee90e182900b60 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-bda5bbb272354164a8ee90e182900b602025-08-20T03:06:54ZengNature PortfolioScientific Reports2045-23222025-04-0115112610.1038/s41598-025-94703-wAn adaptive hierarchical hybrid kernel ELM optimized by aquila optimizer algorithm for bearing fault diagnosisHao Yan0Liangliang Shang1Wan Chen2Mengyao Jiang3Tianqi lu4Fei Li5School of Electrical Engineering and Automation, Nantong UniversitySchool of Electrical Engineering and Automation, Nantong UniversitySchool of Electrical Engineering and Automation, Nantong UniversitySchool of Electrical Engineering and Automation, Nantong UniversitySchool of Electrical Engineering and Automation, Nantong UniversityAnhui Provincial Key Laboratory of Power Electronics and Motion Control, Anhui University of TechnologyAbstract As a critical component of rotating machinery, the operating status of rolling bearings is not only related to significant economic interests but also has a far-reaching impact on social security. Hence, ensuring an effective diagnosis of faults in rolling bearings is paramount in maintaining operational integrity. This paper proposes an intelligent bearing fault diagnosis method that improves classification accuracy using a stacked denoising autoencoder (SDAE) and adaptive hierarchical hybrid kernel extreme learning machine (AHHKELM). First, a hybrid kernel extreme learning machine (HKELM) is initially constructed, leveraging SDAE’s deep network architecture for automatic feature extraction. The hybrid kernel functions address the limitations of single kernel functions by effectively capturing both linear and nonlinear patterns in the data. Subsequently, the hierarchical hybrid kernel extreme learning machine (HHKELM) is refined through an enhanced Aquila Optimizer (AO) algorithm, which iteratively optimizes the kernel hyperparameter combination. The AO algorithm is further enhanced by incorporating chaos mapping, implementing a refined balanced search strategy, and fine-tuning parameter $$G_2$$ , which collectively improve its ability to escape local optima and conduct global searches, thus strengthening the robustness of the model during parameter optimization. Experimental results on the CWRU , MFPT and JNU datasets demonstrate that stacked denoising autoencoder-adaptive hierarchical hybrid kernel extreme learning machine (SDAE-AHHKELM) has better fault classification accuracy, robustness, and generalization than KELM and other methods.https://doi.org/10.1038/s41598-025-94703-wRolling bearingsFault diagnosisStacked denoising autoencodersExtreme learning machineAquila optimizer algorithm |
| spellingShingle | Hao Yan Liangliang Shang Wan Chen Mengyao Jiang Tianqi lu Fei Li An adaptive hierarchical hybrid kernel ELM optimized by aquila optimizer algorithm for bearing fault diagnosis Scientific Reports Rolling bearings Fault diagnosis Stacked denoising autoencoders Extreme learning machine Aquila optimizer algorithm |
| title | An adaptive hierarchical hybrid kernel ELM optimized by aquila optimizer algorithm for bearing fault diagnosis |
| title_full | An adaptive hierarchical hybrid kernel ELM optimized by aquila optimizer algorithm for bearing fault diagnosis |
| title_fullStr | An adaptive hierarchical hybrid kernel ELM optimized by aquila optimizer algorithm for bearing fault diagnosis |
| title_full_unstemmed | An adaptive hierarchical hybrid kernel ELM optimized by aquila optimizer algorithm for bearing fault diagnosis |
| title_short | An adaptive hierarchical hybrid kernel ELM optimized by aquila optimizer algorithm for bearing fault diagnosis |
| title_sort | adaptive hierarchical hybrid kernel elm optimized by aquila optimizer algorithm for bearing fault diagnosis |
| topic | Rolling bearings Fault diagnosis Stacked denoising autoencoders Extreme learning machine Aquila optimizer algorithm |
| url | https://doi.org/10.1038/s41598-025-94703-w |
| work_keys_str_mv | AT haoyan anadaptivehierarchicalhybridkernelelmoptimizedbyaquilaoptimizeralgorithmforbearingfaultdiagnosis AT liangliangshang anadaptivehierarchicalhybridkernelelmoptimizedbyaquilaoptimizeralgorithmforbearingfaultdiagnosis AT wanchen anadaptivehierarchicalhybridkernelelmoptimizedbyaquilaoptimizeralgorithmforbearingfaultdiagnosis AT mengyaojiang anadaptivehierarchicalhybridkernelelmoptimizedbyaquilaoptimizeralgorithmforbearingfaultdiagnosis AT tianqilu anadaptivehierarchicalhybridkernelelmoptimizedbyaquilaoptimizeralgorithmforbearingfaultdiagnosis AT feili anadaptivehierarchicalhybridkernelelmoptimizedbyaquilaoptimizeralgorithmforbearingfaultdiagnosis AT haoyan adaptivehierarchicalhybridkernelelmoptimizedbyaquilaoptimizeralgorithmforbearingfaultdiagnosis AT liangliangshang adaptivehierarchicalhybridkernelelmoptimizedbyaquilaoptimizeralgorithmforbearingfaultdiagnosis AT wanchen adaptivehierarchicalhybridkernelelmoptimizedbyaquilaoptimizeralgorithmforbearingfaultdiagnosis AT mengyaojiang adaptivehierarchicalhybridkernelelmoptimizedbyaquilaoptimizeralgorithmforbearingfaultdiagnosis AT tianqilu adaptivehierarchicalhybridkernelelmoptimizedbyaquilaoptimizeralgorithmforbearingfaultdiagnosis AT feili adaptivehierarchicalhybridkernelelmoptimizedbyaquilaoptimizeralgorithmforbearingfaultdiagnosis |