A Novel Reliability Analysis Approach With Collaborative Active Learning Strategy-Based Augmented RBF Metamodel
Metamodels in lieu of time-demanding performance functions can accelerate the reliability analysis effectively. In this paper, we propose an efficient collaborative active learning strategy-based augmented radial basis function metamodel (CAL-ARBF), for reliability analysis with implicit and nonline...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9247220/ |
| _version_ | 1818663217996496896 |
|---|---|
| author | Yanxu Wei Guangchen Bai Lu-Kai Song |
| author_facet | Yanxu Wei Guangchen Bai Lu-Kai Song |
| author_sort | Yanxu Wei |
| collection | DOAJ |
| description | Metamodels in lieu of time-demanding performance functions can accelerate the reliability analysis effectively. In this paper, we propose an efficient collaborative active learning strategy-based augmented radial basis function metamodel (CAL-ARBF), for reliability analysis with implicit and nonlinear performance functions. For generating the suitable samples, a CAL function is first designed to constrain the new samples being generated in sensitivity region, near limit state surface and keep certain distances mutually. Then by adjusting the adjustment coefficient of CAL function, the CAL-ARBF is mathematically modeled and the corresponding reliability analysis theory is developed. The effectiveness of the proposed approach is validated by four numerical samples, including global nonlinear problem, local nonlinear problem, nonlinear oscillator and truss structure. Through comparison of several state-of-the-art methods, the proposed CAL-ARBF is demonstrated to possess the computational advantages in efficiency and accuracy for reliability analysis. |
| first_indexed | 2024-12-17T05:13:21Z |
| format | Article |
| id | doaj.art-534135db679844c4896189f7f789232d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-17T05:13:21Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-534135db679844c4896189f7f789232d2022-12-21T22:02:11ZengIEEEIEEE Access2169-35362020-01-01819960319961710.1109/ACCESS.2020.30356709247220A Novel Reliability Analysis Approach With Collaborative Active Learning Strategy-Based Augmented RBF MetamodelYanxu Wei0Guangchen Bai1Lu-Kai Song2https://orcid.org/0000-0003-1571-7998School of Energy and Power Engineering, Beihang University, Beijing, ChinaSchool of Energy and Power Engineering, Beihang University, Beijing, ChinaSchool of Energy and Power Engineering, Beihang University, Beijing, ChinaMetamodels in lieu of time-demanding performance functions can accelerate the reliability analysis effectively. In this paper, we propose an efficient collaborative active learning strategy-based augmented radial basis function metamodel (CAL-ARBF), for reliability analysis with implicit and nonlinear performance functions. For generating the suitable samples, a CAL function is first designed to constrain the new samples being generated in sensitivity region, near limit state surface and keep certain distances mutually. Then by adjusting the adjustment coefficient of CAL function, the CAL-ARBF is mathematically modeled and the corresponding reliability analysis theory is developed. The effectiveness of the proposed approach is validated by four numerical samples, including global nonlinear problem, local nonlinear problem, nonlinear oscillator and truss structure. Through comparison of several state-of-the-art methods, the proposed CAL-ARBF is demonstrated to possess the computational advantages in efficiency and accuracy for reliability analysis.https://ieeexplore.ieee.org/document/9247220/Active learning functionradial basis functionreliability analysismetamodel |
| spellingShingle | Yanxu Wei Guangchen Bai Lu-Kai Song A Novel Reliability Analysis Approach With Collaborative Active Learning Strategy-Based Augmented RBF Metamodel IEEE Access Active learning function radial basis function reliability analysis metamodel |
| title | A Novel Reliability Analysis Approach With Collaborative Active Learning Strategy-Based Augmented RBF Metamodel |
| title_full | A Novel Reliability Analysis Approach With Collaborative Active Learning Strategy-Based Augmented RBF Metamodel |
| title_fullStr | A Novel Reliability Analysis Approach With Collaborative Active Learning Strategy-Based Augmented RBF Metamodel |
| title_full_unstemmed | A Novel Reliability Analysis Approach With Collaborative Active Learning Strategy-Based Augmented RBF Metamodel |
| title_short | A Novel Reliability Analysis Approach With Collaborative Active Learning Strategy-Based Augmented RBF Metamodel |
| title_sort | novel reliability analysis approach with collaborative active learning strategy based augmented rbf metamodel |
| topic | Active learning function radial basis function reliability analysis metamodel |
| url | https://ieeexplore.ieee.org/document/9247220/ |
| work_keys_str_mv | AT yanxuwei anovelreliabilityanalysisapproachwithcollaborativeactivelearningstrategybasedaugmentedrbfmetamodel AT guangchenbai anovelreliabilityanalysisapproachwithcollaborativeactivelearningstrategybasedaugmentedrbfmetamodel AT lukaisong anovelreliabilityanalysisapproachwithcollaborativeactivelearningstrategybasedaugmentedrbfmetamodel AT yanxuwei novelreliabilityanalysisapproachwithcollaborativeactivelearningstrategybasedaugmentedrbfmetamodel AT guangchenbai novelreliabilityanalysisapproachwithcollaborativeactivelearningstrategybasedaugmentedrbfmetamodel AT lukaisong novelreliabilityanalysisapproachwithcollaborativeactivelearningstrategybasedaugmentedrbfmetamodel |