An improved adaptive surrogate model and application in thermal management system design
It is time-consuming to obtain the responses of real or high-precision simulation models in complex engineering problems. The surrogate model based on sample points can approximate the real model and thus greatly reduce the computational effort. The selection of sample points has a great influence o...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-10-01
|
| Series: | Materials & Design |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0264127521004366 |
| _version_ | 1818692853708095488 |
|---|---|
| author | Huanwei Xu Hao Li Ge Xiang Xin Zhang |
| author_facet | Huanwei Xu Hao Li Ge Xiang Xin Zhang |
| author_sort | Huanwei Xu |
| collection | DOAJ |
| description | It is time-consuming to obtain the responses of real or high-precision simulation models in complex engineering problems. The surrogate model based on sample points can approximate the real model and thus greatly reduce the computational effort. The selection of sample points has a great influence on the accuracy of the surrogate model. Aiming at the problem of sample point selection in the process of establishing surrogate model, an adaptive sampling method based on distance density and local complexity is proposed. In this method, distance density is used to quantify the sparsity of new sample points, and local complexity is applied to quantify the change complexity of response values near new sample points. The high-quality of new sample point is added to improve the accuracy of the surrogate model. This method is compared with two other classical adaptive sampling methods through nine test functions. The results show that this method can make the new sample point more distributed in the key area of sample space, so that fewer sample points are used to establish a high-precision surrogate model. Finally, the effectiveness of this method is verified through an optimization of the thermal management system design for liquid-cooled cylindrical batteries. |
| first_indexed | 2024-12-17T13:04:23Z |
| format | Article |
| id | doaj.art-18f134c4f0f54e0cb39e62536f34c477 |
| institution | Directory Open Access Journal |
| issn | 0264-1275 |
| language | English |
| last_indexed | 2024-12-17T13:04:23Z |
| publishDate | 2021-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Materials & Design |
| spelling | doaj.art-18f134c4f0f54e0cb39e62536f34c4772022-12-21T21:47:17ZengElsevierMaterials & Design0264-12752021-10-01208109883An improved adaptive surrogate model and application in thermal management system designHuanwei Xu0Hao Li1Ge Xiang2Xin Zhang3Corresponding author.; School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaIt is time-consuming to obtain the responses of real or high-precision simulation models in complex engineering problems. The surrogate model based on sample points can approximate the real model and thus greatly reduce the computational effort. The selection of sample points has a great influence on the accuracy of the surrogate model. Aiming at the problem of sample point selection in the process of establishing surrogate model, an adaptive sampling method based on distance density and local complexity is proposed. In this method, distance density is used to quantify the sparsity of new sample points, and local complexity is applied to quantify the change complexity of response values near new sample points. The high-quality of new sample point is added to improve the accuracy of the surrogate model. This method is compared with two other classical adaptive sampling methods through nine test functions. The results show that this method can make the new sample point more distributed in the key area of sample space, so that fewer sample points are used to establish a high-precision surrogate model. Finally, the effectiveness of this method is verified through an optimization of the thermal management system design for liquid-cooled cylindrical batteries.http://www.sciencedirect.com/science/article/pii/S0264127521004366Surrogate modelAdaptive samplingDistance densityLocal complexityThermal management system design |
| spellingShingle | Huanwei Xu Hao Li Ge Xiang Xin Zhang An improved adaptive surrogate model and application in thermal management system design Materials & Design Surrogate model Adaptive sampling Distance density Local complexity Thermal management system design |
| title | An improved adaptive surrogate model and application in thermal management system design |
| title_full | An improved adaptive surrogate model and application in thermal management system design |
| title_fullStr | An improved adaptive surrogate model and application in thermal management system design |
| title_full_unstemmed | An improved adaptive surrogate model and application in thermal management system design |
| title_short | An improved adaptive surrogate model and application in thermal management system design |
| title_sort | improved adaptive surrogate model and application in thermal management system design |
| topic | Surrogate model Adaptive sampling Distance density Local complexity Thermal management system design |
| url | http://www.sciencedirect.com/science/article/pii/S0264127521004366 |
| work_keys_str_mv | AT huanweixu animprovedadaptivesurrogatemodelandapplicationinthermalmanagementsystemdesign AT haoli animprovedadaptivesurrogatemodelandapplicationinthermalmanagementsystemdesign AT gexiang animprovedadaptivesurrogatemodelandapplicationinthermalmanagementsystemdesign AT xinzhang animprovedadaptivesurrogatemodelandapplicationinthermalmanagementsystemdesign AT huanweixu improvedadaptivesurrogatemodelandapplicationinthermalmanagementsystemdesign AT haoli improvedadaptivesurrogatemodelandapplicationinthermalmanagementsystemdesign AT gexiang improvedadaptivesurrogatemodelandapplicationinthermalmanagementsystemdesign AT xinzhang improvedadaptivesurrogatemodelandapplicationinthermalmanagementsystemdesign |