Global approximation of complex model based on adaptive sampling

doi:10.3785/j.issn.1008-973X.2022.09.015

Journal of ZheJiang University (Engineering Science)

2022, Vol. 56

Issue (9): 1815-1823 DOI: 10.3785/j.issn.1008-973X.2022.09.015

Global approximation of complex model based on adaptive sampling

Xiao-liang YIN(

),Cheng QIAN*(

)

College of information science and engineering, Jiaxing University, Jiaxing 314001, China

Download:

HTML

PDF(1562KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

A global approximation method combining adaptive sampling and surface curvature was proposed to deal with the problem of approximation processing of complex models. The adaptive design domain segmentation sampling method was used to obtain the new sampling points, and gradually improve the accuracy of the response surface approximation model of the source model. A method to determine the accuracy of the response surface approximation model was introduced, and a geometric method was proposed to calculate the surface curvature, and combined with the heuristic search algorithm (DIRECT) to search the maximum curvature point on the response surface model and the best segmentation position of the design domain. The proposed method can be applied to other response surface models and is suitable for the approximate processing of large design domain and large data source models. The approximate processing test results of function source model and complex pure electric vehicle model show that the proposed method is practical and effective.

Key words： response surface methodology adaptive sampling polynomial response surface surface curvature design domain segmentation

Received: 03 September 2021 Published: 28 September 2022

CLC:

TP 391.9

Fund: 浙江省基础公益研究计划项目 (GF20E090020)

Corresponding Authors: Cheng QIAN E-mail: 407392952@qq.com;qc117@sina.com

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Xiao-liang YIN
	Cheng QIAN

Cite this article:

Xiao-liang YIN,Cheng QIAN. Global approximation of complex model based on adaptive sampling. Journal of ZheJiang University (Engineering Science), 2022, 56(9): 1815-1823.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2022.09.015 OR https://www.zjujournals.com/eng/Y2022/V56/I9/1815

基于自适应采样的复杂模型全局近似

针对复杂模型近似处理的问题，提出自适应采样结合曲面曲率的全局近似方法. 采用自适应设计域分割采样方法获取新增采样点，逐步提高源模型的响应面近似模型精度. 引入判定响应面近似模型精度，提出利用几何方法计算曲面曲率，并结合启发式直接搜索算法（DIRECT）搜索响应面模型上的最大曲率点及设计域最佳分割位置. 所提方法可以运用于其他响应面模型，并适合用于大设计域、大数据源模型的近似处理. 函数源模型及复杂电动车模型的近似处理测试结果表明，所提方法具有实用性和有效性.

关键词： 响应面方法, 自适应采样, 多项式响应面, 曲面曲率, 设计域分割

Fig.1 First two iterations of design domain segmentation process using ASCGA

Fig.2 Global approximation flow chart based on ASCGA

Tab.1 Model parameters and ASCGA method parameter setting

Tab.2 Accuracy comparison of function approximation models constructed by three methods under different sampling numbers

Tab.3 Efficiency comparison of three methods for constructing function approximation models under different accuracies

Fig.3 Approximate processing of GF function model by ASCGA method (sample number: 100)

Fig.4 Approximate processing of Schaffer’s function model by ASCGA method (sample number: 150)

Fig.5 Electric vehicle simulation model

Fig.6 Light vehicle driving cycle FTP75

Fig.7 Three states of simulation model

Fig.8 Independent simulation module of simulation model

Fig.9 Handling of state variables in independent simulation module

Fig.10 Independent simulation module of passenger car model

Fig.11 Verify accuracy of approximate model on electric vehicle

Fig.12 Comparison of simulation results with different models under same operating condition


[1]	BÖTTCHER M, FUCHS A, LEICHSENRING F, et al ELSA: an efficient, adaptive ensemble learning-based sampling approach[J]. Advances in Engineering Software, 2021, 154: 102974 doi: 10.1016/j.advengsoft.2021.102974

[2]	BECK J, GUILLAS S Sequential design with mutual information for computer experiments (MICE): emulation of a tsunami model[J]. SIAM/ASA Journal Uncertainty Quantification, 2016, 4 (1): 739- 766 doi: 10.1137/140989613

[3]	GRATIET L L, CANNAMELA C Kriging-based sequential design strategies using fast cross-validation techniques for multi-fidelity computer codes[J]. Technometrics, 2015, 57 (3): 418- 427 doi: 10.1080/00401706.2014.928233

[4]	LIU H, XU S, MA Y, et al An adaptive Bayesian sequential sampling approach for global metamodeling[J]. Journal of Mechanical Design, 2016, 138 (1): 011404

[5]	KUCHERENKO S, GIAMALAKIS D, SHAH N, et al Computationally efficient identification of probabilistic design spaces through application of metamodeling and adaptive sampling[J]. Computers and Chemical Engineering, 2019, 132: 106608

[6]	郭述臻, 昂海松, 蔡红明一种自适应抽样的代理模型构建及其在复材结构优化中的应用[J]. 复合材料学报, 2018, 35 (8): 2084- 2094 GUO Shu-zhen, ANG Hai-song, CAI Hong-ming Construction of an adaptive sampling surrogate model and application in composite material structure optimization[J]. Acta Materiae Compositae Sinica, 2018, 35 (8): 2084- 2094

[7]	AJDARI A, MAHLOOJI H An adaptive exploration-exploitation algorithm for constructing metamodels in random simulation using a novel sequential experimental design[J]. Communications in Statistics: Simulation and Computation, 2013, 43 (5): 947- 968

[8]	EASON J, CREMASCHI S Adaptive sequential sampling for surrogate model generation with artificial neural networks[J]. Computers and Chemical Engineering, 2014, 68 (68): 220- 232

[9]	LIU H, XU S, WANG X, et al Optimal weighted pointwise ensemble of radial basis functions with different basis functions[J]. AIAA Journal, 2016, 54 (10): 3117- 3133 doi: 10.2514/1.J054664

[10]	JIANG P, SHU L, ZHOU Q, et al A novel sequential exploration-exploitation sampling strategy for global metamodeling[J]. IFAC-PapersOnLine, 2015, 48 (28): 532- 537 doi: 10.1016/j.ifacol.2015.12.183

[11]	STEINER M, BOURINET J M, LAHMER T An adaptive sampling method for global sensitivity analysis based on least-squares support vector regression[J]. Reliability Engineering and System Safety, 2019, 183: 323- 340 doi: 10.1016/j.ress.2018.11.015

[12]	WEN Z, PEI H, LIU H, et al A sequential Kriging reliability analysis method with characteristics of adaptive sampling regions and parallelizability[J]. Reliability Engineering and System Safety, 2016, 153: 170- 179 doi: 10.1016/j.ress.2016.05.002

[13]	谢雨珩, 李智, 杨明磊, 等基于自适应采样算法的芳烃异构化代理模型[J]. 化工学报, 2020, 71 (2): 688- 697 XIE Yu-heng, LI Zhi, YANG Ming-lei, et al Surrogate model of aromatic isomerization process based on adaptive sampling algorithm[J]. CIESC Journal, 2020, 71 (2): 688- 697

[14]	VAN D, COUCKUYT I, DESCHRIJVER D, et al A fuzzy hybrid sequential design strategy for global surrogate modeling of high-dimensional computer experiments[J]. SIAM Journal on Scientific Computing, 2015, 37 (2): 1020- 1039 doi: 10.1137/140962437

[15]	PAN G, YE P, WANG P, et al A sequential optimization sampling method for metamodels with radial basis functions[J]. The Scientific World Journal, 2014, 2014: 192862

[16]	SHAHSAVANI D, GRIMVALL A An adaptive design and interpolation technique for extracting highly nonlinear response surfaces from deterministic models[J]. Reliability Engineering and System Safety, 2009, 94 (7): 1173- 1182 doi: 10.1016/j.ress.2008.10.013

[17]	DIEZ M, VOLPI S, SERANI A, et al. Simulation-based design optimization by sequential multi-criterion adaptive sampling and dynamic radial basis functions [M]// MINISCI E, VASILE M, PERIAUX J, et al. Advances in evolutionary and deterministic methods for design, optimization and control in engineering and sciences. [S.l.]: Springer, 2019, 48: 213-228.

[18]	SERANI A, PELLEGRINI R, WACKERS J, et al Adaptive multi-fidelity sampling for CFD-based optimisation via radial basis function metamodels[J]. International Journal of Computational Fluid Dynamics, 2019, 33 (6/7): 237- 255

[19]	LI J X, PENG K, WANG W J, et al. Optimization design of rockoons based on improved sequential approximation optimization [C]// Proceeding of the Institution of Mechanical Engineering, Part G: Journal of Aerospace Engineer, 2022, 236(1): 140-153.

[1]	XIAO Wen-sheng, CUI Jun-guo, LIU Jian, WU Xiao-dong, HUANG Hong-sheng. Optimization study for reducing cogging torque in permanent magnet synchronous motor used for direct-drive oil pumping[J]. Journal of ZheJiang University (Engineering Science), 2015, 49(1): 173-180.

[2]	XIAO Wen-sheng, CUI Jun-guo, LIU Jian, WU Xiao-dong, HUANG Hong-sheng. ptimization study for reducing cogging torque in permanent magnet synchronous motor used for direct-drive oil pumping[J]. Journal of ZheJiang University (Engineering Science), 2014, 48(8): 1-8.

[3]	CHEN Zheng-jie,ZHU Wan-ping,ZHANG Shu-yan,WU Mian-bin,HE Juan,CHEN Hua. Optimization of fermentation conditions for production of a novel antifungal metabolite by response surface methodology[J]. Journal of ZheJiang University (Engineering Science), 2011, 45(10): 1868-1876.

[4]	LEI Ke-Jing, WANG Wen, CHEN Zi-Chen. Non-contact adaptive sampling for unknown free-form surface based on double-probe integration[J]. Journal of ZheJiang University (Engineering Science), 2010, 44(8): 1433-1440.

[5]	ZHANG Tao, CHEN Han-geng, ZHANG Xu, WEI Long-wu,QIAN Chao, CHEN Xin-zhi. Catalytic synthesis of N,N,N′,N′-tetramethylethylenediamine in fixed-bed reactor[J]. Journal of ZheJiang University (Engineering Science), 2010, 44(12): 2401-2405.

Viewed

Full text

Abstract

Cited

Shared

Discussed