Application of Adaptive Sampling Method in Hull Form Optimization

doi:10.16183/j.cnki.jsjtu.2021.179

Abstract

Abstract:

In order to handle the problem of complex and time-consuming simulation calculation in hull form optimization, the approximate model based on adaptive sampling has been widely used. In this paper, a maximum entropy (ME) adaptive sampling method based on uniform design (UD) is developed based on the Kriging approximate model and the leave-one-out (LOO) error method. Compared with the incremental Latin hypercube design (LHD) method, the adaptive sample distribution obtained by the proposed method are more uniform, and the accuracy of the global approximation model is higher. The proposed method is applied to the S60 hull form optimization, and the effectiveness is verified.

Key words: hull form optimization, adaptive sampling, uniform design (UD), maximum entropy (ME) sampling

CLC Number:

U661.31

OUYANG Xuyu, CHANG Haichao, LIU Zuyuan, FENG Baiwei, ZHAN Chengsheng, CHENG Xide. Application of Adaptive Sampling Method in Hull Form Optimization[J]. Journal of Shanghai Jiao Tong University, 2022, 56(7): 937-943.

Figures/Tables 13

Fig.1

Fig.2

Fig.3

Fig.4

Tab.1

Fig.5

Tab.2

Fig.6

Tab.3

Tab.4

Tab.5

Fig.7

Fig.8

References 11

[1]	王超, 高正红, 张伟, 等. 自适应设计空间扩展的高效代理模型气动优化设计方法[J]. 航空学报, 2018, 39(7): 121745. doi: 10.7527/S1000-6893.2018.21745
	WANG Chao, GAO Zhenghong, ZHANG Wei. et al. Efficient surrogate-based aerodynamic design optimization method with adaptive design space expansion[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(7): 121745. doi: 10.7527/S1000-6893.2018.21745
[2]	万德成, 缪爱琴, 赵敏. 基于水动力性能优化的船型设计研究进展[J]. 水动力学研究与进展, 2019, 34(6): 693-712.
	WAN Decheng, MIAO Aiqin, ZHAO Min. Research progress in ship design based on optimization of hydrodynamic performances[J]. Chinese Journal of Hydrodynamics, 2019, 34(6): 693-712.
[3]	LIU H T, XU S L, MA Y, et al. An adaptive Bayesian sequential sampling approach for global metamodeling[J]. Journal of Mechanical Design, 2016, 138(1): 011404. doi: 10.1115/1.4031905 URL
[4]	LIU H T, ONG Y S, CAI J F. A survey of adaptive sampling for global metamodeling in support of simulation-based complex engineering design[J]. Structural and Multidiplinary Optimization, 2018, 57(1): 393-416.
[5]	SHANNON C E. A mathematical theory of communication[J]. The Bell system technical journal, 1948, 27(3): 379-423. doi: 10.1002/j.1538-7305.1948.tb01338.x URL
[6]	LINDLEY D V. On a measure of the information provided by an experiment[J]. The Annals of Mathematical Statistics, 1956, 27(4): 986-1005. doi: 10.1214/aoms/1177728069 URL
[7]	SHEWRY M C, WYNN H P. Maximum entropy sampling[J]. Journal of Applied Statistics, 1987, 14(2): 165-170. doi: 10.1080/02664768700000020 URL
[8]	FANG K T. The uniform design: Application of number-theoretic methods in experimental design[J]. Acta Mathematicae Applicatae Sinica, 1980, 3: 363-372.
[9]	FANG K T, LIU M Q, QIN H, et al. Theory and application of uniform experimental designs[M]. Singapore: Springer Singapore, 2018.
[10]	CHANG H C, ZHAN C S, LIU Z Y, et al. Dynamic sampling method for ship resistance performance optimisation based on approximated model[J]. Ships and Offshore Structures, 2021, 16(4): 386-396. doi: 10.1080/17445302.2020.1730090 URL
[11]	冯佰威, 冯梅, 常海超, 等. 基于径向基插值的曲面变形方法在船型多目标优化中的应用[J]. 华南理工大学学报(自然科学版), 2019, 47(2): 128-136.
	FENG Baiwei, FENG Mei, CHANG Haichao, et al. Application of surface deformation method based on radial basis interpolation in multi-objective optimization of ship hull[J]. Journal of South China University of Technology (Natural Science Edition), 2019, 47(2): 128-136.

方法	参数				寻优结果
方法	初始样本数	训练样本数	测试样本数	RMSE	寻优结果
增量LHD方法	20	50	200	0.869	f(-6.9381, -6.7791)=6.0800
本文方法	20	50	200	0.799	f(0.0107, 0.0012)=0.0013

参数	取值
垂线间长L_PP/m	3.015
吃水T/m	0.163
湿表面积S_W/m²	1.604
Δ/m³	0.121
方形系数C_B	0.600

参数	初始值	上限	下限
Y₁	0.029	0.032	0.026
Y₂	0.024	0.026	0.020
Y₃	0.149	0.156	0.141
Y₄	0.127	0.132	0.122
Y₅	0.192	0.200	0.180
Y₆	0.130	0.135	0.125
Y₇	0.074	0.080	0.070
Y₈	0.018	0.021	0.015

参数	数值	参数	数值
Y₁	0.032	Y₅	0.185
Y₂	0.026	Y₆	0.131
Y₃	0.147	Y₇	0.077
Y₄	0.127	Y₈	0.020

参数	母型船	优化船	变化/%
Δ/m³	0.121	0.121	+0.00
S_W/m²	1.604	1.604	+0.00
C_W/10^-2	0.212	0.194	-8.49
R_T/N	5.688	5.510	-3.13