基于代理模型的三立柱半潜平台多目标优化

doi:10.16183/j.cnki.jsjtu.2019.087

摘要/Abstract

摘要：

在半潜平台初始设计阶段，平台主尺度是影响平台水动力性能和建造成本的关键性因素．因此，对半潜平台主尺度进行多目标优化是一项极具工程意义的研究工作．首先，采用试验设计法确定平台的设计变量和样本数据库．其次，对半潜平台采用面元法和莫里森公式结合的方法进行水动力特性分析．同时在静水面上布置波面升高监测点，计算平台气隙值．根据数值模拟得到的数据库建立基于径向基函数的代理模型，并通过缺一交叉验证法得到径向基函数中的形参数值．所建立的代理模型可以极大提高优化效率．最后，采用多目标粒子群优化算法，以平台安全性和经济性作为两个优化目标，以平台稳性、气隙高度、水平方向运动性能作为约束条件，得到半潜平台的优化方案．通过对半潜平台多目标优化方案的分析，最终提出三立柱半潜平台最高效的优化策略．

关键词: 多目标粒子群优化算法, 代理模型, 缺一交叉验证法, 径向基函数

Abstract:

In the initial design stage of a semi-submersible platform, the main particulars of the platform are the key factor affecting the hydrodynamic performance and construction cost. Therefore, multi-objective optimization of the main particulars of the semi-submersible platform is of great engineering significance. First, the design variables of each platform and sample database are determined by design of experiments. Then, the hydrodynamic performances of the semi-submersible platform are analyzed by using the panel method and Morison’s equation. The distribution of probes for estimating the wave elevations on the calm water surface is arranged, and the airgap can be computed. Based on the database obtained by numerical simulation, the surrogate models based on radial basis function (RBF) are established. Next, the formal parameters in RBF are obtained by using the leave-one-out cross validation method. The surrogate model can greatly improve the optimization efficiency. Finally, by using the multi-objective particle swarm optimization (MOPSO) method, taking safety and economy of offshore platforms as two optimization objectives, and taking platform stability, airgap and horizontal motion performance as constraints, the optimization program for the semi-submersible platform can be obtained. Through the detailed analyses of the optimization program for the semi-submersible platform, the most efficient design strategy for the three-column semi-submersible platform is proposed.

Key words: multi-objective particle swarm optimization (MOPSO), surrogate model, leave-one-out cross validation, radial basis function

中图分类号:

P751

丘文桢, 宋兴宇, 张新曙. 基于代理模型的三立柱半潜平台多目标优化[J]. 上海交通大学学报, 2021, 55(1): 11-20.

QIU Wenzhen, SONG Xingyu, ZHANG Xinshu. Multi-Objective Optimization of Three-Column Semi-Submersible Platforms Based on Surrogate Models[J]. Journal of Shanghai Jiao Tong University, 2021, 55(1): 11-20.

图/表 16

图1

图2

图3

图4

图5

表1

图6

图7

表2

图8

表3

图9

图10

表4

图11

图12

参考文献 14

[1]	张新曙，尤云祥，滕明清．深海半潜浮式生产平台关键理论与技术问题[J].海洋工程，2016, 34(1): 117-123.
	ZHANG Xinshu, YOU Yunxiang, TENG Mingqing. Review of the key theories and technologies for the development of deep-sea semi-submersible floating production unit[J]. The Ocean Engineering, 2016, 34(1): 117-123.
[2]	陈新权，谭家华. 基于遗传算法的超深水半潜式平台优化[J]. 中国海洋平台，2006, 21(6): 24-27.
	CHEN Xinquan, TAN Jiahua. Principal dimensions optimization of semisubmersible for ultra-deepwater based on genetic algorithm[J]. China Offshore Platform, 2006, 21(6): 24-27.
[3]	PARK Y, JANG B S, KIM J D. Hull-form optimization of semi-submersible FPU considering seakeeping capability and structural weight[J]. Ocean Engineering, 2015, 104: 714-724.
[4]	KIM D J, JANG B S. Application of multi-objective optimization for TLP considering hull-form and tendon system[J]. Ocean Engineering, 2016, 116: 142-156.
[5]	ZHANG X S, SONG X Y, YUAN Z M, et al. Glo-bal motion and airgap computations for semi-submersible floating production unit in waves[J]. Ocean Engineering, 2017, 141: 176-204.
[6]	周佳，尉志源，王璞. 半潜式生产平台整体设计与方案优化[J]. 中国海洋平台，2017, 32(1): 21-25.
	ZHOU Jia, WEI Zhiyuan, WANG Pu. Semi-submersible production unit design and optimization[J]. China Offshore Platform, 2017, 32(1): 21-25.
[7]	ZHANG X S, SONG X Y, QIU W Z, et al. Multi-objective optimization of Tension Leg Platform using evolutionary algorithm based on surrogate model[J]. Ocean Engineering, 2018, 148: 612-631.
[8]	LIU B, YANG H, LANCASTER M J. Global optimization of microwave filters based on a surrogate model-assisted evolutionary algorithm[J]. IEEE Transactions on Microwave Theory and Techniques, 2017, 65(6): 1976-1985.
[9]	BAIRD S, BOHREN J A, MCINTOSH C, et al. Optimal design of experiments in the presence of interference[J]. The Review of Economics and Statistics, 2018, 100(5): 844-860.
[10]	NAZARI J, NILI AHMADABADI M, ALMASIEH H. The method of radial basis functions for the solution of nonlinear Fredholm integral equations system[J]. Journal of Linear and Topological Algebra, 2017, 6(1): 11-28.
[11]	MARINI F, WALCZAK B. Particle swarm optimization (PSO). A tutorial[J]. Chemometrics and Intelligent Laboratory Systems, 2015, 149: 153-165.
[12]	GARG H. A hybrid PSO-GA algorithm for constrained optimization problems[J]. Applied Mathematics and Computation, 2016, 274: 292-305.
[13]	REYES-SIERRA M, COELLO C A C. Multi-objective particle swarm optimizers: A survey of the state-of-the-art[J]. International Journal of Computational Intelligence Research, 2006, 2(3): 287-308.
[14]	PENG G, FANG Y W, PENG W S, et al. Multi-objective particle optimization algorithm based on sharing-learning and dynamic crowding distance[J]. Optik, 2016, 127(12): 5013-5020.

主尺度	数值
D/m	24
FB/m	20
CD/m	10
CS/m	26.6
HPL/m	15
Δ/t	6 428

海况参数	数值
H_s/m	15.8
T_p/s	15.4
γ	3.3
σ_a,σ_b	0.07, 0.09
t/h	3
f(θ)	2cos²(θ)/π

设计变量	上界	下界	步长
D/m	26.40	21.60	1.20
CS/m	29.26	23.94	2.66
CD/m	11.00	9.00	1.00
HPL/m	13.50	16.50	0.75

序号	D/m	CS/m	CD/m	HPL/m	X_3，max/m	ΔX_3，max/%	W₁×10^－3/t	ΔW₁/%
00	24	26.6	10	15	4.61	0	6.43	0
01	26.39	25.13	9.41	14.63	3.99	－13.47	6.25	－2.80
02	26.39	25.18	9.36	14.52	3.99	－13.43	6.17	－4.05
03	26.39	25.18	9.31	14.49	4.00	－13.33	6.11	－4.91
04	26.39	25.24	9.28	14.39	4.00	－13.21	6.06	－5.69
05	26.29	25.16	9.21	14.37	4.03	－12.68	5.96	－7.30
06	26.26	25.15	9.16	14.34	4.04	－12.28	5.90	－8.27
07	26.12	25.25	9.09	14.36	4.11	－10.91	5.79	－9.96
08	26.39	25.24	9.03	14.39	4.13	－10.48	5.77	－10.22
09	25.82	25.23	9.10	14.26	4.13	－10.38	5.73	－10.89
10	25.71	25.25	9.09	14.35	4.16	－9.71	5.71	－11.25
11	25.27	25.23	9.14	14.31	4.19	－9.17	5.67	－11.77
12	25.00	25.16	9.12	14.27	4.23	－8.24	5.59	－13.01
13	24.86	25.20	9.11	14.30	4.26	－7.66	5.56	－13.51
14	24.80	25.16	9.09	14.29	4.28	－7.18	5.52	－14.17
15	24.62	25.29	9.09	14.30	4.31	－6.47	5.48	－14.72
16	24.28	25.03	9.12	14.29	4.33	－6.14	5.45	－15.25
17	24.36	25.14	9.07	14.17	4.34	－5.79	5.40	－15.98
18	24.15	25.14	9.07	14.17	4.37	－5.21	5.36	－16.61
19	23.62	25.22	9.15	14.35	4.41	－4.32	5.35	－16.80
20	23.62	25.13	9.07	14.17	4.44	－3.61	5.25	－18.32
21	23.14	25.01	9.12	14.20	4.47	－2.99	5.21	－18.96
22	23.17	25.13	9.07	14.12	4.50	－2.33	5.16	－19.78
23	22.86	25.25	9.11	14.21	4.52	－2.00	5.15	－19.90
24	22.72	25.20	9.11	14.35	4.56	－1.16	5.13	－20.25
25	22.54	25.16	9.07	14.19	4.59	－0.52	5.04	－21.63
26	22.52	25.31	9.03	14.16	4.62	0.25	5.00	－22.19
27	22.32	25.33	9.05	14.29	4.66	1.02	4.98	－22.48
28	22.10	25.45	9.05	14.36	4.71	2.24	4.95	－23.06
29	21.77	25.37	9.01	14.36	4.80	4.08	4.85	－24.64
30	21.67	25.76	9.01	14.37	4.87	5.71	4.83	－24.95

[1]	陶威, 刘钊, 许灿, 朱平. 三维正交机织复合材料翼子板多尺度可靠性优化设计[J]. 上海交通大学学报, 2021, 55(5): 615-623.
[2]	张宇, 王晓亮. 基于显式动力学的软式飞艇流固耦合计算框架[J]. 上海交通大学学报, 2021, 55(3): 311-319.
[3]	陈永信. 滑翔飞行器气动外形与轨迹一体化设计优化[J]. 空天防御, 2021, 4(3): 76-84.
[4]	刘陈续, 于桂兰. 基于神经网络的层状周期结构能量传输谱预测[J]. 上海交通大学学报, 2021, 55(1): 88-95.
[5]	张科, 吴亚东. 拓宽大涵道比风扇稳定运行范围的叶片优化设计[J]. 上海交通大学学报, 2020, 54(10): 1024-1034.
[6]	杨森，何卫平，王月，郭改放. 金属零件微小数据矩阵码快速精定位[J]. 上海交通大学学报（自然版）, 2018, 52(7): 816-824.
[7]	王刚成，马宁，顾解忡. 基于Kriging代理模型的船舶水动力性能多目标快速协同优化[J]. 上海交通大学学报（自然版）, 2018, 52(6): 666-673.
[8]	宋学伟，马玲玲，黄天仑，刘敏. T形管液压成形自适应径向基函数优化设计[J]. 上海交通大学学报（自然版）, 2017, 51(11): 1340-1347.
[9]	聂冰a，赵慧敏a，丁鸣艳b，李文a. 组态式牵引电动机故障诊断模型[J]. 上海交通大学学报（自然版）, 2015, 49(03): 402-405.
[10]	黄铭1，刘俊2. 降雨影响下高边坡渗压神经网络监测模型[J]. 上海交通大学学报（自然版）, 2013, 47(10): 1548-1551.
[11]	黄铭1, 刘俊2. 海堤渗压多测点径向基函数监测模型的建立[J]. 上海交通大学学报（自然版）, 2012, 46(10): 1675-1679.
[12]	凌小峰, 宫新保, 金荣洪. 基于免疫机制的径向基函数网络动态训练方法[J]. 上海交通大学学报（自然版）, 2012, 46(04): 642-645.
[13]	王志强, 邵之江, 万娇娜, 方学毅. 基于径向基函数的动态优化问题联立求解方法[J]. 上海交通大学学报（自然版）, 2011, 45(08): 1221-1225.
[14]	黄铭1, 刘俊2. 堆载预压作用下路基沉降的多测点监测模型[J]. 上海交通大学学报（自然版）, 2011, 45(05): 753-756.
[15]	陈巍，周雄辉，张汝珍，韩先洪，王会凤. 基于Kriging代理模型的注塑产品翘曲优化[J]. 上海交通大学学报（自然版）, 2010, 44(04): 588-0592.