﻿ 基于BP神经网络的海上发射船耐波性优化研究
 舰船科学技术  2023, Vol. 45 Issue (24): 47-51    DOI: 10.3404/j.issn.1672-7649.2023.24.008 PDF

1. 烟台哈尔滨工程大学研究院，山东 烟台 264000;
2. 中集海洋工程研究院有限公司，山东 烟台 264670

Research on seakeeping optimization of marine launcher based on BP neural network
WANG Bao-lai1, YANG Xiao-jie1, LIU Da-hui2
1. Yantai Research Institute of Harbin Engineering University, Yantai 264000, China;
2. CIMC Offshore Engineering Research Institute, Yantai 264670, China
Abstract: In order to ensure the safety of sea launch, BP neural network is used to optimize the launch ship. Carry out general layout design according to the requirements of equipment layout for offshore launch. The bending moment model of the rigid connection end of the rocket launcher is established. Taking the square coefficient, the length and the width of the ship as the optimization variables, the parent ship is optimized through the BP neural network model. The bending moment of the optimized ship is 19.41% less than that of the parent ship. The accuracy of the model is verified by re modeling and numerical simulation of some sample points. The results show that the error of the BP neural network model is less than 1%. This study provides a research idea for the design optimization of offshore launch ship, and a prediction method for risk of offshore rocket launch.
Key words: BP neural network model     full factor experiment     rocket bending moment     launch ship optimization
0 引　言

1 母型船参数

2 发射船总布置设计

3 优化模型的建立

 图 1 火箭模型图 Fig. 1 Rocket model

 $S = {{\theta z\sin\lambda t}} ，$ (1)
 $a = \ddot S = {{\theta z}}{{\lambda}^{\text{2}}}\sin{\lambda{t}},$ (2)
 $f(x,t) = m(z)a = m(z)\ddot S = m(z){{\theta z}}{{\lambda}^{\text{2}}}\sin {{\lambda t}} 。$ (3)

 图 2 火箭微元受力分析图 Fig. 2 Force analysis diagram of micro element of rocket

 $N + \dot Ndz - N + m\ddot y{\rm{d}}z - F{\rm{d}}z + c\dot y = 0 ，$ (4)

 $\dot N{\rm{d}}z + m\ddot y{\rm{d}}z - F{\rm{d}}z + c\dot y = 0 。$ (5)

 $\varepsilon = {{y}}\cdot \ddot{y} ，$ (6)
 ${\sigma} = {{E }\varepsilon } + {{{c}}_{{s}}}{\dot \varepsilon } 。$ (7)

 $M = \int\limits_A \sigma y{\rm{d}}A ，$ (8)

 $\begin{split} {{M}}{{{y}}_{\theta}} = {{\lambda}^{\text{2}}}{\theta\text{sin}\lambda t}\int_{\text{0}}^{{L}} {m(z)} \cdot {z^2}{\rm{d}}z + \frac{{\eta}}{{{{{m}}_{\eta}}}} \cdot \\ \int_0^L {f(z) \cdot m(z){\rm{d}}z\int_0^L {f(z)} } \cdot {z^2} \cdot m(z){\rm{d}}z，\end{split}$ (9)
 $M{y_L} = (g + \ddot z)\sin {\alpha}\int_{\text{0}}^{{L}} {{\text{m(z)}} \cdot {{{z}}^{\text{2}}}} {\rm{d}}z ，$ (10)
 $M = M{y_{\text{θ }}} + M{y_L}，$ (11)
 $\sin {\alpha} = \frac{{{{\theta}_{}}\int_0^L {f(z) \cdot z \cdot m(z){\rm{d}}z} }}{{{L}}} \cdot \frac{{\eta}}{{{{{m}}_{\eta}}}}，$ (12)
 ${\eta} = \frac{{{{{{(}}\frac{{\lambda}}{{{p}}}{\text{)}}}^{\text{2}}}}}{{\sqrt {{{{\text{(1 - }}\frac{{{{\lambda}^{\text{2}}}}}{{{{{p}}^{\text{2}}}}}{\text{)}}}^{\text{2}}} + 4{\varphi }\frac{{\lambda}}{{{p}}}{{\text{)}}^{\text{2}}}} }}，$ (13)
 ${m_{\eta}} = \int_0^L {{f^2}(z)} \cdot m(z){\rm{d}}z。$ (14)

 $M = 2278322.838 \cdot {\theta_{}} + 103495.6558 \cdot {\theta_{}} \cdot \ddot z 。$ (15)

4 优化变量的选取

5 模型优化的实现

 图 3 BP神经网络原理 Fig. 3 Schematic diagram of BP neural network

 图 4 BP神经网络算法流程图 Fig. 4 Flow chart of BP neural network algorithm

 图 5 BP神经网络部分搜索预测结果 Fig. 5 Partial search and prediction results of BP neural network

6 结　语

1）最后优化得到的船型弯矩比母型船减少了19.41%，验证了该模型在火箭发射船设计优化方面的适用性。

2）BP神经网络预测值与实际计算结果的误差不到1%，为海上火箭发射是否存在风险提供了一种预知方法。

3）从优化结果来看，为了提高海上火箭发射的安全性，采用较大的长宽比和方形系数。

 [1] 徐菁. 1996-2005年全球运载火箭发射概况[J]. 国际太空, 2006: 1−3 [2] 张健壮. 2007世界航天运载业分析[J]. 中国航天, 2008: 22−27 [3] 范永辉, 许焕武. 2009年各国航天发射回顾[J]. 中国航天, 2010: 33−37 [4] 徐映霞. 2014世界航天器发射统计[J]. 国际太空, 2015: 5−18 [5] LAWRENCE J. Optimization of marine vessels on the basis of tests on model series[J]. Journal of Marine Science and Technology, 2020: 887–900. [6] MIAO Aiqin. WAN Decheng. Hull form optimization based on an NM+CFD integrated method for KCSm[J]. International Journal of Computational Method, 2020, 17(10): 2050008. [7] WANG S M. DUAN W Y. Study on fast interference wave resistance optimization method for trimaran outrigger layout. Ocean EngineeringVolume, 2021(232): 109104. [8] 刘畅, 朱仁庆, 杨松林. 船舶耐波性模糊优化方法研究[J]. 华东船舶工业学院学报, 2002, 16(2): 12−17 [9] 钱建魁. 基于水动力性能的船型多学科优化设计[D]. 武汉: 武汉理工大学, 2011. [10] 王许洁. 高耐波性单体复合船型构型及水动力性能研究[D]. 哈尔滨: 哈尔滨工程大学, 2012. [11] 冯佰威. 基于多学科设计优化的船舶水动力综合优化研宄[D]. 武汉: 武汉理工大学: 2011 [12] THIAGAJAN KP. Infulence of Blige keel Width on roll Damping of FPSO[J]. Journal of offshore Mechanics & Arctic Engineering, 2010: 397-408 [13] SCAMARDELLA P. Experimental investigation of viscous ROll damping on DTMB model 5671 hull form[C]//ASME 2007, International Conference on Offshore Mechanics and Arctic Engeering: 2007: 221-570. [14] VERNENGO. Resistance and seakeeping optimization of a fast multihull passenger ferry[J]. International Journal of Offshore and Polar Engineering, 2015(1): 26-34. [15] 刘波, 林焰, 吕镇旺, 等. 基于量子行为遗传算法的船体局部结构优化[J]. 船舶力学, 2017, 21(4): 484−492. [16] 周凤杰. 船舶避碰的粒子群-遗传算法混合优化研究[J]. 船舶力学, 2021, 25(7): 909−916. [17] 吴贝尼, 夏丽娟. 基于遗传算法的双向渐进结构优化方法研究[J]. 船舶力学, 2021, 25(2): 193−210. [18] 殷金龙. 海上火箭发射平台的设计与仿真研究[D]. 哈尔滨: 哈尔滨工程大学, 2016. [19] 白乐巍. 基于近似模型的火箭发射船耐波性优化[J]. 船舶工程, 2017.