﻿ 基于 PSO-BP 神经网络的油船中部结构优化
 舰船科学技术  2017, Vol. 39 Issue (1): 41-44 PDF

Oil tank mid-ship structure optimization based on PSO-BP neural network
ZHEN Chun-bo, ZHANG Ai-feng, SHI Ya-peng
College of Traffic Equipment and Ocean Engineering, Dalian Maritime University, Dalian 116026, China
Abstract: The design variables are determined by sensitivity analysis. Then the optimum design of large oil tanker mid structure is carried out by taking hold section structure weight as the objective function, and taking rule's requirements of the plate thickness and stress as the constraint conditions. The BP neural network model based on particle swarm optimization is built, which is used to determine the relationship between stress and design variables in place of finite element analysis. The optimized structure weight decreased by 4.2%. The finite element analysis results show that the optimized structure is satisfied with the requirements of the rule.The PSO-BP neural network model is feasible in the optimization design of the ship structure.
Key words: oil tank     structure optimization     PSO-BP neural network
0 引言

1 优化方案 1.1 设计变量选取

1.2 约束条件

 ${\sigma _{\max }} \leqslant \left[ \sigma \right],$ (1)
 ${\tau _{\max }} \leqslant \left[ \tau \right]。$ (2)

σmaxτmax 通过调用 PSO-BP 神经网络拟合的剪应力板厚函数关系来确定。

1.3 目标函数

 $F\left( X \right) = \sum\limits_{i = 1}^n {{\rho _i}{V_i}} = \sum\limits_{i = 1}^n {{\rho _i}{S_i}{t_i}} 。$ (3)

2 有限元分析

 图 1 应力云图 Fig. 1 Stress nephogram
3 灵敏度分析

 图 2 灵敏度分析结果 Fig. 2 Results of sensitivity analysis

4 PSO-BP 神经网络构建

4.1 结构设计

4.2 训练结果

 图 3 测试误差 Fig. 3 Test error

4.3 泛化能力检测

 图 4 PSO-BP 测试样本误差 Fig. 4 PSO-BP test sample error

5 优化结果及分析

 图 5 舱段应力云图 Fig. 5 Cabin stress nephogram

6 结语

 [1] ﻿俞铭华, 嵇春艳, 管义锋. 大型油船结构优化设计研究进展[J]. 江苏科技大学学报(自然科学版) , 2006 (2):1–6. YU Ming-hua, JI Chun-yan, GUAN Yi-feng. Advances in Structural Optimum Design of Large Crude Oil Carriers[J]. Journal of Jiangsu University of Science and Technology(Natural Science Edition) , 2006 (2) :1–6. [2] 李仲伟, 吴有生, 崔维成. 基于有限元法的小水线面双体船结构优化[J]. 船舶力学, 2005(2): 99-108. [3] 张丽. 巴拿马型集装箱船结构优化设计研究[D]. 上海: 上海交通大学, 2008. [4] 潘彬彬, 崔维成. 基于有限元的整船结构多学科设计优化[J]. 中国造船 , 2010, 01 :47–54. PAN Bin-bin, CUI Wei-cheng. FEM Based MDO Model for Entire Ship Structural Optimization[J]. FEM based MDO model for entire ship structural optimization , 2010, 01 :47–54. [5] KARR D G., BEIER K P, LEE K D. A framework for simulation-based design of ship structures[J]. Journal of Ship Production , 2002, 18 (1) :33–46. [6] ZANIC V, JANCIJEV T, TRINCAS G. Structural design methodology for large ships[J]. Journal of Ship and Ocean Technology , 2001, 5 (1) :14–29. [7] 程远胜, 孙莹, 闫国强. 基于神经网络与遗传算法的潜艇舱壁结构优化[J]. 中国造船 , 2008, 04 :81–87. CHENG Yuan-sheng, SUN Ying, YAN Guo-qiang. Structural Optimization of a Submarine End Plane Transverse Bulkhead Based on Neural Networks and Genetic Algorithm[J]. Structural optimization of a submarine end plane transverse bulkhead based on neural networks and genetic algorithm , 2008, 04 :81–87. [8] UN L, WANG D Y. Optimal structural design of the midship of a VLCC based on the strategy integrating SVM and GA[J]. Optimal structural design of the midship of a VLCC based on the strategy integrating SVM and GA , 2012 (11) :59–67. [9] 邓良. 基于人工神经网络的船舶结构轻量化研究[D]. 济南: 济南大学, 2014. [10] 中国船级社. 钢制海船入级规范[S]. 北京: 人民交通出版社, 2012.