Optimal design of internal pressure resistant square cabin based on strength analysis
-
摘要:
目的 为了使船用耐内压方形舱同时满足强度和轻量化的设计要求,将神经网络代理模型与多种启发式智能优化算法相结合,对耐内压方形舱室结构构件形状和尺寸进行优化分析。 方法 选取方形舱室角隅倒角半径、板材板厚、骨材型号等作为设计变量进行三维参数化建模,根据最优拉丁超立方试验设计方法选取样本点并计算响应值,从而构建径向基(RBF)神经网络代理模型。将该代理模型分别与自适应模拟退火算法 (ASA)、多岛遗传算法 (MIGA)和粒子群算法 (PSO)这3种启发式优化算法相结合,进行全局寻优。 结果 结果显示,3种混合优化方法均能在满足许用强度要求的基础上减轻结构重量;RBF-ASA法在全局中寻求到的最优解具有相对较好的减重效果。 结论 所做研究可为耐内压方形舱室结构优化设计工作提供参考,对于攻克船舶运用核动力装置所面临的关键技术问题具有重要意义。 Abstract:Objectives In order to design a marine internal pressure resistant square cabin which meets the requirements for strength and lightweight design, the neural network surrogate model is combined with heuristic intelligent optimization algorithms and applied to the shape and size optimization of the components of such a cabin. Methods The corner chamfer radius, plate thickness and beam model number are selected as design variables for conducting three-dimensional parametric modeling, and sample points are selected according to the optimal Latin hypercube experimental design method. The response values of these sample points are then calculated to build a radial basis functions (RBF) neural network surrogate model. To perform global optimization, the surrogate model is combined with three heuristic optimization algorithms respectively: an adaptive simulated annealing algorithm (ASA), multi-island genetic algorithm (MIGA) and particle swarm optimization (PSO) algorithm. Results The results show that the three hybrid optimization methods can all reduce structural weight on the basis of meeting the allowable strength requirements, and the optimal solution sought by the RBF-ASA method in the overall situation has a relatively good weight reduction effect. Conclusions This study can provide valuable references for the optimal design of internal pressure-resistant square cabin structures, giving it great significance for overcoming the key technical problems faced by ships using nuclear power plants. -
表 1 钢材性能参数
Table 1. Parameters of steel performance
性能参数 921A钢 DH40钢 ${R_{\rm{m}}}$/(N·mm−2) 655 510 ${R_{{\rm{eH}}}}$/(N·mm−2) 590 390 $\left(\dfrac{R_{\rm{m}}}{2.7}\right)$/(N·mm−2) 243 189 $\left(\dfrac {R_{{\rm{eH}}}}{1.5}\right)$/(N·mm−2) 393 260 弹性模量E/(N·mm−2) 2.1×105 2.1×105 密度/(kg·m−3) 7 850 7 850 许用应力/MPa 243 189 折减后的弹性模量/(N·mm−2) 1.4×105 1.4×105 表 2 构件初始设计值
Table 2. Initial design value of components
构件属性名称 初始设计值/mm 构件属性名称 初始设计值/mm 内壳角隅倒角半径r 600 内壳底部骨材g1 $ \bot \dfrac{{16 \times 200}}{{20 \times 100}}$ 内壳板-1(角隅)板厚t1 32 内壳舷侧骨材g2 $ \bot \dfrac{{16 \times 200}}{{20 \times 100}}$ 内壳板-2(底部)板厚t2 32 内壳顶部骨材g3 $ \bot \dfrac{{16 \times 200}}{{20 \times 100}}$ 内壳板-3板厚t3 32 内壳横舱壁骨材g4 $ \bot \dfrac{{16 \times 200}}{{20 \times 100}}$ 外壳板-1(角隅)板厚t4 28 外壳底部骨材g5 ${\rm{HP220}} \times {\rm{11}}$ 外壳板-2(底部)板厚t5 24 外壳舷侧骨材g6 $ \bot \dfrac{{16 \times 200}}{{20 \times 100}}$ 外壳板-3板厚t6 20 外壳顶部骨材g7 $ \bot \dfrac{{16 \times 200}}{{20 \times 100}}$ 角隅隔板板厚t7 26 外壳横舱壁骨材g8 $ \bot \dfrac{{16 \times 200}}{{20 \times 100}}$ 水平隔板板厚t8 24 底部加强筋g9 $16 \times 180$ 纵向隔板-1(底部)板厚t9 18 舷侧加强筋g10 $16 \times 180$ 纵向隔板-2板厚t10 20 顶部加强筋g11 $16 \times 180$ 横向隔板-1(底部)板厚t11 24 横舱壁水平加强筋g12 $16 \times 180$ 横向隔板-2板厚t12 22 横舱壁垂向加强筋g13 $16 \times 180$ 肘板板厚t13 20 表 3 目标函数的R-squared值
Table 3. R-squared values of objective function
目标函数 R-squared值 ${\sigma _1}$/MPa 0.959 33 ${\sigma _2}$/MPa 0.928 55 M/t 0.998 88 表 4 全局优化后结构的响应结果
Table 4. Response results of structure after global optimization
目标函数 许用值 初始值 ASA
优化值MIGA
优化值PSO
优化值σ1/MPa 243 237.279 242.130 242.243 235.611 σ2/MPa 189 178.761 187.103 185.818 180.756 M/t − 1 569.780 1 355.172 1 445.334 1 422.096 模型减重
百分比/%− − 13.67 7.93 9.41 -
[1] 刘洁雪. 基于响应面法的集装箱船优化设计研究[D]. 天津: 天津大学, 2008.LIU J X. Research on optimum design of a container ship based on response surface methodology[D]. Tianjin: Tianjin University, 2008 (in Chinese). [2] 程远胜, 孙莹, 闫国强, 等. 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, 49(4): 81–87. doi: 10.3969/j.issn.1000-4882.2008.04.011CHENG Y S, SUN Y, YAN G Q, et al. Structural optimization of a submarine end plane transverse bulkhead based on neural networks and genetic algorithm[J]. Shipbuilding of China, 2008, 49(4): 81–87 (in Chinese). doi: 10.3969/j.issn.1000-4882.2008.04.011 [3] 卓思雨. 油船结构轻量化设计及其安全性研究[D]. 上海: 上海交通大学, 2019.ZHUO S Y. Research on structure lightweight design and safety assessment of oil tanker[D]. Shanghai: Shanghai Jiao Tong University, 2019 (in Chinese). [4] 高上地, 陈静, 卢骏锋, 等. 内压下矩形耐压舱角隅结构形状和拓扑优化设计[J]. 中国造船, 2017, 58(1): 94–100. doi: 10.3969/j.issn.1000-4882.2017.01.011GAO S D, CHEN J, LU J F, et al. Shape and topology optimization design of rectangular tank's corner structure under internal pressure[J]. Shipbuilding of China, 2017, 58(1): 94–100 (in Chinese). doi: 10.3969/j.issn.1000-4882.2017.01.011 [5] 陈杨科, 余恩恩, 骆伟, 等. 内压下矩形耐压舱内部结构优化设计[J]. 中国舰船研究, 2017, 12(6): 81–85. doi: 10.3969/j.issn.1673-3185.2017.06.012CHEN Y K, YU E E, LUO W, et al. Optimal design of internal structure of rectangular cabin under internal pressure[J]. Chinese Journal of Ship Research, 2017, 12(6): 81–85 (in Chinese). doi: 10.3969/j.issn.1673-3185.2017.06.012 [6] 陈静, 余恩恩, 卢骏锋, 等. 矩形耐压舱预应力支柱优化设计[J]. 中国舰船研究, 2019, 14(1): 102–106. doi: 10.19693/j.issn.1673-3185.01089CHEN J, YU E E, LU J F, et al. Optimal design of prestressed pillars for rectangular pressure cabin[J]. Chinese Journal of Ship Research, 2019, 14(1): 102–106 (in Chinese). doi: 10.19693/j.issn.1673-3185.01089 [7] American Institute of Steel Construction. Specification for structural steel buildings: ANSI/AISC 360-05[S]. Chicago: American Institute of Steel Construction, Inc., 2005. [8] 中国船级社. 潜水系统和潜水器入级规范[S]. 北京: 中国船级社, 2018.China Classification Society. Classification specification for diving systems and diving systems[S]. Beijing: China Classification Society, 2018 (in Chinese). [9] 吴振君, 王水林, 葛修润. LHS方法在边坡可靠度分析中的应用[J]. 岩土力学, 2010, 31(4): 1047–1054. doi: 10.3969/j.issn.1000-7598.2010.04.007WU Z J, WANG S L, GE X R. Application of Latin hypercube sampling technique to slope reliability analysis[J]. Rock and Soil Mechanics, 2010, 31(4): 1047–1054 (in Chinese). doi: 10.3969/j.issn.1000-7598.2010.04.007 [10] 刘加利. 高速列车气动噪声特性分析与降噪研究[D]. 成都: 西南交通大学, 2013.LIU J L. Study on characteristics analysis and control of aeroacoustics of high-speed trains[D]. Chengdu: Southwest Jiaotong University, 2013 (in Chinese). [11] MOODY J, DARKEN C J. Fast learning in networks of locally-tuned processing units[J]. Neural Computation, 1989, 1(2): 281–294. doi: 10.1162/neco.1989.1.2.281 [12] 郑少平, 陈静, 程远胜, 等. 代理模型技术及其在船舶板架强度和稳定性计算中的应用[J]. 中国造船, 2013, 54(1): 40–51. doi: 10.3969/j.issn.1000-4882.2013.01.007ZHENG S P, CHEN J, CHENG Y S, et al. Surrogate models and their application in calculation of strength and stability of ship grillage[J]. Shipbuilding of China, 2013, 54(1): 40–51 (in Chinese). doi: 10.3969/j.issn.1000-4882.2013.01.007 [13] INGBER L. Adaptive simulated annealing (ASA): lessons learned[J]. Control and Cybernetics, 1996, 25: 33–54. [14] KENNEDY J, EBERHART R. Particle swarm optimization[C]//Proceedings of ICNN'95-International Conference on Neural Networks. Perth: IEEE, 1995. [15] 秦健健, 毛虎平. 基于多岛遗传算法的柴油机连杆结构优化设计[J]. 机械设计与制造, 2017(4): 218–221. doi: 10.3969/j.issn.1001-3997.2017.04.056QIN J J, MAO H P. Diesel engine connecting rod structure optimization design based on MIGA algorithm[J]. Machinery Design & Manufacture, 2017(4): 218–221 (in Chinese). doi: 10.3969/j.issn.1001-3997.2017.04.056 -
ZG2115_en.pdf
-