基于RBF神经网络模型的结构可靠度优化方法

李刚; 孟增

doi:10.3879/j.issn.1000-0887.2014.11.010

基于RBF神经网络模型的结构可靠度优化方法

doi: 10.3879/j.issn.1000-0887.2014.11.010

李刚,
孟增

大连理工大学工程力学系; 工业装备结构分析国家重点实验室(大连理工大学),辽宁大连 116024

基金项目: 国家自然科学基金(11372061; 91315301)

详细信息

作者简介:
李刚(1966—)，男，太原人，教授，博士，博士生导师(通讯作者. E-mail: ligang@dlut.edu.cn);孟增(1987—)，男，甘肃陇南人，博士生(E-mail: mengz@mail.dlut.edu.cn).

中图分类号: TB114.3;O213.2
计量
- 文章访问数: 1015
- HTML全文浏览量: 88
- PDF下载量: 933
- 被引次数: 0
出版历程
- 收稿日期: 2014-05-15
- 刊出日期: 2014-11-18

Reliability-Based Design Optimization With the RBF Neural Network Model

LI Gang,
MENG Zeng

State Key Laboratory of Structural Analysis for Industrial Equipment(Dalian University of Technology); Department of Engineering Mechanics, Dalian University of Technology, Dalian, Liaoning 116024, P.R.China

Funds: The National Natural Science Foundation of China(11372061; 91315301)

摘要

摘要: 在结构构件尺寸、材料属性以及外部载荷等不确定性因素影响下，基于可靠度的优化给出了兼顾结构的成本和安全性能的安全设计方案.由于传统的可靠度优化方法采用嵌套的双层优化列式求解，因此导致计算量过大.为了克服这个问题，学者们相继提出了解耦方法和单循环方法等方法.该文采用RBF神经网络模型用于可靠度优化问题的求解中，通过拉丁超立方方法构造代理模型，并用误差指标来验证代理模型的精确程度，同时自适应更新代理模型直至满足需求.通过与现有可靠度优化4种主流算法的比较，说明了该文提出算法的高效性和稳健性.
- 可靠度 /
- 优化 /
- RBF神经网络 /
- 效率 /
- 稳健性
Abstract: The reliability-based design optimization (RBDO) provides a trade-off between cost and safety given a lot of uncertain factors, such as structure sizes, material properties and external loads. The traditional RBDO approaches were computationally expensive owing to the nesting bilevel optimization. Thereafter, the decoupling approach and single loop approach were proposed to overcome this obstruction. However，the computational demand of these 2 types of approaches was still too huge for complex engineering problems. Here a new adaptive RBDO approach was presented based on the RBF neural network theory. The latin hypercube sampling method was used to construct the surrogate model. The error metrics were used to validate the RBF neural network model and the surrogate model was updated adaptively. Compared with the previous 4 popular RBDO algorithms, the presented method is efficient and robust.
- reliability /
- optimization /
- RBF neural network /
- efficiency /
- robustness

HTML全文

参考文献(15)

[1]	Nikolaidis E, Burdisso R. Reliability-based optimization: a safety index approach[J].Computers & Structures,1988,28(6): 781-788.
[2]	Tu J, Choi K K, Park Y H. A new study on reliability-based design optimization[J]. Journal of Mechanical Design,1999,121(4): 557-564.
[3]	Liang J, Mourelatos Z P, Tu J. A single-loop method for reliability-based design optimisation[J]. International Journal of Product Development,2008,5(1): 76-92.
[4]	Madsen H O, Hansen P F. A comparison of some algorithms for reliability based structural optimization and sensitivity analysis[C]// Proceedings of the 4th IFIPWG 75 Conference.Munich, Germany, 1991.
[5]	CHEN Xiao-guang, Hasselman T K, Neill D J. Reliability based structural design optimization for practical applications[C]// Proceedings of the 38th AIAA/ASME/ASCE /AHS/ASC Structures, Structural Dynamics, and Materials Conference.Kissimmee, FL, 1997.
[6]	程耿东, 许林. 基于可靠度的结构优化的序列近似规划算法[J]. 计算力学学报, 2006,23(6): 641-646.(CHENG Geng-dong, XU Lin. Sequential approximate programming approach to reliability based structural optimization[J]. Chinese Journal of Computational Mechanics,2006,23(6): 641-646. (in Chinese))
[7]	Yi P, Cheng G, Jiang L. A sequential approximate programming strategy for performance-measure-based probabilistic structural design optimization[J]. Structural Safety,2008,30(2): 91-109.
[8]	Du X, Chen W. Sequential optimization and reliability assessment method for efficient probabilistic design[J]. Journal of Mechanical Design,2004,126(2): 225-233.
[9]	许林, 程耿东, 易平. 利用系统可靠度约束下的优化设计求解公差分配问题[J]. 机械强度, 2007,28(6): 839-844.(XU Lin, CHENG Geng-dong, YI Ping. Tolerance assignment using algorithm for system reliability based optimal design[J]. Journal of Mechanical Strength,2007,28(6): 839-844.(in Chinese))
[10]	Youn B D, Choi K K, Yang R J, Gu L. Reliability-based design optimization for crashworthiness of vehicle side impact[J]. Structural and Multidisciplinary Optimization,2004,26(3/4): 272-283.
[11]	Xu K, Xie M, Tang L C, Ho S T. Application of neural networks in forecasting engine systems reliability[J]. Applied Soft Computing,2003,2(4): 255-268.
[12]	Wu Y T, Millwater H R, Cruse T A. Advanced probabilistic structural analysis method for implicit performance functions[J]. AIAA Journal,1990,28(9): 1663-1669.
[13]	Youn B D, Choi K K, Park Y H. Hybrid analysis method for reliability-based design optimization[J]. Journal of Mechanical Design,2003,125(2): 221-232.
[14]	Li G, Meng Z. A modified chaos control approach of the performance measure functions for reliability-based design optimization[C]//10th World Congress on Structural and Multidisciplinary Optimization.Orlando, Florida, USA, 2013.
[15]	Venter G, Haftka R T, Chirehdast M. Response surface approximations for fatigue life prediction[C]//Proceedings of the 38th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Material Conference and AIAA/ASM/AHS Adaptive Structures Forum.Kissimmee, FL, 1997.