在结构可靠性分析中，蒙特卡罗（MC）是最准确的方法，但是对大量样本点的精确计算限制了它在工程实际中的应用.为了减少分析次数，以BP(Back Propagation)神经网络技术为基础，提出了一种改进的MC方法（BP-MC）.该方法通过进行实验设计（DOE）构建BP模型，以权重因子和到失效面的距离作为筛选准则，从MC样本点中筛选出失效面附近的点添加至训练集，重新训练BP模型直至满足收敛准则.随后以该BP模型识别样本点是否处于失效域，从而计算结构的失效概率.最后,以数学模型和加筋板极限强度可靠性计算为例，验证了BP-MC算法的准确与高效.
Monte Carlo (MC) is a very accurate method in the structure reliability calculation, however, its application is limited due to a large number of computation when it comes to complex engineering structures. It is time-consuming even in a single analysis. To reduce the calculation, the neural network approach is adopted to construct the BP-MC method. The back propagation (BP) neural network is built through design of experiments (DOE), then the weighting factors and the distance to failure surface are used as filters to pick up the design points out of the MC points. Those picked points are prone to cause the structure failure, and transferred into the training set to update the BP model. The filter-update process continues until the convergence of the BP, and then reliability index is calculated with the BP model on the MC points. The efficiency and usability are elucidated with a mathematic model and a stiffened panel model at the end of this paper.
［1］ECHARD B, GAYTON N, LEMAIRE M. AK-MCS: An active learning reliability method combining Kriging and Monte Carlo simulation［J］. Structural Safety, 2011, 33(2): 145-154.
［2］张崎. 基于Kriging方法的结构可靠性分析及优化设计［D］.大连: 大连理工大学, 2005.
ZHANG Qi. Structure reliability analysis and optimization based on Kriging technique［D］. Dalian: Dalian University of Technology, 2005.
［3］RASHKI M, MIRI M, MOGHADDAM M A. A new efficient simulation method to approximate the probability of failure and most probable point［J］. Structural Safety, 2012, 39(4): 22-29.
［4］OKASHA N M . An improved weighted average si-mulation approach for solving reliability-based analysis and design optimization problems ［J］. Structural Safety, 2016, 60: 47-55.
［5］ECHARD B, GAYTON N, LEMAIRE M, et al. A combined Importance Sampling and Kriging reliability method for small failure probabilities with time-demanding numerical models［J］. Reliability Engineering and System Safety, 2012, 111(2): 232-240.
［6］陆强华. 基于径向基函数神经网络的结构可靠性分析［J］. 中国科技信息, 2008(5): 234-235.
LU Qianghua. Structure reliability analysis based on radial basis function neural network［J］. China Science and Technology Information, 2008 (5): 234-235.
［7］康飞, 李俊杰, 李守巨, 等. 边坡系统可靠度分析智能响应面法框架［J］. 武汉大学学报(工学版), 2016, 49(5): 654-660.
KANG Fei, LI Junjie, LI Shouju, et al. Framework of intelligent response surface methods for system reliability analysis of slopes［J］. Engineering Journal of Wuhan University, 2016, 49(5): 654-660.
［8］徐元铭, 陈丽华, 彭兴林. 进化神经网络响应面法在结构可靠性中应用［J］. 飞机设计, 2008, 28(5): 33-38.
XU Yuanmin, CHEN Lihua, PENG Xinglin. Evolutionary neural network response surface for structural reliability analysis ［J］. Aircraft Design, 2008, 28(5): 33-38.
［9］胡新明,王德禹. 基于迭代均值组合近似模型和序贯优化与可靠性评估法的船舶结构优化设计［J］.上海交通大学学报, 2017, 51(2): 150-156.
HU Xinming, WANG Deyu. Optimization of ship structures using ensemble of surrogate with recursive arithmetic average and sequential optimization and reliability assessment［J］. Journal of Shanghai Jiao Tong University, 2017, 51(2): 150-156.
［10］周明光.基于径向基函数的结构可靠性分析算法研究［D］.长沙: 湖南大学, 2013.
ZHOU Mingguang. Research on structural reliability analysis based on radial basis function［D］. Changsha: Hunan University, 2013.
［11］DNV. Structural reliability analysis of marine structures. Classification notes no. 30.6, Det Norske Veritas Classification, AS, Hovik［M］. Norway: DNV, 1992.
［12］常海超, 冯佰威, 刘祖源, 等. 船型优化中样本点选取方法对近似模型精度的影响研究［J］. 中国造船, 2013, 54(4): 84-93.
CHANG Haichao, FENG Baiwei, LIU Zuyuan, et al. Influence of sample points’ selection methods on the accuracy of approximation model in hull form optimization［J］. Shipbuilding of China, 2013, 54(4): 84-93.
［13］杨卓懿. 无人潜器总体方案设计的多学科优化方法研究［D］.哈尔滨: 哈尔滨工程大学, 2012.
YANG Zhuoyi. A study on multidisciplinary design optimization method for scheme design of autonomous underwater vehicle［D］. Harbin: Harbin Engineering University, 2012.
［14］SHU Z, MOAN T. Reliability analysis of a bulk carrier in ultimate limit state under combined global and local loads in the hogging and alternate hold loading condition［J］. Marine Structures, 2011, 24(1): 1-22.
［15］GASPAR B, NAESS A, LEIRA B J, et al. System reliability analysis of a stiffened panel under combined uniaxial compression and lateral pressure loads［J］. Structural Safety, 2012, 39: 30-43.
