[1]胡启国,李致明.采用MEA-AdaBoost-BP模型的工程结构可靠性分析方法[J].华侨大学学报(自然科学版),2022,43(3):291-296.[doi:10.11830/ISSN.1000-5013.202103025]
　HU Qiguo,LI Zhiming.Reliability Analysis Method of Engineering Structure Based on MEA-AdaBoost-BP Model[J].Journal of Huaqiao University(Natural Science),2022,43(3):291-296.[doi:10.11830/ISSN.1000-5013.202103025]
点击复制

采用MEA-AdaBoost-BP模型的工程结构可靠性分析方法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第43卷
期数:
2022年第3期
页码:
291-296
栏目:
出版日期:
2022-05-10

文章信息/Info

Title:
Reliability Analysis Method of Engineering Structure Based on MEA-AdaBoost-BP Model
文章编号:
1000-5013(2022)03-0291-06
作者:
胡启国;  李致明
重庆交通大学 机电与车辆工程学院, 重庆 400074
Author(s):
HU Qiguo;  LI Zhiming
School of Mechanical and Vehicle Engineering, Chongqing Jiaotong University, Chongqing 400074, China
关键词:
可靠性指标;  思维进化算法(MEA);  AdaBoost-BP神经网络;  MEA-AdaBoost-BP算法;  强预测器函数
Keywords:
reliability index;  mind evolutionary algorithm(MEA);  AdaBoost-BP neural network;  MEA-AdaBoost-BP algorithm;  strong predictor function
分类号:
TB114.3;TP183
DOI:
10.11830/ISSN.1000-5013.202103025
文献标志码:
A
摘要:
针对工程结构可靠性设计中算法和计算存在的问题,提出基于MEA-AdaBoost-BP神经网络算法模型的可靠性求解方法. 运用思维进化算法(MEA)求解训练集权值和阈值优化的BP神经网络,并构造为弱预测器函数.然后,运用AdaBoost算法将多个优化后的BP神经网络弱预测器函数迭代训练,形成MEA-AdaBoost-BP神经网络算法模型强预测器函数. 最后,利用逼近隐性功能函数求解可靠性指标,并将其与AdaBoost-BP算法和Monte-Carlo算法进行比较.研究结果表明:所提算法在计算中与Monte-Carlo算法相比,其迭代次数分别仅为16次和46次,效率高,计算精度与Monte-Carlo法接近;而和AdaBoost-BP法相比,其可靠性指标误差分别仅为1.59%和1.88%,计算结果更精确.
Abstract:
Aiming at the algorithm and calculation in engineering structure reliability design, a reliability solving method was proposed based on MEA-AdaBoost-BP neural network algorithm model. The optimized BP neural network was constructed as a weak predictor function by solving the training set weights and threshold values through the Mind Evolutionary Algorithm(MEA). Then the AdaBoost algorithm was used to iteratively train several optimized BP neural network weak predictor functions to form the strong predictor function of the MEA-AdaBoost-BP neural network algorithm model. Finally, the approximate the implicit function was used to solve the reliability index, which was compared with AdaBoost-BP algorithm and the Monte-Carlo method. The results show that the proposed method is efficient because its number of iterations is only 16 and 46 respectively compared with the Monte-Carlo method and its calculation accuracy is close to that of the Monte-Carlo method; the error of reliability index is only 1.59% and 1.88% respectively compared with that of AdaBoost-BP method,and the calculation result is more accurate.

参考文献/References:

[1] HUANG Xiyong,ALIABADI F M H.A boundary element method for structural reliability[J].Key Engineering Materials,2015,627:453-456.DOI:10.4028/www.scientific.net/KEM.627.453.
[2] LOW B K,PHOON K K.Reliability-based design and its complementary role to Eurocode 7 design approach[J].Computers and Geotechnics,2015,65:30-44.DOI:10.1016/j.compgeo.2014.11.011.
[3] WEN Kai,HE Lei,LIU Jing,et al.An optimization of artificial neural network modeling methodology for the reliability assessment of corroding natural gas pipelines[J].Journal of Loss Prevention in the Process Industries,2019,60:1-8.
[4] GOSWAMI S,GHOSH S,CHAKRABORTY S.Reliability analysis of structures by iterative improved response surface method[J].Structural Safety,2016,60:55-56.DOI:10.1016/j.strusafe.2016.02.002.
[5] DENG J,GU Desheng,LI Xibing,et al.Structural reliability analysis for implicit performance functions using artificial neural network[J].Structural Safety,2005,27(1):25-48.DOI:10.1016/j.strusafe.2004.03.004.
[6] 姜逢源,董胜,张鑫.基于改进神经网络的板桩结构可靠性分析[J].海洋湖沼通报,2018(2):103-109.
[7] WANG Wenxu,TANG Ruichun,LI Cheng.A BP neural network model optimized by mind evolutionary algorithm for predicting the ocean wave heights[J].Ocean Engineering,2018,162:98-107.DOI:10.1016/j.oceaneng.2018.04.039.
[8] ROUSSOULY N,PETITJEAN F,SALAUN M.A new adaptive response surface method for reliability analysis[J].Probabilistic Engineering Mechanics,2013,32:103-115.DOI:10.1016/j.probengmech.2012.10.001.
[9] BLATMAN G,SUDRET B.An adaptive algorithm to build up sparse polynomial chaos expansions for stochastic finite element analysis[J].Probabilistic engineering mechanics,2010,25(2):183-197.DOI:10.1016/j.probengmech.2009.10.003.
[10] 张小庆,康海贵,王复明.求解隐式功能函数可靠度的一种新方法[J].大连理工大学学报,2003,43(5):650-653.DOI:10.3321/j.issn:1000-8608.2003.05.024.
[11] 张明.结构可靠度分析: 方法与程序[M].北京:科学出版社,2009:190-192
[12] NGUYEN H D,SHIN M,TORBOL M.Reliability assessment of a planar steel frame subjected to earthquakes in case of an implicit limit-state function[J].Journal of Building Engineering,2020,32:101782.DOI:10.1016/j.jobe.2020.101782.
[13] 朱晨飞,黄淑华,王怀聪,等.一种改进的BP-AdaBoost算法及应用研究[J].现代电子技术,2019,42(19):64-67,72.DOI:10.16652/j.issn.1004-373x.2019.19.015.
[14] 吴俊利,张步涵,王魁.基于AdaBoost的BP神经网络改进算法在短期风速预测中的应用[J].电网技术,2012,36(9):221-225.DOI:10.13335/j.1000-3673.pst.2012.09.037.
[15] 刘阔,李晓雷,王健.一种基于Kriging模型的机械结构可靠性分析方法[J].东北大学学报(自然科学版),2017,38(7):1002-1006.DOI:10.12068/j.issn.1005-3026.2017.07.019.

备注/Memo

备注/Memo:
收稿日期: 2021-03-19
通信作者: 胡启国(1966-),男,教授,博士,主要从事机械可靠性分析及优化、机械系统动力学的研究.E-mail:swpihqg@163.com.
基金项目: 国家自然科学基金资助项目(51375519); 重庆市基础科学与前沿技术研究专项(cstc2015jcyjBX0133)
更新日期/Last Update: 2022-05-20