首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于神经网络的结构可靠性优化设计
引用本文:张义民,张雷.基于神经网络的结构可靠性优化设计[J].应用力学学报,2005,22(1):49-54.
作者姓名:张义民  张雷
作者单位:吉林大学,长春,130025
基金项目:国家自然科学基金资助项目(项目编号: 50175043)
摘    要:结合随机摄动技术和随机模拟方法,提出了可靠性优化设计的一种数值逼近法,将服从任意分布的可靠性概率约束等价转化为确定型约束,可以迅速准确地获得优化设计结果。针对具有多失效模式的结构可靠性优化设计,提出了随机模拟-神经网络方法,模拟得到随机设计变量与系统可靠度之间的显性函数表达式,简化了计算过程,同时可以获得较高的计算精度,具有很好的工程实用价值。

关 键 词:任意分布参数  可靠性优化设计  数值逼近法  多失效模式  随机模拟神经网络法
文章编号:1000-4939(2005)01-0049-06

Structural Reliability Optimwn Design Based on MCS-NN Method
Zhang Yimin,Zhang Lei.Structural Reliability Optimwn Design Based on MCS-NN Method[J].Chinese Journal of Applied Mechanics,2005,22(1):49-54.
Authors:Zhang Yimin  Zhang Lei
Abstract:Two methods for structural reliability are investigated. Firstly, a numerical approach method is used in the optimal reliability design with arbitrary distribution parameters, where the probabilistic constraints can be transformed into deterministic constraints, and the reliability optimal design parameters are obtained accurately and quickly. Simultaneously, MCS NN method is applied to optimal reliability design with multi failure modes, and then the explicit expression between the design parameters and the system reliability is given rightly. Therefore, the process of optimal reliability design can be implemented expediently.
Keywords:arbitrary distribution parameters  reliability optimal design  numerical approach method  many failure modes  MCS  NN method    
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号