期刊文献+

参数概率灵敏度分析的神经网络方法及其应用 被引量:7

Neural network method in parametric probabilistic sensitivity analysis and its application
下载PDF
导出
摘要 参数概率灵敏度分析是可靠性设计中非常重要的一项工作,它可以提供基本变量分布参数的变化引起可靠性的变化信息,为判断系统参数的重要性提供依据。本文将商用有限元计算-神经网络方法-Monte Carlo法相结合,基于这种快速响应模型的复杂结构可靠性分析方法,针对结构随机参数的概率灵敏度分析,提出一个考虑随机变量全局分散性的新的度量参数,作为一种工程实用的快速近似方法,相对于传统的确定性及局部灵敏度具有更清晰的意义和指导作用,通过一个算例实现了该法在工程上的应用,并利用ANSYS的概率分析模块验证了该法的有效性。 The analysis of parametric probabilistic sensitivity analysis is important for reliability-based design, which shows changes of system reliability caused by the change of basic variances. In this paper, the commerical FE simulation-neural network-Monte Carlo methods were used together, based on the quick-response model, the parametric probabilistic sensitivity was analyzed too, and a new scaling parameter was presented here considering the global disperisty of stochastic parameters. The sensitivity indices can be computed by the simple and approximate formula in engineering. A numerical example is presented to verify the feasibility and the effectivity by comparing with the analysis of ANSYS.
出处 《计算力学学报》 EI CAS CSCD 北大核心 2011年第B04期29-32,共4页 Chinese Journal of Computational Mechanics
基金 国家基础研究计划(2010CB832700) NSAF基金(10876100) 中物院科学技术发展基金(2010B203025)资助项目
关键词 神经网络 MONTE Carlo 快速响应模型 概率灵敏度 neural network monte Carlo quick-response model probabilistic sensitivity
  • 相关文献

参考文献9

二级参考文献26

  • 1吕爱钟.巷道围岩参数及地应力可辨识性的探讨[J].岩石力学与工程学报,1988,7(2):155-164.
  • 2Hect-Nielsen R. Theory of the back-propagation, neural network [A]. Pro of the Int Joint Conf on Neural Network, Ⅰ IEEE press [C], New YORK, 1989, 593-611.
  • 3Ledesma A, GENS A. Parameter and variance estimation in geo-technical back analysis using prior information [ J ]. Int Jour for Numer and Analy Methods in Geomech. 1996, 20:119 - 141.
  • 4任青文.非线性有限单元法[M].南京:河海大学出版社,1999.12-23.
  • 5尹泽勇(译),有限元法,1985年,748页
  • 6Saltelli A, et al. Sensitivity Analysis[M]. Chichester: Wiley, 2000.
  • 7Haftka R T, Adelman H M. Recent developments in structural sensitivity analysis [J]. Structural Optimization, 1989,1 (2): 137-152.
  • 8Tong M, et al. Numerical modelling for temperature distribution in steel bridges [J]. Computers &Structures, 2001,79(6): 583-593.
  • 9Brownjohn J M W, Xia P Q. Dynamic assessmentof curved cable-stayed bridge by model updating[J].Journal of Structural Engineering, ASCE , 2000,126(2):252-260.
  • 10Hornik K, et al. Multilayer feedforward networks are universal approximators [J]. Neural Networks,1989,2(5) :359-366.

共引文献69

同被引文献44

引证文献7

二级引证文献12

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部