+高级检索
基于遗传算法与神经网络的钢桁架可靠度计算
DOI:
作者:
作者单位:

湖南大学土木工程学院

作者简介:

通讯作者:

基金项目:

湖南省交通厅科技项目(201525)


Reliability Calculation of Steel Truss Based on GA and Neural Network
Author:
Affiliation:

1.College of Civil Engineering,Hunan University,Changsha;2.College of Civil Engineering, Hunan University

Fund Project:

Science and Technology Program of Hunan Province (201525)

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
    摘要:

    提出了适用于钢桁架这一类具有复杂隐式功能函数结构的可靠度计算方法。该方法先采用神经网络逼近隐式功能函数,然后基于可靠度指标的几何意义,运用新改进的遗传算法搜索钢桁架可靠度指标最优解及验算点。最后通过两个算例分别使用JC法和蒙特卡洛重要抽样法验证了新改进的遗传算法的准确性和有效性。结果表明,新改进的遗传算法与蒙特卡洛法计算的钢桁架可靠度指标相对误差仅为0.23%;且对于小概率失效结构,引入的自适应随机变量能有效改善传统方法中初始种群基因不良的问题。说明该方法在计算复杂隐式功能函数结构可靠度指标时,具有计算速度快、计算简单、精度高等优点,因而具有工程实际意义。

    Abstract:

    The calculation method is proposed in this paper, which is about reliability of structure with complex implicit function like steel truss. It adopts firstly the neural network to approach implicit function and NGA(New Genetic Algorithm) is employed to obtain the optimal solution of reliability index of steel truss and its design point on the basis of the geometric implication of reliability index. Finally, JC method and Monte Carlo Critical Sampling Method are introduced respectively in two examples to verify the accuracy and validity of NGA. The results manifest that the relative error is only 0.33 percent when NGA and Monte Carlo Method are used respectively to calculate reliability index of steel truss. In addition, the introduction of adaptive random variable can greatly improve the gene of initial population for small probability failure structures. All above prove that NGA is of significance in practical projects about calculating the reliability index of structure with complex implicit function due to its advantages of fast computation speed and high precision.

    参考文献
    相似文献
    引证文献
文章指标
  • PDF下载次数:
  • HTML阅读次数:
  • 摘要点击次数:
  • 引用次数:
引用本文
历史
  • 收稿日期: 2018-04-17
  • 最后修改日期: 2019-09-03
  • 录用日期: 2019-09-05
  • 在线发布日期:
  • 出版日期:
作者稿件一经被我刊录用,如无特别声明,即视作同意授予我刊论文整体的全部复制传播的权利,包括但不限于复制权、发行权、信息网络传播权、广播权、表演权、翻译权、汇编权、改编权等著作使用权转让给我刊,我刊有权根据工作需要,允许合作的数据库、新媒体平台及其他数字平台进行数字传播和国际传播等。特此声明。
关闭