节点文献

基于小波神经网络和疲劳曲线的结构疲劳寿命及可靠度预测

Application of artificial neural networks and fatigue curves in prediction of fatigue life and reliability of structures

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 纪冬梅胡毓仁

【Author】 JI Dong-mei,HU Yu-ren (School of Naval Architecture Ocean and Civil Engineering,Shanghai Jiao Tong University,Shanghai 200030,China)

【机构】 上海交通大学船舶海洋与建筑工程学院上海交通大学船舶海洋与建筑工程学院 上海200030上海200030

【摘要】 基于疲劳曲线,考虑应力范围的随机性,获得结构疲劳寿命所服从的分布,计算出期望寿命的可靠度。以非线性Morlet小波基作为激励函数形成神经元,结合小波与神经网络的优点,建立小波神经网络模型,从而得到应力范围、结构疲劳寿命及可靠度之间的关系,用于预测某应力范围下所期望可靠度的疲劳寿命,或者所期望疲劳寿命的可靠度。

【Abstract】 The life distribution of the structures and the reliability of the expected life can be obtained by applying the fatigue curves and considering the randomicity of the stress range.The wavelet neural network was constituted taking the nonlinear Morlet wavelet radices as the stimulant function,and it can combine the advantages of wavelet analysis and neural networks.The relationships among the stress range,the life of the structures and the reliability can be obtained based on the wavelet neural network.The fatigue life of the expected reliability or the reliability of the expected life under a certain stress range can be predicted by using the trained network.

  • 【文献出处】 船舶力学 ,Journal of Ship Mechanics , 编辑部邮箱 ,2006年05期
  • 【分类号】U661.4
  • 【被引频次】9
  • 【下载频次】445
节点文献中: 

本文链接的文献网络图示:

本文的引文网络