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。
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.
出处
《船舶力学》
EI
北大核心
2006年第5期84-89,共6页
Journal of Ship Mechanics
关键词
小波神经网络
疲劳寿命预测
可靠度
疲劳曲线
wavelet neural network
prediction of fatigue life
reliability
fatigue curves
