摘要
基于Levenberg-Marquardt规则BP神经网络算法,利用频率变化量和曲率模态参数分别对框架结构损伤定位和定量识别问题进行了研究和实例分析。结果表明,它们均能对结构损伤进行预测,BP神经网络适用于此类损伤无规律对象问题的诊断。
On the basis of the theory that natural frequency changes and curvature mode shapes can be used to determine the locations and degrees of damage of structures, a BP neural network technique with an improved input structure is developed. The results show that two kinds of parameters can both be used to detect the structural damage and that the BP neural network models may well be applied to predicting diagnosis of some problems of irregular objects.
出处
《国防交通工程与技术》
2004年第2期15-19,29,共6页
Traffic Engineering and Technology for National Defence
