基于改进的BP神经网络的桥梁结构损伤诊断研究  

Study of Bridge Structure Damage Diagnosis Based on Improved BP Neural Network

作　　者：艾叶青[1] 王根会[1] 朱尚清 

机构地区：[1]兰州交通大学土木工程学院,甘肃兰州730070 [2]中国路桥集团桥梁技术有限公司,北京100102

出　　处：《兰州交通大学学报》2005年第3期44-47,共4页Journal of Lanzhou Jiaotong University

摘　　要：采用改进后的BP神经网络对桥梁结构进行损伤诊断,通过与传统BP网络法的诊断结果进行对比,得出改进后的BP网络算法在实际应用中能克服传统BP网络算法收敛速度慢,存在局部极小的问题.改进后BP网络的桥梁结构损伤诊断具有较好的诊断效果,与传统的BP神经网络相比,不仅提高了计算速度,而且较大地提高了识别精度,具有较好的应用前景.In this paper, an improved BP neural network is proposed for the structural damage diagnosis. It is compared with the traditional BP neural network through diagnosis results.The improved BP neural network algorithm can overcome astringency slowly and partition minimum that are in traditional BP neural network algorithm.The Improved BP network has better diagnosis results. The results show that the improved BP neural network gives rise to a more accurate prediction and improves the computational speed in traditional BP neural network.The improved BP neural network has better application prospects.

关 键 词：神经网络 改进后的BP神经网络 损伤诊断 

分 类 号：U441.4[建筑科学—桥梁与隧道工程]