摘要
模型误差、量测噪声及量测数据不完整等因素是制约结构损伤识别技术应用的主要难点.为此,利用结构部分节点静力位移以及前几阶固有频率构造出神经网络合适的输入参数形式.采用改进动量BP神经网络算法对一五榀桁架结构进行了损伤识别数值模拟研究.识别结果表明,在一定水平噪声及量测数据不完备条件下,网络仍有较好的识别损伤位置及程度能力.
Some factors, such as modeling error, measured noises, incomplete measured data, are main difficulties for many structural damage processes being utilized. The input parameter vectors for neural networks are constituted by using static displacements on partial nodes and several low frequencies. A damage numerical verification study on a five-bay truss was carried out by using an improved momentum BP neural network. 1-dentification results indicate that the neural networks have excellent capability to identify structural damage location and damage extent under the conditions of limited noises and incomplete measured data.
出处
《哈尔滨工业大学学报》
EI
CAS
CSCD
北大核心
2005年第4期488-490,共3页
Journal of Harbin Institute of Technology
基金
国家自然科学基金重点资助项目(5043901050378012)
关键词
静力位移
固有频率
神经网络
噪声
static displacement
natural frequency
neural networks
measured noises
