摘要
提出基于时间序列分析和人工神经网络的结构损伤诊断方法,并应用于钢筋混凝土筒仓结构的损伤诊断中。对筒仓结构的加速度响应建立自回归模型,提取模型系数的前四阶系数和结构的周期作为结构的损伤敏感因子,把损伤敏感因子作为输入向量输入到人工神经网络中,对这个神经网络进行训练,根据完成训练的网络对结构进行损伤诊断。结果表明结合时间序列分析和神经网络的损伤诊断方法能够有效地诊断筒仓结构的损伤。
An approach based on time series analysis and artificial neural network for structural damage diagnosis was proposed,which has been applied to the silo structure damage diagnosis.An Autoregressive(AR)model were used to fit the acceleration time history obtained from silo structure,and the four coefficients of the AR models combined with the period of silo structure were considered to be damage-sensitive features,and used as input into an artificial neural network,which was trained to classify damage cases.The results showed that a combination of time series analysis and artificial neural work can effectively classify damage cases in silo structure.
作者
王亚东
Wang Yadong(Central Southern China Electric Power Design Institute,Wuhan 430071,China)
出处
《山西建筑》
2020年第14期38-39,共2页
Shanxi Architecture
