摘要
曲率模态是结构损伤识别的敏感标示量,采用数值仿真方法,把曲率模态用于桥梁损伤识别.利用简支梁损伤前后一阶曲率变化率作为识别参数,便可明显确定其多处损伤位置.对相关样本参数进行归一化处理并引入噪声干扰,利用BP人工神经网络进行数值仿真计算,也能对其损伤程度进行有效模拟,验证了BP神经网络也有很强的泛化能力及容错能力.
Based on numerical simulation,the curvature modal method used in damage identification of bridges was discussed.The curvature mode is very sensitive.When the change of the first-order curvature mode is used in the damage identification for simply supported beam bridges,it can locate the multiple damage accurately.With the BP Neural network trained by some sample data which is normalized and added noise,it can also realize the degree of damage identification,and prove the generalization capability tolerant capability of the BP Neural network.
出处
《华北水利水电学院学报》
2009年第4期37-39,共3页
North China Institute of Water Conservancy and Hydroelectric Power
基金
郑州航空工业管理学院青年基金项目
关键词
损伤识别
曲率模态
BP人工神经网络
简支梁
damage identification
curvature mode
BP artificial networks
simply supported beam
