混凝土强度无损检测数据处理的混沌优化神经网络模型  

Chaos Optimum and Neural Network Model for Data Processing in Nondestructive Testing of Concrete Intensity

作　　者：史承明[1] 林维正[2] 张陵[3] 

机构地区：[1]上海宝钢集团房屋质量检测站,上海201900 [2]同济大学,上海200092 [3]西安交通大学,陕西西安710049

出　　处：《无损检测》2006年第3期123-126,共4页Nondestructive Testing

摘　　要：依据混凝土标准试块强度检测数据,建立了混沌优化的神经网络计算模型,从而克服传统BP网络收敛速度慢、易出现麻痹现象等不足。与混凝土无损检测现行规程规定的方法相比较,该计算模型简单可行,搜索速度快,预测结果可靠、精度高。A chaos optimum and neural network calculation model was built based on plenty of testing data of concrete intensity to cover the shortage of single BP neural network, such as slow astringency and easy torpidity. Compared with the algorithm stipulated in the current concrete nondestructive testing regulation, the model built was more simple and rapid for operation and higher in precision and reliability.

关 键 词：超声检测 混凝土强度 信号处理 神经网络 

分 类 号：TG115.28[金属学及工艺—物理冶金]