基于OLS算法的RBF神经网络在大坝安全监测中的应用  

The OLS Algorithm for RBF network And its applications

作　　者：刘红涛 

机构地区：[1]陕西省西安市临潼区油槐街道办,陕西西安710604

出　　处：《中国科技博览》2010年第8期292-293,共2页China Science and Technology Review

摘　　要：文章介绍了RBF网络的基本原理以及网络中心选取OLS算法（正交最小二乘法），并将该方法应用于大坝渗流安全监测资料的分析预报上，应用结果表明：该神经网路可以很好地克服BP神经网络学习过程的收敛过分依赖于初值和可能出现局部收敛的缺陷，具有较快的运算速度、较强的非线性映射能力和较好的预报功能。Basic concepts of RBF neural network and the OLS algorithm are introduced in this paper. The actual application in dam seeps safety monitoring forecast shows that ： The neural network can overcome some demerit of BP neural networks in learning process, the constringency excessively depend on initial value and optimization constringency and often can, t appear. The RBF neural networks possess the rapid operation speed in learning and strong nonlinear mapping ability and very good efficiency.

关 键 词：RBF 神经网络OLS算法 大坝 安全监测 

分 类 号：X924.2[环境科学与工程—安全科学]