摘要
基于遗传神经网络的基本概念及学习步骤,对大坝坝基渗流量、坝基扬压力监测数据进行了训练和预测。结果表明,利用遗传算法特有的全局优化能力,可以较好地完成网络的学习,而且还减少了网络训练次数,缩短了网络训练时间。
On the basis of brief introduction of the principle and algorithm of genetic neural network, the forcast model is applied on the monitoring data of seepage and hydraulic uplift pressure of a dam foundation. The result indicates that the forcast model could complete the training and forcasting of the network with less training frequency and time by means of overall optimizing ability of genetic algorithm.
出处
《水电能源科学》
2003年第4期26-27,34,共3页
Water Resources and Power
