作　　者： ; ; ; ;

机构地区： 华北水利水电学院

出　　处： 《华北水利水电学院学报》 2005年第2期9-11,共3页

摘　　要： 科学的预测城市生活需水量对城市的发展具有十分重要的意义.城市生活需水量受到多重因素的影响,各因素之间的相关性较大.将自变量利用偏最小二乘回归处理,提取对因变量影响强的成分,既可以克服变量之间的相关性问题,又可以降低神经网络的输入维数;利用神经网络建模可以较好地解决非线性问题.将偏最小二乘回归与神经网络耦合,建立了城市生活用水量预报模型.实例表明,耦合模型的拟合和预报精度均较好. It is quite significant to urban development that the urban life-water quantity is scientifically forecasted. The urban life-water quantity is influenced by many factors among which the relativities are big. Dealt with independent variables by the partial least_squares method, it can not only solve the relationship between independent variables but also reduce the input dimensions in neural network model, and then use the neural network which can solve the non-linear problem better.The model for the urban life-water quantity prediction is established, combining neural network with the partial least_squares method. The result of an example shows the prediction and fitting have high precision.

关 键 词： 偏最小二乘回归 神经网络 城市生活用水量

领　　域： [水利工程] [自动化与计算机技术] [自动化与计算机技术]