论文部分内容阅读
水资源供需矛盾日益突出,需水量预测已成为广泛关注的焦点.需水量预测可以为“三条红线”的实施提供依据,以强化水资源管理和节水监督管理,缓解水资源供需矛盾.基于BP神经网络模型,采用自适应调整的算法,改进了BP神经网络模型中学习率的求解方法,并将其应用到郑州市经济社会需水量预测中,预测了2012年和2015年经济社会需水量,分别为14.41亿m3和14.84亿m3;通过与BP神经网络模型、主成分回归分析结果对比,发现改进后的BP神经网络模型根据迭代误差自动调整学习率,求解速度和计算结果精度明显提高,适用于郑州市需水量预测.
The contradiction between supply and demand of water resources has become increasingly prominent, water demand forecasting has become the focus of widespread attention.Water demand forecasting can provide the basis for the implementation of “three red lines” to strengthen the supervision of water resources management and water conservation and alleviate the contradiction between water supply and demand. Based on the BP neural network model and adaptive adjustment algorithm, the method of solving the learning rate in BP neural network model is improved and applied to the economic and social water demand prediction of Zhengzhou City. The economic and social needs in 2012 and 2015 Respectively. Compared with the BP neural network model and principal component regression analysis, it is found that the improved BP neural network model automatically adjusts the learning rate according to the iterative error, and the solution speed and accuracy of the calculation result are obviously improved , For Zhengzhou City, water demand forecast.