欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为了尽可能准确预测城市未来的需水量,以上海市为例,对年用水量的9个相关因子进行主成分分析,得到两个综合因子。将两综合因子与用水量的历史数据一起作为输入项,建立一种小波网络模型,以1980～2005年的数据为训练样本,采用引入了附加动量项和自适应学习率的BP算法进行模型率定,并以2006～2008年的数据对模型进行了检验。结果表明：所建模型结构简洁,收敛速度与预测精度均较为理想,在城市需水预测中有着广阔的应用前景。而如何选择最佳隐层数和隐层节点数以及获得更快的收敛速度仍将是今后研究的重点问题
英文摘要：
Taking Shanghai City as an example,we extract two comprehensive factors by principal components analysis from 9 factors relevant with the annual water consumption,which are adopted as inputs with the historical water consumption data to establish a wavelet network model.The improved BP algorithm with additional momentum method and adaptive learning rate has been applied for model calibration using data from 1980 to 2005;and the model is verified based on the data from 2006 to 2008.The results indicate that the proposed model is superior in the structure,convergence rate and prediction precision,which has a broad application prospect in urban water demand prediction.Choosing the best hidden layers and hidden layer nodes to obtain the faster convergence rate is the focus in further study.
同期刊论文项目
同项目期刊论文
Spatio-temporal patterns of hydrological processes and their responses to human activities in the Po
Impacts of climate change and human activities on surface runoff in the Dongjiang River basin of Chi
Changing properties of hydrological extremes in south China: natural variations or human influences?
Multiscale streamflow variations of the Pearl River basin and possible implications for the water De
Precipitation variability (1956~2002) in the Dongjiang River (Zhujiang River basin, China) and assoc
Statistical behaviours of precipitation regimes in China and their links with atmospheric circulatio
Estimation of evapotranspiration using remotely sensed land surface temperature and the revised thre
The Influence of dam and lakes on the Yangtze River streamflow: Long-range correlation and complexit
期刊信息
位置：