基于多尺度分析与神经网络的需水量预测

详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文

英文篇名：Water demand forecasting based on multi-scales analysis and neural network 中文刊名：计算机工程与应用 英文刊名：Computer Engineering and Applications 作者：畅建霞 ; 于兴杰 ; 黄强 ; 刘招 英文作者：CHANG Jian-xia ; YU Xing-jie ; HUANG Qiang ; LIU Zhao College of Hydroelectric Power ; Xi’an University of Technology ; Xi’an 710048 ; China 中文关键词：多尺度分解 ; BP神经网络 ; 小波分析 ; 需水量预测 英文关键词：multi-scale decomposition ; BP Neural Network ; wavelet analysis ; water demand forecasting 出版日期：2008-06-11 机构：西安理工大学水电学院,西安理工大学水电学院,西安理工大学水电学院,西安理工大学水电学院 西安710048,西安710048,西安710048,西安710048 年：2008 期：17 出版单位：计算机工程与应用

摘要

采用小波多尺度分解的方法,将需水量时间序列分解为多个较平稳的细节子序列和一个趋势序列,再利用BP神经网络对分解后的各序列进行预测,把预测后的序列聚合重构,得到预测结果。以新疆石河子地区的需水量为例对该方法作了验证。表明多尺度分析与神经网络耦合预测,比单一BP神经网络预测精度更高,可满足实际需要。
The time series of water demand can be decomposed into several stationary detailed time series and a tendency time series according to the algorithm of this multi-scales in this paper.Decomposed time series are forecasted with BP neural network to obtain the prediction series.Then the forecasting results are reconstructed by wavelet theory.So,the forecasting result is gained.An example of water demand of Shihezi in Xinjiang Province is used to testify the feasibility of the new method.The results show that the method of coupling multi-scale decomposition and BP neural network has advantages over the traditional BP neural network in predicted qualification-rate,and has feasibility in forecasting of time series.

引文

[1]郑治真,沈萍.小波变换及其MATLAB工具的应用[M].北京:地震出版社,2001.
    [2]吴东杰,王金生,滕彦国.小波分解与变换法预测地下水位动态[J].水利学报,2004,5(5):39-42.
    [3]宁津生,汪海洪,罗志才.小波分析在大地测量中的应用及其进展[J].武汉大学学报,2004,8(29):659-662.
    [4]张少文,张学成.基于多尺度下AR(P)耦合预测模型的应用研究[J].四川大学学报:工程科学版,2004,9(5):16-19.
    [5]Mallat S.A wavelet tour of signal processing[M].2nd ed.USA:Academic Press,1999.
    [6]Chen S,Billings S A.Neural networks for nonlinear dynamic system modeling and identification[J].Int J Control,1992,56:291-319.