水稻需水量预测的小波BP网络模型  

Wavelet BP network model for prediction of the water requirement of rice

作　　者：冯艳[1] 付强[1] 李国良[1] 李伟业[1] 刘仁涛[1] 冯登超[2] 

机构地区：[1]东北农业大学水利与建筑学院,哈尔滨150030 [2]天津大学电子信息工程学院,天津300072

出　　处：《农业工程学报》2007年第4期66-69,共4页Transactions of the Chinese Society of Agricultural Engineering

基　　金：国家自然科学基金(No.30400275);中国博士后科学基金(No.2004035167);黑龙江省青年基金(No.QC04C28)

摘　　要：结合BP网络和小波分析的优势,建立一种水稻需水量预测的小波BP网络模型,旨在准确预测水稻需水量,为制定合理的灌溉制度与提高水分利用效率提供重要依据。该文以小波函数代替传统BP网络中的S型激活函数,对三江平原富锦灌区16年的水稻需水量实测序列进行分析,网络结构为6-10-1,训练355次时,精度达到0.01。结果均优于BP算法、RAGA SABP模型,表明该模型收敛速度快,预测精度高,为该领域研究提供了新的思路。In order to provide foundation for making scientific irrigation schedule and heighten the water use efficiency, the advantage of BP network and wavelet analysis is integrated to establish a wavelet BP network model for predicting water requirement of rice. Replaced the traditional S-shaped activation function with the wavelet function, 16 years actual measuring series of water requirement of rice in Fujin irrigation area of Sanjiang Plain were analyzed. With the network structure of 6-10-1, the precision of prediction reaches 0. 01 while it is disciplined 355 times. The result is superior to both BP algorithm and RAGASABP model, and shows that the model has fast convergence speed and high forecasting precision. A new idea of research is given in the field.

关 键 词：BP网络 小波分析 水稻需水量 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]