摘要
阐述神经网络的概念和特点,着重介绍BP神经网络并在Matlab环境下建立基于BP神经网络的施肥模型,以土壤养分(氮、磷、钾)和实际产量为模型输入,以氮肥、磷肥和钾肥的施用量为模型数输出,进行网络训练,直至获得满意的施肥模型。结合投入产出物的价格对模型功能进行扩展,按利润最大化目标进行施肥决策。
The concept and characteristic for Artifical Neural Network are described. BP Artifical Neural Network and Fertilization model based on BP Artifical Neural Network in the Matlab system are introduced emphatically. The inputs of model are soil nutrients (N,P,K) and yield goal, the outputs are application rate of fertilizer (N,P,K). These data are trained in network until the ideal fertilization model is obtained, and integrate the price of the inputs and outputs matter to enlarge the function of model.
出处
《中国农机化》
北大核心
2004年第5期20-22,共3页
Chinese Agricul Tural Mechanization
