以 Delphi3.0为开发工具 ,建立了植物病虫害 BP神经网络预测系统 ,阐述了 BP神经网络的基本原理和预测系统的制作过程 ,并以陕西汉中地区小麦条锈病流行程度的预测为例说明了其应用。结果表明 ,该系统的预测结果与实际发生程度高度吻合 Based on Delphi3.0, a BP neural network prediction system for plant diseases and insect pests was established. The basic principle of BP neural network and the production process of the prediction system were described. The prediction of the prevalence of wheat stripe rust in Hanzhong area in Shaanxi Province was taken as an example to illustrate its application. The results show that the forecast result of this system is in good agreement with the actual occurrence