采用模糊神经网络方法结合粗糙集理论和主成分分析技术,研制了模糊神经网络区域降水预报系统,系统利用VB和MATLAB6.5联合开发,并采用中文菜单显示的人机对话方式操作,使模糊神经网络的网络结构和多种参数的调整变得灵活而易于操作;实际应用表明,该系统对广西3个区域平均降水预报效果良好,适用性强,为广西有效防御和减少灾害提供了新的有效方法和业务服务系统。
In terms of Fuzzy neural network (FNN) combined with rough sets theory and Principal component analysis (PCA), a forecasting system of regional rainfall is established. The system is developed by VB and MATLAB6.5. Application results show that the system operated in interactive mode with Chinese character menu is convenient and superior On forecast for regional rainfall to FNN marked by adjusting parameter and structure.The system provides a new and effective methods and business services to relieve the Guangxi calamity.