基于粒子群的支持向量机SVR冰情预报研究  

Study on Ice Regime Forecast Based on SVR Optimized by Particle Swarm Optimization Algorithm

作　　者：薛小辉 王富强[2] 周翔南[2] 

机构地区：[1]河南金正水利工程设计咨询有限公司,河南郑州450008 [2]华北水利水电学院,河南郑州450011

出　　处：《安徽农业科学》2012年第23期11765-11768,共4页Journal of Anhui Agricultural Sciences

基　　金：国家自然科学基金项目(51009065);河南省重点科技攻关计划项目(112102110033)

摘　　要：[目的]研究基于粒子群算法优化支持向量机SVR的黄河宁蒙段封河、开河日期预报模型。[方法]采用相关分析和成因分析相结合的方法选取合适的冰情预报因子组合,并运用粒子群算优化方法确定最优参数构建预报模型,将其运用到黄河宁蒙段封开河日期预报中。[结果]该模型预报精度高、运行时间短,预报平均误差为3.51 d,平均运行时间为10.464 s,预报效果明显优于遗传算法优化的支持向量回归与反向传播式神经网络,能够较准确地对封开河日期做出预报。[结论]基于粒子群算法优化支持向量回归的方法可以用于冰情预报。[Objective] The research aimed to study forecast models of the freeze-up date and break-up date in Ningxia-Inner Mongolia section of the Yellow River based on SVR optimized by particle swarm optimization algorithm.[Method] Correlation analysis and cause analysis were used to select suitable forecast factor combination of the ice regime.Particle swarm optimization algorithm was used to determine the optimal parameter to construct forecast model,which was used to forecast freeze-up date and break-up date in Ningxia-Inner Mongolia section of the Yellow River.[Result] The model had high prediction accuracy and short runtime.Average forecast error was 3.51 d,and average runtime was 10.464 s.Its forecast effect was better than that of support vector regression optimized by genetic algorithm and back propagation type neural network.It could accurately forecast freeze-up date and break-up date.[Conclusion] SVR based on particle swarm optimization algorithm could be used for ice regime forecast.

关 键 词：粒子群算法 支持向量机 SVR 冰情预报 

分 类 号：S112[农业科学—农业基础科学]