GM(1,2)模型改进方法研究及应用  

Study on the improved method for GM(1,2) model and its application

作　　者：雷鸣雳[1] 冯祖仁[2] 

机构地区：[1]西安交通大学系统工程研究所,西安710049 [2]西安交通大学机械制造系统工程国家重点实验室,西安710049

出　　处：《控制与决策》2013年第6期950-952,956,共4页Control and Decision

基　　金：国家自然科学基金项目(60875043);教育部博士点基金项目(2010020111003)

摘　　要：针对GM(1,2)建模难点和模型缺陷提出两种改进方法:一是运用相关匹配算法,在历史数据库中搜索与主序列具有强关联特性的数据序列,确定为模型参考序列;二是引入粒子群算法,以模型预测性能评价指标为目标函数对模型参数进行辨识,改善模型预测性能.算例结果表明了改进方法的适用性和有效性.@@@@Two improved method are proposed for the difficulty and defects of the traditional GM(1,2) model. Firstly, the correlation matching algorithm is adopted to search the reference sequence which has the maximum grey relation grade in the history database. Secondly, the particle swarm optimization algorithm is used to identify the model parameters by taking the evaluation function of the forecasting performance as the objective function. The simulation results show the effectiveness and the applicability of the presented method.

关 键 词：灰色预测 GM(1 2)模型 粒子群算法 相关系数 

分 类 号：N94[自然科学总论—系统科学]