基于直觉模糊线性方程组的IFTS预测方法  

Forecasting method of IFTS based on intuitionistic fuzzy linear equations

作　　者：郑寇全[1,2] 雷英杰[1] 余晓东[1] 王睿[1] 

机构地区：[1]空军工程大学防空反导学院 [2]中国人民解放军68331部队

出　　处：《控制与决策》2014年第5期941-945,共5页Control and Decision

基　　金：国家自然科学基金项目(61272011;61309022);国家重点实验室基金项目(2012ADL-DW0301)

摘　　要：针对模糊时间序列预测理论对不确定性数据集的实时模糊变化趋势研究存在的不足,规范了直觉模糊时间序列的定义,提出了基于直觉模糊线性方程组的直觉模糊时间序列预测方法.所提出的算法将模型的求解转化为一系列带有约束的线性规划问题,准确地反映了序列数据随时间发展变化的模糊关联规律,简化了预测模型的复杂度,提高了时间序列预测的精度,扩展了直觉模糊时间序列预测理论的应用范围.最后,通过仿真实验验证了所提出方法的有效性和优越性.To the study deficiency of the fuzzy time series forecasting theory for real-time fuzzy variation trend of uncertain data sets, the intuitionistic fuzzy time series forecasting model is presented by using the intuitionistic fuzzy system of linear equations. In the proposed approach, the solution to the models is transformed into the linear programming problem. Then, the fuzzy connection rules of the sequence dates changing with time are reflected precisely. Meanwhile, the forecasting accuracy of time series in the complex environment is improved, thus greatly extending the intuitionistic fuzzy time series forecasting application. Finally, the classical instance verifies the effectiveness and superiority of the proposed method.

关 键 词：直觉模糊集 时间序列 线性方程组 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]