基于ICOFWA算子的连续区间模糊组合预测模型及其应用  

The Continuous Interval Combination Forecasting Model Based on ICOFWA Operator and Their Applications

作　　者：朱家明[1] 陈华友[1] 周礼刚[1] 刘金培[2] 

机构地区：[1]安徽大学数学科学学院,安徽合肥230601 [2]安徽大学商学院,安徽合肥230601

出　　处：《模糊系统与数学》2016年第3期172-184,共13页Fuzzy Systems and Mathematics

基　　金：国家自然科学基金资助项目(71371011;71301001;11426033);教育部高等学校博士点基金资助项目(20123401110001);教育部人文社科青年项目(13YJC630092)

摘　　要：现有的区间组合预测中,各单项预测方法的权重系数均为固定实数,而实际上,模糊加权系数能够更好的解释客观世界的模糊性和不确定性,从而有效地改进传统组合预测方法取固定实数权重的缺陷。因此,本文提出一种权重系数为三角模糊数的组合预测新方法,构建了基于诱导连续有序模糊加权平均(ICOFWA)算子的模糊连续区间变权组合预测模型。通过实例分析说明该区间组合预测方法的有效性,并对参数做了灵敏度分析。The weighting coefficients of all single forecasting method are determined by positive real numbers in the existing interval combination forecasting method. In fact, the fuzzy weighting coefficients could have a better explanation on the fuzziness and uncertainty of objective world. It also could overcome the defects of fixed weighting coefficients of positive real numbers in the traditional interval combination forecasting method effectively. Hence, this paper proposes a new method that the weighting coefficients are triangular fuzzy numbers, and the fuzzy continuous interval combination forecasting model is developed based on the induced continuous fuzzy ordered weighted averaging operator. An example is also provided to illustrate the proposed method in which the effectiveness is guaranteed, and sensitivity analysis is given to some parameters.

关 键 词：模糊区间组合预测 ICOFWA算子 三角模糊权重 有效性 

分 类 号：O159[理学—数学]