基于驱动因素控制的DFCGM(1,N)及其拓展模型构建与应用  

Modeling and applications of DFCGM(1,N) and its extended model based on driving factors control

作　　者：丁松[1] 党耀国[1] 徐宁 朱晓月 DING Song, DANG Yao-guo1, XU Ning2, ZHU Xiao-yue1(1. College of Economics and Management, Nanjing University of Aeronautics and Astronautic, Nanjing 211106, China~ 2. College of Management Science and Engineering, Nanjing Audit University, Nanjing 211815, Chin)

机构地区：[1]南京航空航天大学经济与管理学院,南京211106 [2]南京审计大学管理科学与工程学院,南京211815

出　　处：《控制与决策》2018年第4期712-718,共7页Control and Decision

基　　金：国家自然科学基金项目(71371098;71771119;71701101);江苏省普通高校研究生科研创新计划项目(KYZZ16_0153);南京航空航天大学博士学位论文创新与创优基金项目(BCXJ16-09);江苏省社科基金重点研究项目(16GLA001);江苏省高校自然科学研究项目(16KJD120001)

摘　　要：针对一类驱动因素具有复杂变化特征的系统行为预测问题,将驱动因素序列对系统的作用函数引入经典GM(1,N)模型的灰色作用量,构建驱动因素控制的DFCGM(1,N)模型及其拓展模型,并探讨参数估计方法;从白化信息充分和匮乏两个角度,利用经验分析法和智能优化算法探索驱动因素控制参数的识别方法,并给出模型建模预测步骤;最后,通过对我国粮食产量进行预测,验证了模型的有效性和实用性,表明所提出模型能够有效解决多驱动因素影响的系统预测问题.To solve the forecasting problems of system behavior affected by driving factors with a complicated changing patterns, a driving foctor control grey model of N variables driving foctor control grey model of N variables（DFCGM（1,N）） model based on driving factors control and its derived model are designed by introducing a driver function into the construction of the grey action item in the conventional GM（1,N） model, and subsequently the method of estimating the parameters is discussed. According to the sufficient and insufficient information about the driving factors, empirical analysis and intelligent optimization algorithms are used to explore the estimation of driving factors control parameters, respectively, and subsequently the modeling procedure is given with a flowchart. Finally, the effectiveness and practicality of the proposed model are verified by forecasting the grain production in China. Results show that the proposed model can effectively solve the forecasting problems on the system affected by multiple driving factors.

关 键 词：灰色预测 驱动因素控制 DFCGM(1 N) 粮食产量预测 

分 类 号：N941.5[自然科学总论—系统科学]