基于驱动因素控制的DFCGM$(1,N)$ 及其拓展模型构建与应用

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.

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

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.