基于数列变换优化的灰色系统模型

Data mapping optimization based grey model

提出了一种可对含负项数列建立灰色系统模型的变换方法,并利用Matlab对变换参数进行优化。针对变换函数的特点提出了一种简化变换参数优化的方法,使二维优化问题简化为一维优化,可显著减小优化计算量,同时可获得较高的模型精度,这样就可在处理含负项数列的同时获得较高的模型精度,拓展了GM模型的应用范围。具体算例验证了所提建模方法的有效性。

A data mapping method is adopted to get the GM model of data sequence that contains negative items. To get optimum parameters of the data mapping function, optimization is performed through Matlab. Furthermore, based on the characteristic of the data mapping function a simplified data mapping parameters optimization method is proposed for reducing the 2-D to 1-D optimization problem, which can considerably reduce the computational amounts of optimization, and achieve quite high precision of modeling. This method not only can treat data sequence containing negative items, but also can achieve rather precise GM modeling, which enlarge the application areas of GM model. Actual cases validate the efficiency of this method.