既有的关于GM(1,N)模型的研究,都是建立在实数序列基础上,文章将对GM(1,N)模型进行拓广,深入探讨该模型在区间灰数序列情形下的建模机理和建模方法,提出了基于核与灰半径的GM(1,N)模型。将以区间灰数序列的核序列和灰半径序列为基础建立GM(1,N)预测模型,进而对区间灰数序列的核与灰半径进行模拟预测,根据核与灰半径的计算公式推导出区间灰数的上界和下界,从而实现对区间灰数序列的模拟预测。最后,将文中提出的GM(1,N)模型应用于对霾存在时的空气质量指数AQI的预测研究中,模拟预测效果较好,从而验证了该模型的有效性和可行性。
The existing GM(1,N) model research is about the real number sequence. The GM(1,N) model is extended to explore the modeling mechanism and modeling method in the case of interval gray number series, then the GM(1,N) model based on kernel and gray radius is proposed. The GM(1,N) prediction model is established based on the kernel sequence and the gray radius sequence of the interval gray number sequence,and simulate and predict the kernel and gray radius of the interval gray series. According to the formula of kernel and gray radius, the upper and lower bounds of interval gray numbers are deduced to realize the simulation and prediction of the interval gray number series. Finally, the GM(1,N) model proposed is applied to predict the air quality index AQI in the presence of haze. The simulation results show that the model is effective and feasible.