论文部分内容阅读
传统的GM(1,1)模型,只适用于等间距监测数据序列的模拟预测,对非等间距监测序列,一般经过等间距处理或经过复杂的变换计算再建立非等间距模型。针对传统GM(1,1)模型的不足,本文探讨了几种合理且实用的改进GM(1,1)预测模型,并对各种优化GM(1,1)模型和传统GM(1,1)模型的预测结果进行了系统的对比分析。
The traditional GM (1,1) model is only suitable for the simulation prediction of the equally spaced monitoring data series. For non-equally spaced monitoring sequences, the non-equidistant model is usually established after equidistant processing or complicated transformation calculation. In order to overcome the shortcomings of the traditional GM (1,1) model, this paper discusses several reasonable and practical improved GM (1,1) prediction models, and analyzes various GM (1,1) models and traditional GM (1,1) ) Model of the predictive results of a systematic comparative analysis.