【摘要】 给出了一种能动态选择最优初始条件及相应辨识参数的新型灰色GM(1, 1)预测模型,文中称为GM(1, 1)新陈代谢模型。这种改良的GM(1, 1)模型在对深圳市民中心大型屋顶网架健康智能监测系统时程数据的动态预测中,取得了良好的应用效果。更多还原

【Abstract】 An improved GM (1, 1) called metabolic GM (1, 1) model is proposed in order to improve prediction accuracy. In traditional GM (1, 1), initial conditions and identifying parameters no longer change once they are confirmed. However, it is not fit for dynamic and long data prediction. This model which can choose the best initialization conditions and dynamically confirm identifying parameters like a metabolism process is introduced. This metabolic GM (1, 1) model is applied to predict time-displacement data for a Health Intelligent Monitoring System for Large-Scale Roof Lattice Structure of Shenzhen Civil Center and achieves good results.更多还原