沉降预测的非等步长灰色时变参数模型

针对经典灰色系统模型的不足，根据灰色系统理论的信息处理原则，在模型中引入遗忘因子，建立了灰色系统沉降预测的非等步长灰色时变参数模型，并在求解过程中引入遗忘因子以修正预测结果。模型充分考虑了预测系统的时变性和灰色性，从而降低对预测系统状态的预测误差。实例预测表明，灰色时变参数模型可以将工后总沉降量的预测误差控制在2．3％以内。误差检验结果显示，预测结果的精度等级较引入遗忘因子修正前有显著的提高。

Unequal Interval Gray Time-varying Parameters Model for Settlement Prediction

The gray time-varying parameters model of unequal interval is built to avoid the faults of classical gray model, following the information handling principle of the gray theory and leading a forgetting factor into the model to correct the prediction results. In the model, both time-varying property and the correcting effect of the forgetting factor are considered, so the prediction error is smaller. The case study shows that the error of finishing settlement can be controlled within 2 3% by the Gray TVP Model. As a result, the error checking indicates the precision grade is updated after prediction results is corrected by the forgetting factor.