灰色GM(2,1)模型在滑坡变形预测中的应用

Application of gray GM(2,1) model to prediction of landslide deformation

应用灰色模型对滑坡变形进行预测,目前常用灰色GM(1,1)模型,而灰色GM(2,1)模型应用较少。在实际建模中发现,取不同长度的数据序列,建立的模型也不一样,所得的预测结果也有所不同。针对上述问题,本文基于统计的方法,得出白店子滑坡灰色预测模型最佳数据序列长度,在此基础上建立GM(2,1)模型对该滑坡深部位移进行预测,并与GM(1,1)模型预测结果进行了对比。结果表明,总体精度上GM(2,1)模型略高,预测误差较小,有很好的应用价值。

An ordinary gray GM(1,1) model is generally used for landslide deformation prediction,while the GM(2,1) model is used less.It is found that taking different lengths of data series,the model and the predictions are also different in the actual modeling.In response to the above problems,this paper examines the best length of data series of the Baidianzi landslide and uses gray prediction model.The GM(2,1) model of the landslide deep displacement is established for prediction and compared with the prediction of the GM(1,1) model.The results show that the precision of GM(2,1) model prediction is relatively high and the prediction error is comparatively low.