基于卡尔曼滤波的GM模型及其在公路边坡变形预测中的应用

The Application of Kalman Filter Based GM Model in Road Slop Deformation Monitoring

在公路边坡变形监测与预测中,当用GM(1,1)模型对稳定的变形数据序列进行预测时,效果较好。但是,如果变形数据中因外界因素干扰而出现异常数据,使变形曲线发生波动,此时单纯采用GM(1,1)模型进行预测,就难以取得理想的预测精度。为此,本文提出一种基于卡尔曼滤波的GM预测模型,即先用卡尔曼滤波法对原始变形监测数据进行滤波处理,而后再建立GM模型进行灰色预测。通过公路边坡变形预测的应用研究,证明基于卡尔曼滤波的GM模型可以有效地提高预测精度。

In road slope deformation monitoring and forecasting, when GM is used, it can get good results in forecasting the steady deformation data. However, the forecast precision of GM model will decline when the abnormity data appear and the deformation data curve fluctuate up and down with the changeful environmental conditions. In this situation, the forecast results of GM model will become worse. Therefore, this paper presents a GM model based on Kalman filter. This model uses Kalman filter method to filter the original deformation monitoring data, and then, builds the GM model to forecast road slop deformation. The related case studying has proved that this Kalman filter based GM model can effectively increase the forecast precision.