最优权组合模型在季冻区公路软基工后沉降中的应用

Application of Optimal Weight Combination Model in Settlement of Highway Soft Foundation in Seasonal Frozen Area

为研究最优权组合预测模型在季冻区公路软基沉降预测中的适用性,选取某一级公路的典型断面,采用分层沉降仪进行沉降监测,通过沉降管上磁环位置的移动来反映路基沉降变化。根据一年的沉降实测资料,对原始非线性数据进行三次样条插值处理,基于最优权权重法将灰色GM(1,1)及二次曲线模型进行组合,对地基的远期沉降进行预测,将预测结果与实测资料进行对比,探究该模型的适用性,同时基于季冻区气候特点,选取适合高寒地区路基监测的合理时距。研究表明:最优权权重组合模型的预测效果与样本数密切相关,适当增加建立模型的样本数亦可显著提高预测精度;在考虑区域气候条件下,适当减少冬季及沉降速率较慢的月份的样本数量,增加在沉降初期及冻融前后的样本数量可以有效提高模型的预测效果;本文的最优权组合预测模型可以较好地预测季冻区公路远期沉降,为类似工程的沉降预测提供参考。

In order to study the applicability of the optimal weight combination prediction model in the settlement prediction of highway soft foundation in the seasonal frozen area,the layered settlement meter was used to monitor the settlement in a typical section of a first grade highway.The change of subgrade settlement was reflected by the movement of the magnetic ring on the settlement tube.The original nonlinear data were processed by cubic spline interpolation according to the measured settlement data of one year.The grey GM(1,1)and the conic model were combined based on the optimal weight method to predict the long-term settlement of the foundation.Afterwards,the predicted results were compared with the measured data to explore the applicability of the model.Meanwhile,selected a reasonable time interval suitable for subgrade monitoring in alpine regions based on the climatic characteristics of the seasonal frozen region.The research shows that the prediction effect of the optimal weight combination model is closely related to the number of samples,thus properly increasing the number of samples establishing the model can significantly improve the prediction accuracy.Under the consideration of regional climatic conditions,properly reducing the number of samples in winter and months with slow settlement rate and increasing the number of samples in the initial stage of settlement and before and after freezing and thawing can effectively improve the prediction effect of the model.The optimal weight combination forecasting model in this study can better predict the long-term settlement of highway in seasonal frozen area and provide reference for the settlement prediction of similar projects.