改进最小二乘法对基坑支护结构竖向位移预测  

Forecasting for horizontal displacement of foundation pit supporting structure based on the improved least-squares method

作　　者：王波[1] 欧阳治华[1] 肖晓 

机构地区：[1]武汉科技大学资源与环境工程学院,湖北武汉430081

出　　处：《辽宁工程技术大学学报（自然科学版）》2017年第12期1279-1283,共5页Journal of Liaoning Technical University (Natural Science)

摘　　要：为提高支护结构竖向沉降预测精度的问题,采用改进最小二乘法模型.在前期沉降值的基础上,引入一个修正后的最小二乘法预测曲线,得到新的预测模型,建立既保证原来的维数,而又不影响整个沉降发展趋势的改进最小二乘法模型.以SMW工法基坑支护为工程实例,利用改进最小二乘法对采集的监测数据进行研究,求出支护结构竖向位移拟合曲线,进而得到拟合值.结果表明:该方法所得的实测值和预测值进行比较,与实测值误差很小且满足规范规定的数值,证明该方法在SMW工法支护结构竖向位移预测中应用的有效性及预测所提高的精度;既保证了传统最小二乘法位移曲线的维数,又不影响整个预测沉降变形曲线的发展趋势,更适用于周边环境复杂的基坑支护结构竖向位移预测.In order to enhance forecasting precision for the vertical displacement of supporting structure, this paper proposed an improved least-squares method model. By using the modified data taken from the traditional least-squares method model, an improved least-squares method model was built based on the pre-settlement value,which ensured the original dimensionality and retained the settlement growing trend of the whole information. Taking the foundation pit supporting structure of composite steel soil-cement mixed diaphragm wall as a study project case, the improved least-squares method was used to study collected monitoring data, and the fitted curve of the displacement of the supporting structure was obtained and further obtained the fitted value. The results show that the absolute error of the improved least-squares method is smaller than that of the traditional least-squares method, and the prediction accuracy is improved. The improved least-squares method model not only ensures the original dimensionality, but also retains the growing trend of the whole information, which is more suitable for the prediction of the supporting structure with complex surrounding environment.

关 键 词：SMW工法桩 最小二乘法 改进最小二乘法 沉降预测 基坑 

分 类 号：TU196.2[建筑科学—建筑理论]