奇异谱分析-灰色混合模型在深基坑变形预测中的应用

Application of Singular Spectrum Analysis-Grey Mixed Model in Deformation Prediction of Deep Foundation Pit

针对基坑变形的监测和预测易受到噪声干扰的问题,采用了基于奇异谱分析的基坑变形数据重构方法,提取基坑变形的主趋势分量,用于构建灰色预测模型,提升基坑沉降和水平位移监测和预测的准确性。采用广州某基坑工程的数据进行了测试,结果表明:与直接采用灰色模型对原始数据预测相比,奇异谱分析-灰色混合模型在不同的数据维度下均能提供更准确的预测结果。

The monitoring and prediction of foundation pit deformation are easily interfered by noise.To improve the accuracy of monitoring and prediction of foundation pit settlement and horizontal displacement,a data reconstruction method based on singular spectrum analysis is employed to extract the main trend component of foundation pit deformation,which is then used to build a gray prediction model.Real project data is used for testing,and the results show that the singular spectrum analysis-grey prediction model can provide more accurate prediction results under different data dimensions,compared with using only grey model for the original data modeling and prediction.