优化组合模型在建筑物基坑沉降预测中的应用  

Application of Optimal Combination Model in Prediction of Building Foundation Pit Settlement

作　　者：胡琦琦 马森 HU Qiqi;MA Sen(Zhejiang Land Survey and Planning Co.,Ltd.,Hangzhou 310030,China;Sanmen County Natural Resources and Planning Bureau,Taizhou 317100,China)

机构地区：[1]浙江省国土勘测规划有限公司,浙江杭州310030 [2]三门县自然资源和规划局,浙江台州317100

出　　处：《测绘与空间地理信息》2023年第12期173-176,共4页Geomatics & Spatial Information Technology

摘　　要：为了确保建筑物在建设过程中的安全,需要准确掌握建筑物基坑及周边的变形情况。针对建筑物基坑沉降变形预测问题,本文对单一的GM(1.1)模型与BP神经网络模型进行优化并构建组合预测模型。优化组合模型一方面解决了单一预测模型稳定性差、预测精度低的问题,另一方面提高了预测模型的适用性。将本文提出的组合预测模型应用于某在建建筑物基坑沉降变形预测中,结果表明,相较于单一的GM(1.1)模型与BP神经网络模型,本文提出的优化组合预测模型的预测精度与稳定性更高,证明了组合预测模型在建筑物基坑类沉降预测中的可靠性。In order to ensure the safety of buildings in the construction process,it is necessary to accurately grasp the deformation of building foundation pit and surrounding.Aiming at the prediction problem of building foundation pit settlement deformation,this paper optimizes the single GM(1.1)model and BP neural network model,and constructs a combined prediction model.On the one hand,the optimized combination model overcomes the problems of poor stability and low prediction accuracy of a single prediction model,on the other hand,it improves the applicability of the prediction model.The combined prediction model proposed in this paper is applied to the prediction of foundation pit settlement deformation of a building under construction.The results show that compared with the single GM(1.1)model and BP neural network model,the prediction accuracy and stability of the optimized combined prediction model proposed in this paper are higher,which proves the reliability of the combined prediction model in the prediction of foundation pit settlement of buildings.

关 键 词：GM(1.1)模型 BP神经网络模型 遗传算法 建筑物基坑 沉降预测 

分 类 号：P25[天文地球—测绘科学与技术] TB22[天文地球—大地测量学与测量工程]