GA-BP神经网络地基纠偏沉降预测中的应用研究  

Study on the application of GA-BP Neural Network in the prediction of foundation deviation correction settlement

作　　者：王晓磊[1] 王斌 席亚军 刘历波[1] Wang Xiaolei;Wang Bin;Xi Yajun;Liu LiBo(School of Civil Engineerings Hebei University of Engineering,Handan 056038,China;Hebei Institute of Building Science Co.Ltd,Shijiazhang 050021,China)

机构地区：[1]河北工程大学土木工程学院,河北邯郸056038 [2]河北省建筑科学研究院有限公司,河北石家庄050021 [3]河北建研科技有限公司,河北石家庄050021

出　　处：《建筑科学》2020年第11期107-115,共9页Building Science

基　　金：河北省建设科技研究计划项目(2018-2014)。

摘　　要：在建筑纠偏实施过程中应用沉降监测数据对建筑回倾状况进行预测具有重要的工程意义。本文基于邯郸市某多层住宅建筑浅层掏土纠偏工程,研究GA-BP神经网络以掏土量和掏土位置为控制参数进行纠偏过程中建筑基础底板沉降预测分析中的应用效果,并进行与GA算法单监测点预测对比。结果表明,预测模型精相比于GA算法准度较高,能够对整体地基纠偏过程进行预测,与实际监测数据偏差不大,能够指导纠偏施工,相关研究成果可为同类工程的事前设计及施工可控性提供参照依据。It is of great engineering significance to apply settlement monitoring data to predict the reverse inclination of buildings in the process of building deviation correction.Based on the shallow excavation correction project of a multi-storey residential building in Handan City,the application effect of GA-BP neural network in the prediction and analysis of the settlement of the foundation floor of the building foundation in the process of rectifying the deviation with the amount and position of the excavated soil are studied,and it is compared with the prediction of the single monitoring point of the GA algorithm.The results show that the precision of the prediction model is higher than that of GA algorithm,and it can predict the whole foundation deviation correction process.The deviation between the prediction model and the actual monitoring data is small,and it can guide the deviation correction construction.The related research results can be of the same kind.The pre-design and construction controllability of the project provide reference basis.

关 键 词：地基沉降 纠偏加固 GA-BP神经网络算法 水平掏土法 沉降预测 

分 类 号：TU433[建筑科学—岩土工程]