摘要
基坑安全管理是大型建筑基坑施工的关键内容,基坑结构位移预测是预防基坑支护事故的重要手段。但是由于基坑局部基坑位移成因复杂,现有的支持向量回归(SVR)、随机森林(RF)方法忽略了基坑位移随空间位移局部减弱、随时间局部位移加快增长的特点,导致预测精度不高。因此,本文提出一种融合时空注意力机制的GA-BP神经网络(A-GABP)方法,通过时空特征准确表示基坑位移预测的时空维度及其特征相关性,提高基坑位移预测的有效性。最后,本文以苏州市某大型工程为实例,对基坑的水平与垂直位移监测数据进行模型训练与评估,按时域特征、空域特征、多阶时域空域特征进行量化分析与研究,并与现有方法进行比较。实验结果表明,本文方法的拟合指数比其他几种方法分别提高29.19%与41.25%,多阶时空域特征相较于单独的时间域或空间域特征分别提高3.08%与1.83%。
The safety management of the foundation pit is the key content of the construction of large-scale building foundation pits,and the displacement prediction of the foundation pit structure is an important means to prevent the maintenance accident of the foundation pit.However,due to the complex causes of local pit displacement in the pit,the existing support vector regression(SVR)and random forest(RF)methods ignore the characteristics of local weakening of the pit displacement with spatial dis⁃placement and accelerating growth with time local displacement,resulting in low prediction accuracy.Therefore,in this paper,a GA-BP neural network method that integrates the spatiotemporal attention mechanism(A-GA-BP)is proposed,which accu⁃rately represents the spatiotemporal dimensions and feature correlations of the foundation pit displacement prediction through spa⁃tiotemporal features,and improves the effectiveness of the foundation pit displacement prediction.Finally,taking a large-scale project in Suzhou as an example,this paper trains and evaluates the horizontal and vertical displacement monitoring data of the foundation pit,and quantifies the temporal features,spatial features and multi-order temporal and spatial features,and com⁃pares them with the existing methods.Experiment results show that the fitting index of this method is 29.19%and 41.25%higher than that of other methods,and the multi-order temporal and spatial features are 3.08%and 1.83%higher than the temporal or spatial features alone.
作者
王玉立
杨昌松
邱劲
韦俊
吴宏杰
WANG Yu-li;YANG Chang-song;QIU Jing;WEI Jun;WU Hong-jie(School of Electronic and Information Engineering,Suzhou University of Science and Technology,Suzhou 215009,China;School of Civil Engineering,Suzhou University of Science and Technology,Suzhou 215011,China;Suzhou Institute of Smart City,Suzhou University of Science and Technology,Suzhou 215009,China;Jiangsu Smart Engineering Laboratory of Big Data,Jiangsu Key Laboratory of Computer Information Processing Technology,Soochow University,Suzhou 215006,China)
出处
《计算机与现代化》
2023年第5期39-45,共7页
Computer and Modernization
基金
国家自然科学基金资助项目(62073231,61772357,61902272,61876217,61902271)。
关键词
时空注意力机制
基坑位移预测
多时域空域特征
BP神经网络
spatiotemporal attention mechanism
foundation pit displacement prediction
multi temporal and spatial features
BP neural network
