基于季节与趋势模式的基坑顶部变形预测  

Deformation Prediction at the Top of Foundation Pits Based on Seasonal and Trend Patterns

作　　者：高林 文青山 冼进业 祝敏刚 GAO Lin;WEN Qingshan;XIAN Jinye;ZHU Mingang(China Power Construction Group Hainan Electric Power Design and Research Institute Co.,Ltd.,Haikou 570011,China;Shenzhen Zhigu Yichuan Information Technology Co.,Ltd.,Shenzhen 518000,Guangdong,China;Faculty of Engineering,China University of Geosciences(Wuhan),Wuhan 430074,China;China Power Construction Group Urban Planning and Design Institute Co.,Ltd.,Guangzhou 511400,China)

机构地区：[1]中国电建集团海南电力设计研究院有限公司,海口570011 [2]深圳市智谷一川信息科技有限公司,广东深圳518000 [3]中国地质大学(武汉)工程学院,武汉430074 [4]中国电建集团城市规划设计研究院有限公司,广州511400

出　　处：《科技和产业》2024年第21期300-305,共6页Science Technology and Industry

摘　　要：提出一种通过粒子群算法(PSO)优化变分模态分解(VMD)控制参数,并结合回声状态网络(ESN)和自注意力机制的基坑顶部变形预测方法。首先,利用粒子群算法优化VMD的控制参数,将基坑顶部变形序列数据分解成不同的本征模态函数(IMF),根据不同频率特征,将变形序列分解成季节项、趋势项与随机项。将自注意力机制与回声状态网络结合,对重构后的长时间序列数据进行建模,并对比筛选不同时长的输入数据,以确定最佳输入时长,从而提高预测精度。以广州某基坑的变形监测数据为例,对所提方法进行验证。实验结果表明,在输入步长为3的情况下,模型的MSE(均方误差)为0.62,R2为0.986,有效提升了基坑顶部变形预测的准确性与稳定性。A method for predicting top-of-foundation-pit deformation was proposed by optimizing the control parameters of variational mode decomposition(VMD)using particle swarm optimization(PSO)and combining echo state networks(ESN)with a self-attention mechanism.Firstly,the PSO was used to optimize the control parameters of VMD,decomposing the deformation sequence data of the foundation pit top into different intrinsic mode functions(IMF).According to the different frequency characteristics,the deformation sequence was decomposed into seasonal,trend,and random components.The self-attention mechanism was combined with ESN to model the reconstructed long-term sequence data,and different input data lengths are compared and selected to determine the optimal input length,thereby improving prediction accuracy.The proposed method was validated using deformation monitoring data from a foundation pit in Guangzhou.Experimental results show that with an input step of 3,the method achieves an MSE(mean square error)of 0.62 and an R 2 of 0.986,significantly improving the accuracy and stability of top-of-foundation-pit deformation prediction.

关 键 词：变分模态分解(VMD) 本征模态函数(IMF) 变形预测 基坑安全 回声状态网络(ESN) 

分 类 号：P642[天文地球—工程地质学]