上海大学力学与工程科学学院,上海 200444
秦世伟(1973—),男,讲师,硕导,博士。主要从事岩土工程检测方向研究。E-mail: 10002358@shu.edu.cn
戴自立(1987—),男,副教授,博导,博士。主要从事土木工程防灾减灾方向研究。E-mail: zilidai@shu.edu.cn
收稿:2023-12-08,
修回:2024-01-29,
纸质出版:2024-12-15
移动端阅览
秦世伟,朱则匀,戴自立.基于GCN⁃LSTM组合模型的基坑钢支撑轴力时空序列预测[J].防灾减灾工程学报,2024,44(06):1257-1264.
QIN Shiwei,ZHU Zeyun,DAI Zili.Spatiotemporal Sequence Prediction of Axial Force in Foundation Pit Steel Supports Based on GCN-LSTM Combined Model[J].Journal of Disaster Prevention and Mitigation Engineering,2024,44(06):1257-1264.
秦世伟,朱则匀,戴自立.基于GCN⁃LSTM组合模型的基坑钢支撑轴力时空序列预测[J].防灾减灾工程学报,2024,44(06):1257-1264. DOI: 10.13409/j.cnki.jdpme.20231208001.
QIN Shiwei,ZHU Zeyun,DAI Zili.Spatiotemporal Sequence Prediction of Axial Force in Foundation Pit Steel Supports Based on GCN-LSTM Combined Model[J].Journal of Disaster Prevention and Mitigation Engineering,2024,44(06):1257-1264. DOI: 10.13409/j.cnki.jdpme.20231208001.
基坑钢支撑的轴力变化是反应基坑中内力变化的重要指标,也是基坑工程灾害防治的重点研究对象。由于土体力学性质的复杂性以及受力演化的不确定性,单纯通过监测和计算难以把握基坑中实际的内力变化趋势。已有研究表明支撑轴力的演化具有典型的时序特征,可使用时间序列预测模型对数据进行预测分析,但预测精度普遍不高。基坑中多个点位的支撑轴力变化往往具有明显的空间相关性,但现有的模型无法捕捉空间信息。为解决上述问题,使用图卷积神经网络(Graph Convolutional Neural Network, GCN)和长短期记忆网络(Long Short⁃Term Memory, LSTM),组合构建了能捕捉数据时间和空间特征的时空序列预测模型。该模型根据实际点位的空间信息构建了邻接矩阵并生成对应的空间特征,以支撑轴力,空间信息,温度作为输入特征,来预测支撑轴力的发展趋势。使用上海某车站项目中四个具有空间相关性的点位数据进行预测分析,并将组合模型的预测结果与实测数据、单一LSTM模型预测数据进行对比,结果表明:(1)组合模型的收敛速度更快,对于长周期的数据拟合能力更强,并且能更好的反应数据的波动性;(2)组合模型的精度高于仅考虑时间序列特征的单一LSTM模型,有效提高了支撑轴力数据的预测精度。该模型可为实际工程数值预测提供计算参考。
The variation of axial force in foundation pit steel supports is a crucial indicator that reflects the changes in internal force within foundation pit. It is a key research focus in disaster prevention and mitigation in foundation pit engineering. Due to the complexity of soil mechanical properties and the uncertainty of stress evolution
it is challenging to capture the variation of internal force in foundation pit solely through monitoring and calculation. Previous studies have shown that the evolution of support axial force exhibits typical temporal characteristics
suggesting that temporal sequence models can be used for predictive analysis. However
the accuracy of these predictions is generally low. Additionally
significant spatial correlations exist in the axial force variation at multiple locations in foundation pit
yet existing models often fail to capture spatial information. To address the issues above
this study establishes a model that combines Graph Convolutional Neural Network (GCN) and Long Short-Term Memory (LSTM)
which is a spatiotemporal prediction model capable of capturing both temporal and spatial features of the data. The model constructed an adjacency matrix based on the spatial information of actual locations and generated corresponding spatial features. By utilizing axial force
spatial information
and temperature as input parameters
this model predicted the trend of support axial force. Predictive analysis was conducted using data from four spatially correlated points in a metro station in Shanghai
and the results of the combined model were compared with actual measurements and predictions based on the LSTM model. The results indicated that: (1) The combined model exhibited a faster convergence speed
stronger fitting capabilities for long-period data
and better responsiveness to data volatility; (2) The accuracy of the combined model surpassed that of the LSTM model that only considered temporal sequence. The combined model effectively enhances the prediction accuracy of axial force data
providing computational references for numerical predictions in engineering applications.
刘汉龙 , 马彦彬 , 仉文岗 . 大数据技术在地质灾害防治中的应用综述 [J]. 防灾减灾工程学报 , 2021 , 41 ( 4 ): 710 - 722 .
Liu H L , Ma Y B , Zhang W G . Overview of the application of big data technology in geological disaster prevention and control [J]. Journal of Disaster Prevention and Mitigation Engineering , 2021 , 41 ( 4 ): 710 - 722 . (in Chinese)
袁金荣 , 赵福勇 . 基坑变形预测的时间序列分析 [J]. 土木工程学报 , 2001 , 34 ( 6 ): 55 - 59 .
Yuan J R , Zhao F Y . Time series analysis for deformation prediction of foundation pits [J]. Journal of Civil Engineering , 2001 , 34 ( 6 ): 55 - 59 . (in Chinese)
Feng T G , Wang C R , Zhang J , et al . Prediction of stratum deformation during the excavation of a foundation pit in composite formation based on the artificial bee colony–back-propagation model [J]. Engineering Optimization , 2022 , 54 ( 7 ): 1217 - 1235 .
孟凡丽 , 郑棋 , 李燕 , 等 . 基于BP神经网络的深基坑围护变形预测 [J]. 浙江工业大学学报 , 2014 , 42 ( 4 ): 367 - 372 .
Meng F L , Zheng Q , Li Y , et al . Deformation prediction of deep foundation pit support based on BP neural network [J]. Journal of Zhejiang University of Technology , 2014 , 42 ( 4 ): 367 - 372 . (in Chinese)
胡少伟 , 李原昊 , 单常喜 , 等 . 基于改进的PSO-BP神经网络的边坡稳定性研究 [J]. 防灾减灾工程学报 , 2023 , 43 ( 4 ): 854 - 861 .
Hu S W , Li Y H , Shan C X , et al . Study on slope stability based on an improved PSO-BP neural network [J]. Journal of Disaster Prevention and Mitigation Engineering , 2023 , 43 ( 4 ): 854 - 861 . (in Chinese)
Yu L L , Liu X X , Su L , et al . Research on the back propagation neural network haze prediction model based on particle swarm optimization [C]∥ 2020 International Conference on Computer Engineering and Application (ICCEA) . IEEE , 2020 : 344 - 348 .
李彦杰 , 薛亚东 , 岳磊 , 等 . 基于遗传算法-BP神经网络的深基坑变形预测 [J]. 地下空间与工程学报 , 2015 , 11 ( 增2 ): 741 - 749 .
Li Y J , Xue Y D , Yue L , et al . Deep foundation pit deformation prediction based on genetic algorithm-BP neural network [J]. Chinese Journal of Underground Space and Engineering , 2015 , 11 ( Sup2 ): 741 - 749 . (in Chinese)
谢洋洋 , 付超 , 吴大鹏 , 等 . 利用PSO-GA-LSSVM模型预测基坑周边建筑物沉降 [J]. 测绘地理信息 , 2021 , 46 ( 3 ): 50 - 54 .
Xie Y Y , Fu C , Wu D P , et al . Prediction of settlement around foundation pits using the PSO-GA-LSSVM model [J]. Geomatics and Information Science of Wuhan University , 2021 , 46 ( 3 ): 50 - 54 . (in Chinese)
Zhu Q , Luo Y L , Zhou D Y , et al . Drought prediction using in situ and remote sensing products with SVM over the Xiang River Basin, China [J]. Natural Hazards , 2021 , 105 : 2161 - 2185 .
李立云 , 孙庆玺 . 基坑开挖诱发既有建(构)筑物变形的SVM-BP预测模型及其工程应用 [J]. 防灾科技学院学报 , 2020 , 22 ( 2 ): 1 - 9 .
Li L Y , Sun Q X . SVM-BP prediction model for deformation of existing buildings induced by foundation pit excavation and its engineering application [J]. Journal of Institute of Disaster Prevention Science and Technology , 2020 , 22 ( 2 ): 1 - 9 . (in Chinese)
徐浩峰 , 应宏伟 , 朱向荣 . 时间序列分析方法预报基坑支撑轴力 [J]. 水利学报 , 2004 , 35 ( 1 ): 105 - 109 .
Xu H F , Ying H W , Zhu X R . Time series analysis method for predicting axial force in foundation pitsupport [J]. Journal of Hydraulic Engineering , 2004 , 35 ( 1 ): 105 - 109 . (in Chinese)
曹净 , 丁文云 , 赵党书 , 等 . 基于LSSVM-ARMA模型的基坑变形时间序列预测 [J]. 岩土力学 , 2014 , 35 ( 增2 ): 579 - 586 .
Cao J , Ding W Y , Zhao D S , et al . Time series prediction of foundation pit deformation based on the LSSVM-ARMA model [J]. Rock and Soil Mechanics , 2014 , 35 ( Sup2 ): 579 - 586 . (in Chinese)
刘俊城 , 谭勇 , 张生杰 . 地铁车站深基坑开挖变形智能多步预测方法 [J]. 上海交通大学学报 , 2023 , 58 ( 7 ): 1108 - 1117 .
Liu J C , Tan Y , Zhang S J . Intelligent multi-step prediction method for deformation during deep foundation pit excavation at subway stations [J]. Journal of Shanghai Jiao Tong University , 2023 , 58 ( 7 ): 1108 - 1117 . (in Chinese)
Li H L , Zhao Z Z , Du X . Research and application of deformation prediction model for deep foundation pit based on LSTM [J]. Wireless Communications and Mobile Computing , 2022 , 2022 ( 1 ): 9407999 .
Zheng J , Wang Y , Xu W J , et al . GSSA: Pay attention to graph feature importance for GCN via statistical self-attention [J]. Neurocomputing , 2020 , 417 : 458 - 470 .
Li S , Li W T , Wang W . Co-gcn for multi-view semi-supervised learning [C]∥ Proceedings of the AAAI conference on artificial intelligence . New york : New YOrk Hilton Midtown , 2020 : 4691 - 4698 .
Zhou X , Wu X T , Ding P , et al . Research on transformer partial discharge UHF pattern recognition based on CNN-lSTM [J]. Energies , 2019 , 13 ( 1 ): 61 .
Hakim N L , Shih T K , Kasthuri Arachchi S P , et al . Dynamic hand gesture recognition using 3DCNN and LSTM with FSM context-aware model [J]. Sensors , 2019 , 19 ( 24 ): 5429 .
杨丽 , 吴雨茜 , 王俊丽 , 等 . 循环神经网络研究综述 [J]. 计算机应用 , 2018 , 38 ( 增2 ): 1 - 6, 26 .
Yang L , Wu Y X , Wang J L , et al . A review on recurrent neural networks [J]. Journal of Computer Applications , 2018 , 38 ( Sup2 ): 1 - 6, 26 . (in Chinese)
万磊 , 余飞 , 鲁统伟 , 等 . 基于CEEMDAN-CNN-GRU组合模型的短期负荷预测方法 [J]. 河北科技大学学报 , 2022 , 43 ( 2 ): 154 - 161 .
Wan L , Yu F , Lu T W , et al . Short-term load forecasting method based on the combination of CEEMDAN-CNN-GRU model [J]. Journal of Hebei University of Scienceand Technology , 2022 , 43 ( 2 ): 154 - 161 . (in Chinese)
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
苏公网安备32010202012147号
