基于优化长短时记忆网络的深基坑变形预测方法及其工程应用

doi:10.6040/j.issn.1672-3961.0.2024.118

摘要/Abstract

摘要： 为更精准地预测基坑开挖诱发的支护结构变形,构建一种紧邻隧道深基坑变形预测模型,采用灰狼优化算法(grey wolf optimizer, GWO)自动优化长短时记忆网络模型(long short-term memory, LSTM)中的超参数,提升了原始LSTM模型预测结果的准确性。以南京市区内某紧邻隧道的深基坑项目为工程背景,对比分析BP神经网络、原始LSTM和GWO-LSTM模型的基坑变形预测结果,3种模型的决定系数(R2)分别为0.992、0.967和0.999,说明了GWO-LSTM模型在预测深基坑变形方面的优势和准确性。最后,采用GWO-LSTM模型对D₁₄监测点变形进行预测分析,预测结果与实测值基本一致,研究结果可为紧邻隧道深基坑安全建设提供技术支撑。

关键词: 深基坑工程, 变形预测, 机器学习, 神经网络, 优化算法

Abstract: To more accurately predict the deformation of support structures induced by excavation of foundation pits. The research constructed a deformation prediction model for deep foundation pits adjacent to tunnels. The grey wolf optimizer(GWO)algorithm was used to automatically optimize the hyperparameters in the long-short term memory network(LSTM), which improved the accuracy of the original LSTM model's prediction results. Taking a deep excavation project adjacent to a tunnel in the urban area of Nanjing as the engineering background, a comparative analysis was conducted on the prediction results of excavation deformation using BP neural network, original LSTM and GWO-LSTM models. The R2 of the three models were 0.992, 0.967, and 0.999, respectively, indicating the advantages and accuracy of the GWO-LSTM model in predicting deep excavation deformation. Finally, the GWO-LSTM model was used to predict and analyze the deformation of D₁₄ monitoring point and the predicted results were basically consistent with the measured values. The research results could provide technical support for the safe construction of deep foundation pits adjacent to tunnels.

Key words: deep foundation pit, deformation prediction, machine learning, neural network, optimization algorithm

中图分类号:

TU46+3

祝明,石承龙,吕潘,刘现荣,孙驰,陈建城,范宏运. 基于优化长短时记忆网络的深基坑变形预测方法及其工程应用[J]. 山东大学学报 (工学版), 2025, 55(3): 141-148.

ZHU Ming, SHI Chenglong, LÜ Pan, LIU Xianrong, SUN Chi, CHEN Jiancheng, FAN Hongyun. Deformation prediction method and engineering application of deep foundation pit based on optimized LSTM method[J]. Journal of Shandong University(Engineering Science), 2025, 55(3): 141-148.

参考文献

[1] 喻军, 龚晓南, 李元海. 基于海量数据的深基坑本体变形特征研究[J]. 岩土工程学报, 2014, 36(增刊2): 319-324. YU Jun, GONG Xiaonan, LI Yuanhai. Study on deformation characteristics of deep foundation pit based on massive data[J]. Chinese Journal of Geotechnical Engineering, 2014, 36(Suppl.2): 319-324.
[2] 李连祥, 韩志霄, 张潇潇, 等. 基于岩体稳定的土岩双元基坑破坏模式[J]. 山东大学学报(工学版), 2024, 54(3): 70-80. LI Lianxiang, HAN Zhixiao, ZHANG Xiaoxiao, et al. Failure mode of soil-rock dual foundation pit based on rock mass stability[J]. Journal of Shandong University(Engineering Science), 2024, 54(3): 70-80.
[3] 李连祥, 张强, 石锦江, 等. 基坑开挖邻近隧道水平形变位移规律[J]. 山东大学学报(工学版), 2021, 51(1): 46-52. LI Lianxiang, ZHANG Qiang, SHI Jinjiang, et al. Law of horizontal deformation displacement of tunnels due to adjacent excavation[J]. Journal of Shandong University(Engineering Science), 2021, 51(1): 46-52.
[4] 张陈蓉, 俞剑, 黄茂松. 基坑开挖对邻近地下管线影响的变形控制标准[J]. 岩土力学, 2012, 33(7): 2027-2034. ZHANG Chenrong, YU Jian, HUANG Maosong. Deformation controlling criterion of effect on underground pipelines due to foundation pit excavation[J]. Rock and Soil Mechanics, 2012, 33(7): 2027-2034.
[5] 朱晓天. 渗流作用下粉质黏土地层超深基坑危害数值模拟分析[J]. 隧道与地下工程灾害防治, 2022, 4(2): 98-106. ZHU Xiaotian. Numerical simulation analysis of ultra-deep foundation pit in silty clay formation under seepage[J]. Hazard Control in Tunnelling and Underground Engineering, 2022, 4(2): 98-106.
[6] 杨雨冰, 周彪, 谢雄耀. 邻近基坑施工作用下盾构隧道横向变形及开裂特性研究[J]. 岩石力学与工程学报, 2016, 35(增刊2): 4082-4093. YANG Yubing, ZHOU Biao, XIE Xiongyao. Study on lateral deformation and cracking characteristics of shield tunnel under adjacent foundation pit construction[J]. Chinese Journal of Rock Mechanics and Engineering, 2016, 35(Suppl.2): 4082-4093.
[7] 李涛, 杨依伟, 周予启, 等. 深基坑内支撑拆除时支护结构水平位移计算方法[J]. 岩石力学与工程学报, 2022, 41(增刊1): 3021-3032. LI Tao, YANG Yiwei, ZHOU Yuqi, et al. Calculation method of horizontal displacement of supporting structure during demolition of internal support in deep foundation pit[J]. Chinese Journal of Rock Mechanics and Engineering, 2022, 41(Suppl.1): 3021-3032.
[8] 梁发云, 褚峰, 宋著, 等. 紧邻地铁枢纽深基坑变形特性离心模型试验研究[J]. 岩土力学, 2012, 33(3): 657-664. LIANG Fayun, CHU Feng, SONG Zhu, et al. Centrifugal model test research on deformation behaviors of deep foundation pit adjacent to metro stations[J]. Rock and Soil Mechanics, 2012, 33(3): 657-664.
[9] YE S H, ZHAO Z F, WANG D. Deformation analysis and safety assessment of existing metro tunnels affected by excavation of a foundation pit[J]. Underground Space, 2021, 6(4): 421-431.
[10] 孙钧, 温海洋. 人工智能科学在软土地下工程施工变形预测与控制中的应用实践: 理论基础、方法实施、精细化智能管理(示例)[J]. 隧道建设(中英文), 2020, 40(1): 1-8. SUN Jun, WEN Haiyang. Application of artificial intelligence science to construction deformation prediction and control of underground engineering in soft soil: cases study on theoretical foundation, method application and fine intelligent technical management[J]. Tunnel Construction, 2020, 40(1): 1-8.
[11] 汤志立, 徐千军. 基于9种机器学习算法的岩爆预测研究[J]. 岩石力学与工程学报, 2020, 39(4): 773-781. TANG Zhili, XU Qianjun. Rockburst prediction based on nine machine learning algorithms[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(4): 773-781.
[12] 刘开云, 乔春生, 滕文彦. 边坡位移非线性时间序列采用支持向量机算法的智能建模与预测研究[J]. 岩土工程学报, 2004, 26(1): 57-61. LIU Kaiyun, QIAO Chunsheng, TENG Wenyan. Research on non-linear time sequence intelligent model construction and prediction of slope displacement by using support vector machine algorithm[J]. Chinese Journal of Geotechnical Engineering, 2004, 26(1): 57-61.
[13] 徐长节, 李欣雨. 基于人工神经网络的深基坑支护结构侧移预测[J].上海交通大学学报, 2024, 58(11):1735-1744. XU Changjie, LI Xinyu. Lateral deformation prediction of deep foundation retaining structures based on artificial neural network[J]. Journal of Shanghai Jiaotong University, 2024, 58(11): 1735-1744.
[14] 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(增刊2): 741-749. LI Yanjie, XUE Yadong, YUE Lei, et al. Deformation prediction of deep foundation pit based on genetic algorithm-BP neural network[J]. Chinese Journal of Underground Space and Engineering, 2015, 11(Suppl.2): 741-749.
[15] LÜ Y, LIU T T, MA J, et al. Retraction Note: study on settlement prediction model of deep foundation pit in sand and pebble strata based on grey theory and BP neural network[J]. Arabian Journal of Geosciences, 2022, 15(8): 742.
[16] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[17] 张生杰, 谭勇. 基于LSTM算法的基坑变形预测[J]. 隧道建设(中英文), 2022, 42(1): 113-120. ZHANG Shengjie, TAN Yong. Deformation prediction of foundation pit based on long short-term memory algorithm[J]. Tunnel Construction, 2022, 42(1): 113-120.
[18] SHAN J Z, ZHANG X, LIU Y W, et al. Deformation prediction of large-scale civil structures using spatiotemporal clustering and empirical mode decomposition-based long short-term memory network[J]. Automation in Construction, 2024, 158: 105222.
[19] MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61.
[20] 孙铁军, 李杰, 张豹, 等. 基于GWO-SVR模型的基坑边坡变形预测及敏感性分析[J]. 公路, 2022, 67(4): 390-395. SUN Tiejun, LI Jie, ZHANG Bao, et al. Deformation prediction and sensitivity analysis of foundation pit slope based on GWO-SVR model[J]. Highway, 2022, 67(4): 390-395.
[21] 阮永芬, 余东晓, 吴龙, 等. DE-GWO算法优化SVM反演软土力学参数[J]. 岩土工程学报, 2021, 43(增刊1): 166-170. RUAN Yongfen, YU Dongxiao, WU Long, et al. Optimization of SVM inversion of soft soil mechanical parameters by DE-GWO algorithm[J]. Chinese Journal of Geotechnical Engineering, 2021, 43(Suppl.1): 166-170.
[22] 邱道宏, 傅康, 薛翊国, 等. 深埋隧道TBM掘进参数LSTM时序预测模型及应用研究[J]. 中南大学学报(自然科学版), 2021, 52(8): 2646-2660. QIU Daohong, FU Kang, XUE Yiguo, et al. LSTM time-series prediction model for TBM tunneling parameters of deep-buried tunnels and application research[J]. Journal of Central South University(Science and Technology), 2021, 52(8): 2646-2660.
[23] ZHANG W G, TANG L B, LI H R, et al. Probabilistic stability analysis of Bazimen landslide with monitored rainfall data and water level fluctuations in Three Gorges Reservoir, China[J]. Frontiers of Structural and Civil Engineering, 2020, 14(5): 1247-1261.
[24] TANG L B, MA Y B, WANG L, et al. Application of long short-term memory neural network and prophet algorithm in slope displacement prediction[J]. International Journal of Geoengineering Case Histories, 2021, 6(4): 48-66.
[25] 苏恩杰, 叶飞, 何乔, 等. 基于卷积神经网络-长短期记忆的施工期盾构管片上浮过程预测模型[J]. 同济大学学报(自然科学版), 2023, 51(9): 1352-1361. SU Enjie, YE Fei, HE Qiao, et al. Prediction model of shield segment floating process during construction based on convolutional neural networks and long short-term memory[J]. Journal of Tongji University(Natural Science), 2023, 51(9): 1352-1361.
[26] 李洛宾, 龚晓南, 甘晓露, 等. 基于循环神经网络的盾构隧道引发地面最大沉降预测[J]. 土木工程学报, 2020, 53(增刊1): 13-19. LI Luobin, GONG Xiaonan, GAN Xiaolu, et al. Prediction of maximum ground settlement caused by shield tunnel based on cyclic neural network[J]. China Civil Engineering Journal, 2020, 53(Suppl.1): 13-19.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed