Time Series Prediction of Diaphragm Wall Deformation Based on GWO-LSTM-CNN

LUO Weibo; LI Long; ZHANG Yuhao; TONG Liyuan; WU Kai

doi:10.3724/j.gyjzG24123001

Volume 56 Issue 7

Jul. 2026

Turn off MathJax

Article Contents

Article Navigation > INDUSTRIAL CONSTRUCTION > 2026 > 56(7): 216-222

LUO Weibo, LI Long, ZHANG Yuhao, TONG Liyuan, WU Kai. Time Series Prediction of Diaphragm Wall Deformation Based on GWO-LSTM-CNN[J]. INDUSTRIAL CONSTRUCTION, 2026, 56(7): 216-222. doi: 10.3724/j.gyjzG24123001

Citation:

LUO Weibo, LI Long, ZHANG Yuhao, TONG Liyuan, WU Kai. Time Series Prediction of Diaphragm Wall Deformation Based on GWO-LSTM-CNN[J]. INDUSTRIAL CONSTRUCTION, 2026, 56(7): 216-222. doi: 10.3724/j.gyjzG24123001

Citation:

PDF( 1293 KB)

Time Series Prediction of Diaphragm Wall Deformation Based on GWO-LSTM-CNN

doi: 10.3724/j.gyjzG24123001

1. CCCC Third Harbor Engineering Co., Ltd., Shanghai 200030, China;
2. School of Transportation, Southeast University, Nanjing 211189, China

Received Date: 2024-12-30
Available Online: 2026-08-31
Publish Date: 2026-07-20

Abstract

Abstract

Based on the foundation excavation project of a metro station on Nanjing Metro Line 11， this study proposes an intelligent dynamic prediction model for diaphragm wall deformation using an autoregressive approach to achieve high-precision predictions for multiple future time steps. The model integrates Long Short-Term Memory （LSTM） networks and Convolutional Neural Networks （CNN）， leveraging their complementary strengths in extracting spatiotemporal features. Furthermore， the Grey Wolf Optimizer （GWO） was employed to optimize the model’s hyperparameters， thereby enhancing its prediction performance and stability. The results demonstrated that GWO significantly improved the accuracy of the fusion model in multi-step prediction tasks， verifying the applicability and reliability of the proposed method in complex engineering environments.
- deep foundation excavation,
- diaphragm wall deformation,
- deep learning,
- model fusion,
- Grey Wolf Optimizer

FullText(HTML)

References(22)

References

[1]	WANG J H，XU Z H，WANG W D. Wall and ground movements due to deep excavations in shanghai soft soils[J]. Journal of Geotechnical and Geoenvironmental Engineering，2010，136（7）:985-994.
[2]	MOORMANN C. Analysis of wall and ground movements due to deep excavations in soft soil based on a new worldwide database[J]. Soils and Foundations，2004，44（1）:87-98.
[3]	刘美麟，房倩，张顶立，等.基于改进MSD法的基坑开挖动态变形预测[J].岩石力学与工程学报，2018，37（7）:1700-1707.
[4]	DAN K，SAHU R B. Estimation of ground movement and wall deflection in braced excavation by minimum potential energy approach[J]. International Journal of Geomechanics，2018，18（7）:04018068.
[5]	张坤勇，张梦，孙斌，等.考虑时空效应的软土狭长型深基坑地连墙变形计算方法[J].岩土力学，2023，44（8）:2389-2399.
[6]	HOU Y M，WANG J H，ZHANG L L. Finite-element modeling of a complex deep excavation in Shanghai[J]. ACTA Geotechnica，2009，4（1）:7-16.
[7]	赵其华，孙钧，徐伟.地连墙变形的神经网络多步预测研究[J].成都理工学院学报，2002（5）:581-585.
[8]	王宇霁，杨潇.基于动态递归神经网络的地连墙安全预测[J].路基工程，2016（3）:60-64.
[9]	王雨，刘国彬，屠传豹.基于遗传-GRNN在深基坑地连墙测斜预测中的研究[J].岩土工程学报，2012，34（增刊1）:167-171.
[10]	宋楚平.一种改进的BP神经网络深基坑变形预测方法[J].土木工程与管理学报，2019，36（5）:45-49.
[11]	许凯文.基于遗传算法优化BP神经网络的深基坑地连墙变形预测[J].粉煤灰综合利用，2021，35（5）:6-11.
[12]	ZHAO H J，LIU W，SHI P X，et al. Spatiotemporal deep learning approach on estimation of diaphragm wall deformation induced by excavation[J]. Acta Geotechnica，2021，16（11）:3631-3645.
[13]	赵华菁，张名扬，刘维，等.基于神经网络算法的深基坑地连墙变形动态预测[J].地下空间与工程学报，2021，17（增刊1）:321-327.
[14]	YANG J，LIU Y，YAGIZ S，et al. An intelligent procedure for updating deformation prediction of braced excavation in clay using gated recurrent unit neural networks[J]. Journal of Rock Mechanics and Geotechnical Engineering，2021，13（6）:1485-1499.
[15]	SONG F，ZHONG H，LI J，et al. Multi-point rcnn for predicting deformation in deep excavation pit surrounding soil mass[J]. IEEE Access，2023，11:124808-124818.
[16]	FAN H，LI L，ZHOU S，et al. Prediction and risk assessment of lateral collapse in deep foundation pits using machine learning[J]. Automation in Construction，2025，171:106011.
[17]	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.
[18]	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.
[19]	HOCHREITER S，SCHMIDHUBER J. Long short-term memory[J]. Neural Computation，1997，9（8）:1735-1780.
[20]	LECUN Y，BOTTOU L，BENGIO Y，et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE，1998，86（11）:2278-2324.
[21]	MIRJALILI S，MIRJALILI M S，LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software，2014，69:46-61.
[22]	PASZKE A，GROSS S，MASSA F，et al. Pytorch:an imperative style，high-performance deep learning library[J]. Advances in Neural Information Processing Systems，2019，32:8024-8035.