Predicting excavation-induced lateral displacement using improved particle swarm optimization and extreme learning machine with sparse measurements

Monitoring lateral displacement in deep excavation projects is crucial for structural stability and safety. Traditional methods, like manual inclinometers, are accurate but costly and labor-intensive. Automated systems provide real-time data but face challenges with dense sensor placement and high c...

Full description

Saved in:
Bibliographic Details
Main Authors: Cheng Chen, Guan-Nian Chen, Song Feng, Xiao-Zhen Fan, Liang-Tong Zhan, Yun-Min Chen
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-08-01
Series:Underground Space
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2467967425000406
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849419462052151296
author Cheng Chen
Guan-Nian Chen
Song Feng
Xiao-Zhen Fan
Liang-Tong Zhan
Yun-Min Chen
author_facet Cheng Chen
Guan-Nian Chen
Song Feng
Xiao-Zhen Fan
Liang-Tong Zhan
Yun-Min Chen
author_sort Cheng Chen
collection DOAJ
description Monitoring lateral displacement in deep excavation projects is crucial for structural stability and safety. Traditional methods, like manual inclinometers, are accurate but costly and labor-intensive. Automated systems provide real-time data but face challenges with dense sensor placement and high costs. This study presents a novel prediction method using an extreme learning machine (ELM) optimized by an improved particle swarm optimization (IPSO) algorithm. The IPSO-ELM approach utilizes sparse automated measurements to accurately predict lateral displacement profiles, minimizing the need for dense sensor deployment. A case study of a 30.2-m-deep excavation project in Hangzhou, China, demonstrates the method’s effectiveness. The results demonstrate that the IPSO-ELM model maintains high prediction accuracy, with low root mean square error (RMSE) and mean absolute error (MAE) values, even under conditions of sparse sensor placement. Across the entire test dataset, with a sensor spacing of 5.0 m, the model achieved maximum RMSE values ranging from 0.94 to 2.79 mm and maximum MAE values ranging from 0.77 to 2.18 mm, thereby showcasing its robustness and reliability in predicting lateral displacement. A detailed discussion was conducted on the errors associated with various sensor spacing intervals when implementing the proposed method. This study underscores the potential of IPSO-ELM as a cost-effective and reliable tool for automatic monitoring in increasingly complex urban excavation projects.
format Article
id doaj-art-8faa5804c330458ebe152f9dc4999f4d
institution Kabale University
issn 2467-9674
language English
publishDate 2025-08-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Underground Space
spelling doaj-art-8faa5804c330458ebe152f9dc4999f4d2025-08-20T03:32:04ZengKeAi Communications Co., Ltd.Underground Space2467-96742025-08-012312514510.1016/j.undsp.2025.02.004Predicting excavation-induced lateral displacement using improved particle swarm optimization and extreme learning machine with sparse measurementsCheng Chen0Guan-Nian Chen1Song Feng2Xiao-Zhen Fan3Liang-Tong Zhan4Yun-Min Chen5School of Engineering, Hangzhou City University, Hangzhou 310015, China; MOE Key Laboratory of Soft Soils and Geoenvironmental Engineering, Zhejiang University, Hangzhou 310058, China; Corresponding author at: School of Engineering, Hangzhou City University, Hangzhou 310015, China.School of Civil & Environmental Engineering and Geography Science, Ningbo University, Ningbo 315211, ChinaCollege of Civil Engineering, Fuzhou University, Fuzhou 350108, ChinaSchool of Engineering, Hangzhou City University, Hangzhou 310015, ChinaMOE Key Laboratory of Soft Soils and Geoenvironmental Engineering, Zhejiang University, Hangzhou 310058, ChinaMOE Key Laboratory of Soft Soils and Geoenvironmental Engineering, Zhejiang University, Hangzhou 310058, ChinaMonitoring lateral displacement in deep excavation projects is crucial for structural stability and safety. Traditional methods, like manual inclinometers, are accurate but costly and labor-intensive. Automated systems provide real-time data but face challenges with dense sensor placement and high costs. This study presents a novel prediction method using an extreme learning machine (ELM) optimized by an improved particle swarm optimization (IPSO) algorithm. The IPSO-ELM approach utilizes sparse automated measurements to accurately predict lateral displacement profiles, minimizing the need for dense sensor deployment. A case study of a 30.2-m-deep excavation project in Hangzhou, China, demonstrates the method’s effectiveness. The results demonstrate that the IPSO-ELM model maintains high prediction accuracy, with low root mean square error (RMSE) and mean absolute error (MAE) values, even under conditions of sparse sensor placement. Across the entire test dataset, with a sensor spacing of 5.0 m, the model achieved maximum RMSE values ranging from 0.94 to 2.79 mm and maximum MAE values ranging from 0.77 to 2.18 mm, thereby showcasing its robustness and reliability in predicting lateral displacement. A detailed discussion was conducted on the errors associated with various sensor spacing intervals when implementing the proposed method. This study underscores the potential of IPSO-ELM as a cost-effective and reliable tool for automatic monitoring in increasingly complex urban excavation projects.http://www.sciencedirect.com/science/article/pii/S2467967425000406Automated monitoringExtreme learning machineLateral displacementDeep excavationParticle swarm optimizationPredictive modeling
spellingShingle Cheng Chen
Guan-Nian Chen
Song Feng
Xiao-Zhen Fan
Liang-Tong Zhan
Yun-Min Chen
Predicting excavation-induced lateral displacement using improved particle swarm optimization and extreme learning machine with sparse measurements
Underground Space
Automated monitoring
Extreme learning machine
Lateral displacement
Deep excavation
Particle swarm optimization
Predictive modeling
title Predicting excavation-induced lateral displacement using improved particle swarm optimization and extreme learning machine with sparse measurements
title_full Predicting excavation-induced lateral displacement using improved particle swarm optimization and extreme learning machine with sparse measurements
title_fullStr Predicting excavation-induced lateral displacement using improved particle swarm optimization and extreme learning machine with sparse measurements
title_full_unstemmed Predicting excavation-induced lateral displacement using improved particle swarm optimization and extreme learning machine with sparse measurements
title_short Predicting excavation-induced lateral displacement using improved particle swarm optimization and extreme learning machine with sparse measurements
title_sort predicting excavation induced lateral displacement using improved particle swarm optimization and extreme learning machine with sparse measurements
topic Automated monitoring
Extreme learning machine
Lateral displacement
Deep excavation
Particle swarm optimization
Predictive modeling
url http://www.sciencedirect.com/science/article/pii/S2467967425000406
work_keys_str_mv AT chengchen predictingexcavationinducedlateraldisplacementusingimprovedparticleswarmoptimizationandextremelearningmachinewithsparsemeasurements
AT guannianchen predictingexcavationinducedlateraldisplacementusingimprovedparticleswarmoptimizationandextremelearningmachinewithsparsemeasurements
AT songfeng predictingexcavationinducedlateraldisplacementusingimprovedparticleswarmoptimizationandextremelearningmachinewithsparsemeasurements
AT xiaozhenfan predictingexcavationinducedlateraldisplacementusingimprovedparticleswarmoptimizationandextremelearningmachinewithsparsemeasurements
AT liangtongzhan predictingexcavationinducedlateraldisplacementusingimprovedparticleswarmoptimizationandextremelearningmachinewithsparsemeasurements
AT yunminchen predictingexcavationinducedlateraldisplacementusingimprovedparticleswarmoptimizationandextremelearningmachinewithsparsemeasurements