Reconstruction and prediction of tunnel surrounding rock deformation data based on PSO optimized LSSVR and GPR models

Predicting the deformation of surrounding rock is an important task to ensure the safety of mountain tunnel construction.This study, set against the backdrop of an actual under-construction tunnel, reconstructed the missing surrounding rock monitoring data using a Particle Swarm Optimization-based L...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhenqian Huang, Zhen Huang, Pengtao An, Jun Liu, Chen Gao, Juncai Huang
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123024016979
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846115752550072320
author Zhenqian Huang
Zhen Huang
Pengtao An
Jun Liu
Chen Gao
Juncai Huang
author_facet Zhenqian Huang
Zhen Huang
Pengtao An
Jun Liu
Chen Gao
Juncai Huang
author_sort Zhenqian Huang
collection DOAJ
description Predicting the deformation of surrounding rock is an important task to ensure the safety of mountain tunnel construction.This study, set against the backdrop of an actual under-construction tunnel, reconstructed the missing surrounding rock monitoring data using a Particle Swarm Optimization-based Least Squares Support Vector Regression model (PSO-LSSVR), and subsequently predicted the tunnel surrounding rock deformation using the constructed Gaussian Process Regression model (PSO-GPR).The research results indicate that the average relative error of the PSO-LSSVR reconstruction model is 1.21 %, lower than the 4.82 % of the LSSVR reconstruction model and the 4.69 % of the BP reconstruction model. The relative errors of the PSO-LSSVR prediction model and the BP prediction model are 0.55 % and 2.9 %, respectively, both higher than the PSO-GPR prediction model. The PSO-GPR model considers three covariance functions: the Squared Exponential function (SE), the Rational Quadratic function (RQ), and the Matern function (Matern), with relative errors of 0.16 %, 0.15 %, and 0.23 % in the test results, respectively. However, PSO-GPR-SE has a computational efficiency advantage.Overall, PSO-GPR-SE is a suitable model for predicting the deformation of surrounding rock during mountain tunnel construction.
format Article
id doaj-art-116fe79def534a5193d3411957475bc0
institution Kabale University
issn 2590-1230
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-116fe79def534a5193d3411957475bc02024-12-19T10:59:31ZengElsevierResults in Engineering2590-12302024-12-0124103445Reconstruction and prediction of tunnel surrounding rock deformation data based on PSO optimized LSSVR and GPR modelsZhenqian Huang0Zhen Huang1Pengtao An2Jun Liu3Chen Gao4Juncai Huang5School of Civil Engineering and Architecture, Guangxi University, Nanning 530004, PR ChinaSchool of Civil Engineering and Architecture, Guangxi University, Nanning 530004, PR China; Key Laboratory of Disaster Prevention and Structural Safety of Ministry of Education, Guangxi University, Nanning 530004, PR ChinaSchool of Civil Engineering and Architecture, Guangxi University, Nanning 530004, PR China; Key Laboratory of Disaster Prevention and Structural Safety of Ministry of Education, Guangxi University, Nanning 530004, PR China; Corresponding author.School of Civil Engineering and Architecture, Guangxi University, Nanning 530004, PR ChinaChina Construction Seventh Engineering Division.Corp.Ltd, Zhengzhou 450004, PR ChinaSchool of Civil Engineering and Architecture, Guangxi University, Nanning 530004, PR ChinaPredicting the deformation of surrounding rock is an important task to ensure the safety of mountain tunnel construction.This study, set against the backdrop of an actual under-construction tunnel, reconstructed the missing surrounding rock monitoring data using a Particle Swarm Optimization-based Least Squares Support Vector Regression model (PSO-LSSVR), and subsequently predicted the tunnel surrounding rock deformation using the constructed Gaussian Process Regression model (PSO-GPR).The research results indicate that the average relative error of the PSO-LSSVR reconstruction model is 1.21 %, lower than the 4.82 % of the LSSVR reconstruction model and the 4.69 % of the BP reconstruction model. The relative errors of the PSO-LSSVR prediction model and the BP prediction model are 0.55 % and 2.9 %, respectively, both higher than the PSO-GPR prediction model. The PSO-GPR model considers three covariance functions: the Squared Exponential function (SE), the Rational Quadratic function (RQ), and the Matern function (Matern), with relative errors of 0.16 %, 0.15 %, and 0.23 % in the test results, respectively. However, PSO-GPR-SE has a computational efficiency advantage.Overall, PSO-GPR-SE is a suitable model for predicting the deformation of surrounding rock during mountain tunnel construction.http://www.sciencedirect.com/science/article/pii/S2590123024016979Surrounding rock deformationData reconstructionPrediction modelPSO-LSSVRPSO-GPR
spellingShingle Zhenqian Huang
Zhen Huang
Pengtao An
Jun Liu
Chen Gao
Juncai Huang
Reconstruction and prediction of tunnel surrounding rock deformation data based on PSO optimized LSSVR and GPR models
Results in Engineering
Surrounding rock deformation
Data reconstruction
Prediction model
PSO-LSSVR
PSO-GPR
title Reconstruction and prediction of tunnel surrounding rock deformation data based on PSO optimized LSSVR and GPR models
title_full Reconstruction and prediction of tunnel surrounding rock deformation data based on PSO optimized LSSVR and GPR models
title_fullStr Reconstruction and prediction of tunnel surrounding rock deformation data based on PSO optimized LSSVR and GPR models
title_full_unstemmed Reconstruction and prediction of tunnel surrounding rock deformation data based on PSO optimized LSSVR and GPR models
title_short Reconstruction and prediction of tunnel surrounding rock deformation data based on PSO optimized LSSVR and GPR models
title_sort reconstruction and prediction of tunnel surrounding rock deformation data based on pso optimized lssvr and gpr models
topic Surrounding rock deformation
Data reconstruction
Prediction model
PSO-LSSVR
PSO-GPR
url http://www.sciencedirect.com/science/article/pii/S2590123024016979
work_keys_str_mv AT zhenqianhuang reconstructionandpredictionoftunnelsurroundingrockdeformationdatabasedonpsooptimizedlssvrandgprmodels
AT zhenhuang reconstructionandpredictionoftunnelsurroundingrockdeformationdatabasedonpsooptimizedlssvrandgprmodels
AT pengtaoan reconstructionandpredictionoftunnelsurroundingrockdeformationdatabasedonpsooptimizedlssvrandgprmodels
AT junliu reconstructionandpredictionoftunnelsurroundingrockdeformationdatabasedonpsooptimizedlssvrandgprmodels
AT chengao reconstructionandpredictionoftunnelsurroundingrockdeformationdatabasedonpsooptimizedlssvrandgprmodels
AT juncaihuang reconstructionandpredictionoftunnelsurroundingrockdeformationdatabasedonpsooptimizedlssvrandgprmodels