Litcius/Paper detail

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

Zhenqian Huang, Zhen Huang, Pengtao An, Jun Liu, Chen Gao, Juncai Huang

2024Results in Engineering19 citationsDOIOpen Access PDF

Abstract

• By optimizing the hyper-parameters of least squares support vector regression using particle swarm optimization, we constructed the PSO-LSSVR model for the reconstruction of missing monitoring data during tunnel construction. • By optimizing the hyper-parameters of Gaussian process regression using particle swarm optimization, we constructed the PSO-GPR model for the prediction of surrounding rock deformation in tunnels. • This study achieved the goal of predicting surrounding rock deformation even with partial missing monitoring data through the constructed PSO-LSSVR reconstruction model and PSO-GPR prediction model. 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.

Topics & Concepts

Ground-penetrating radarDeformation (meteorology)Support vector machineArtificial intelligenceComputer scienceGeologyPredictive modellingDeformation monitoringGeotechnical engineeringMachine learningData miningRadarTelecommunicationsOceanographyRock Mechanics and ModelingGeoscience and Mining TechnologyLandslides and related hazards
Reconstruction and prediction of tunnel surrounding rock deformation data based on PSO optimized LSSVR and GPR models | Litcius