Attitude-Predictive Control of Large-Diameter Shield Tunneling: PCA-SVR Machine Learning Algorithm Application in a Case Study of the Zhuhai Xingye Express Tunnel DOI Creative Commons
Hui Li,

Yijun Tan,

Decheng Zeng

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(4), P. 1880 - 1880

Published: Feb. 12, 2025

In order to realize effective attitude-predictive control during large-diameter shield tunneling, this study established an intelligent framework for attitude prediction. Specifically, a principal component analysis–support vector regression (PCA-SVR) hybrid model was constructed, based on analysis. The analysis method used mine the relevant input parameters and reduce accompanying data noise. SVR statistical learning structural risk minimization overcome overfitting. Taking tunnel, Zhuhai Xingye Express Tunnel, as example, proposed PCA-SVR validated by considering tunnel excavation parameters, geometric geological parameters. At same time, correlation coefficient analyze relationship between results show that propulsion cylinder pressure is important factor affecting trajectory of motion. geometrical have strong with predicted are within range corresponding monitoring data. high prediction accuracy verifies can accurately predict tunneling. be reference attitude-prediction shields in similar projects.

Language: Английский

Attitude-Predictive Control of Large-Diameter Shield Tunneling: PCA-SVR Machine Learning Algorithm Application in a Case Study of the Zhuhai Xingye Express Tunnel DOI Creative Commons
Hui Li,

Yijun Tan,

Decheng Zeng

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(4), P. 1880 - 1880

Published: Feb. 12, 2025

In order to realize effective attitude-predictive control during large-diameter shield tunneling, this study established an intelligent framework for attitude prediction. Specifically, a principal component analysis–support vector regression (PCA-SVR) hybrid model was constructed, based on analysis. The analysis method used mine the relevant input parameters and reduce accompanying data noise. SVR statistical learning structural risk minimization overcome overfitting. Taking tunnel, Zhuhai Xingye Express Tunnel, as example, proposed PCA-SVR validated by considering tunnel excavation parameters, geometric geological parameters. At same time, correlation coefficient analyze relationship between results show that propulsion cylinder pressure is important factor affecting trajectory of motion. geometrical have strong with predicted are within range corresponding monitoring data. high prediction accuracy verifies can accurately predict tunneling. be reference attitude-prediction shields in similar projects.

Language: Английский

Citations

1