Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Application of QPSO-LSSVM in tunnel surrounding rocks deformation prediction
Predicting and analyzing tunnel surrounding rocks deformation is of great significance to the safe implementation of tunneling projects. In this paper, the QPSO-LSSVM algorithm is applied to the study of tunnel surrounding rocks deformation prediction, and case study and validation are conducted based on indicator-based data and time-series data. The results show that the QPSO-LSSVM algorithm outperforms the PSO-LSSVM as well as the LSSVM algorithm in the case analysis of indicator-based data, while the QPSO-LSSVM algorithm outperforms the seven methods of GM(l,l), ARIMA(l,l,l), BP neural network (BP), linear regression (LR), SVR, LSSVM, and PSO-LSSVM in the analysis of time-series data. Therefore, applying the QPSO-LSSVM algorithm to the tunnel surrounding rocks deformation prediction analysis is feasible and efficient. This provides new ideas for machine learning in the field of tunnel surrounding rocks deformation prediction.
Application of QPSO-LSSVM in tunnel surrounding rocks deformation prediction
Predicting and analyzing tunnel surrounding rocks deformation is of great significance to the safe implementation of tunneling projects. In this paper, the QPSO-LSSVM algorithm is applied to the study of tunnel surrounding rocks deformation prediction, and case study and validation are conducted based on indicator-based data and time-series data. The results show that the QPSO-LSSVM algorithm outperforms the PSO-LSSVM as well as the LSSVM algorithm in the case analysis of indicator-based data, while the QPSO-LSSVM algorithm outperforms the seven methods of GM(l,l), ARIMA(l,l,l), BP neural network (BP), linear regression (LR), SVR, LSSVM, and PSO-LSSVM in the analysis of time-series data. Therefore, applying the QPSO-LSSVM algorithm to the tunnel surrounding rocks deformation prediction analysis is feasible and efficient. This provides new ideas for machine learning in the field of tunnel surrounding rocks deformation prediction.
Application of QPSO-LSSVM in tunnel surrounding rocks deformation prediction
Yang, Jingsheng (Autor:in)
25.11.2022
572001 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Deformation evaluation on surrounding rocks of underground caverns based on PSO-LSSVM
| British Library Online Contents | 2017
Deformation evaluation on surrounding rocks of underground caverns based on PSO-LSSVM
| British Library Online Contents | 2017