A novel intelligent displacement prediction model of karst tunnels

Fu, Haiying; Zhao, Yanyan; Ding, Haojiang; Rao, Yunkang; Yang, Tao; Zhou, Ming-zhe

doi:10.1038/s41598-022-21333-x

Cited by 1 publication

(1 citation statement)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The third method for obtaining friction factor α is by consulting empirical handbooks [28]- [31]. However, with the rapid development of mining technology, changes have occurred in roadway cross-section dimensions, support types, and roadway infrastructure.…”

Section: Introductionmentioning

confidence: 99%

Forecasting the Friction Factor of a Mine Airway Using an Improvement Stacking Ensemble Learning Approach

Qi,

Gao,

Obracaj

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The prediction of frictional air resistance using the inherent properties of roadways is of great significance for ventilation network computation and flow regulation in underground mines. This study proposes an improved stacked learning and error correction-based prediction model for the frictional air resistance of mine airways, called friction factor. A prediction set is established by selecting ten factors, including tunnel spatial features and support forms, with the ventilation resistance coefficient as the label. The improved stacked model consists of two layers. The first layer is the base learning module, which is composed of four components: Principal Components Analysis and Back Propagation (PCA-BP), GA-Projection Pursuit Regression (GA-PPR), Random Forest (RF), LightGBM (LGBM). The second layer is the meta-learning module, which is composed of the Ridge Regression (RR). Compared to traditional stacked models, the improved model first uses the Extreme Gradient Boosting (XG Boost) learner to evaluate the significance of input feature variables to eliminate redundancy and improve accuracy, thus enhancing prediction precision and computational efficiency. Then, the first-layer prediction results are weighted based on the errors of different prediction models in the training set using K-fold cross-validation. Box-Cox transformation is applied to the training set data from the first layer to the second layer to improve prediction normality and homogeneity. The error correction prediction model extracts the historical prediction errors from the meta-learning module and constructs an error prediction model using support vector machines (SVR), which are then combined with the meta-learning results to obtain the final prediction. The improved stacked model is compared with traditional ensemble learning models and single prediction models, and quantified using three metrics: root mean square error (RMSE), mean absolute error (MAE), and R-squared (R 2 ). The results demonstrate that the proposed improved model effectively enhances the prediction accuracy of the ensemble learning models, providing a new prediction method for the accurate acquisition of the friction factor of mine airways.

show abstract

Section: Introductionmentioning

confidence: 99%