@Article{cmes.2023.025714,
AUTHOR = {Yuxin Chen, Weixun Yong, Chuanqi Li, Jian Zhou},
TITLE = {Predicting the Thickness of an Excavation Damaged Zone around the Roadway Using the DA-RF Hybrid Model},
JOURNAL = {Computer Modeling in Engineering \& Sciences},
VOLUME = {136},
YEAR = {2023},
NUMBER = {3},
PAGES = {2507--2526},
URL = {http://www.techscience.com/CMES/v136n3/51804},
ISSN = {1526-1506},
ABSTRACT = {After the excavation of the roadway, the original stress balance is destroyed, resulting in the redistribution of stress
and the formation of an excavation damaged zone (EDZ) around the roadway. The thickness of EDZ is the key
basis for roadway stability discrimination and support structure design, and it is of great engineering significance
to accurately predict the thickness of EDZ. Considering the advantages of machine learning (ML) in dealing with
high-dimensional, nonlinear problems, a hybrid prediction model based on the random forest (RF) algorithm is
developed in this paper. The model used the dragonfly algorithm (DA) to optimize two hyperparameters in RF,
namely mtry and ntree, and used mean absolute error (MAE), root mean square error (RMSE), determination coefficient (R<sup>2</sup>), and variance accounted for (VAF) to evaluate model prediction performance. A database containing 217
sets of data was collected, with embedding depth (<i>ED</i>), drift span (<i>DS</i>), surrounding rock mass strength (<i>RMS</i>),
joint index (<i>JI</i>) as input variables, and the excavation damaged zone thickness (<i>EDZT</i>) as output variable. In
addition, four classic models, back propagation neural network (BPNN), extreme learning machine (ELM), radial
basis function network (RBF), and RF were compared with the DA-RF model. The results showed that the DARF mold had the best prediction performance (training set: MAE = 0.1036, RMSE = 0.1514, R<sup>2</sup> = 0.9577, VAF
= 94.2645; test set: MAE = 0.1115, RMSE = 0.1417, R<sup>2</sup> = 0.9423, VAF = 94.0836). The results of the sensitivity
analysis showed that the relative importance of each input variable was <i>DS</i>, <i>ED</i>, <i>RMS</i>, and <i>JI</i> from low to high.},
DOI = {10.32604/cmes.2023.025714}
}