Abstract
A simple and accurate evaluation method of broken rock zone thickness (BRZT), which is usually used to describe the broken rock zone (BRZ), is meaningful, due to its ability to provide a reference for the roadway stability evaluation and support design. To create a relationship between various geological variables and the broken rock zone thickness (BRZT), the multiple linear regression (MLR), artificial neural network (ANN), Gaussian process (GP) and particle swarm optimization algorithm (PSO)-GP method were utilized, and the corresponding intelligence models were developed based on the database collected from various mines in China. Four variables including embedding depth (ED), drift span (DS), surrounding rock mass strength (RMS) and joint index (JI) were selected to train the intelligence model, while broken rock zone thickness (BRZT) is chosen as the output variable, and the k-fold cross-validation method was applied in the training process. After training, three validation metrics including variance account for (VAF), determination coefficient (R2) and root mean squared error (RMSE) were applied to describe the predictive performance of these developed models. After comparing performance based on a ranking method, the obtained results show that the PSO-GP model provides the best predictive performance in estimating broken rock zone thickness (BRZT). In addition, the sensitive effect of collected variables on broken rock zone thickness (BRZT) can be listed as JI, ED, DS and RMS, and JI was found to be the most sensitive factor.
Highlights
After the excavation of the tunnel, the original stress balance of the rock mass around the roadway was destroyed, which leads to the redistribution of original stress and has an impact on the surrounding underground structures including surrounding rock mass and surrounding filling bodies [1,2,3]
The results show that the Gaussian process model can provide the predictive performance with variance account for (VAF) of 90.4209, R2 of 0.9051 and root mean squared error (RMSE) of 0.1798 for training datasets and VAF of 86.7895, R2 of 0.8900 and RMSE of 0.1733 for testing datasets, and the actual broken rock zone thickness (BRZT)
Before using the particle swarm optimization algorithm (PSO) to find the hyper-parameter of the Gaussian process (GP) model for achieving the best predictive performance, several parameters including the number of particles and the maximum number of iterations of PSO should be defined by the user
Summary
After the excavation of the tunnel, the original stress balance of the rock mass around the roadway was destroyed, which leads to the redistribution of original stress and has an impact on the surrounding underground structures including surrounding rock mass and surrounding filling bodies [1,2,3]. Proposed a broken rock zone predictive formula based on the indoor test and filed experience These formulas can be used to predict the broken rock zone thickness (BRZT), only a few factors are considered, a few engineering sites have been verified, and it is hard to be applied in the complex engineering environment. Some artificial intelligence models were applied in the roadways broken rock zone (BRZ) prediction, the application of the Gaussian process (GP) was not analyzed, the effect of various factors on the broken rock zone thickness (BRZT) was not conducted. The Gaussian process (GP) method was selected to predict the broken rock zone thickness (BRZT) in this study, the PSO algorithm was utilized to search the optimal hyper-parameter combination for optimal predictive performance, and a sensitivity analysis was carried out to find the most sensitive factor in the present paper
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
