Abstract
Accurately predicting the stability of complex high rock slopes is crucial to prevent infrastructure damage and potential casualties. Existing studies have primarily relied on linear or log-linear regression models based on laboratory data, limiting their practical application. In this study focused on the Jelapang rock slope in Perak, a multidisciplinary approach combining geological, geotechnical, and remote sensing analyses was employed to consider various rock mass properties and slope geometrical parameters. The Rock Mass Rating (RMR), Slope Mass Rating (SMR), and factor of safety (FOS) were computed for 48 regions of the rock slope. Subsequently, a Radial Basis Function Neural Network (RBFNN) model was utilised to predict the FOS, RMR, and SMR. Three RBFs were developed: RBF-1 for estimating the factor of safety, RBF-2 for rock mass rating, and RBF-3 for slope mass rating. For comparison purposes, the performance of the RBFNN models was compared with Multilayer Perceptron (MLP) models. The results demonstrated that the optimised RBFNN model provided a state-of-the-art technique for accurately predicting and controlling slope stability. Notably, the RBFNN models exhibited remarkable precision, as indicated by root-mean-squared error (RMSE) values of 2.02172e-30 for the training process of RBF-1, 7.58671e-28 for RBF-2, and 2.71129e-27 for RBF-3. Comparison results revealed that the RBF models outperformed the MLPs. Additionally, sensitivity analysis results indicated that Uniaxial Compressive Strength (UCS) had the highest effect on the FOS.
Published Version
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 call