A novel artificial intelligence technique for analyzing slope stability using PSO-CA model |
| |
Authors: | Luo Zhenyan Bui Xuan-Nam Nguyen Hoang Moayedi Hossein |
| |
Affiliation: | 1.School of Resources and Safety Engineering, Central South University, Changsha, 410083, China ;2.Department of Surface Mining, Mining Faculty, Hanoi University of Mining and Geology, 18 Vien Street, Duc Thang Ward, Bac Tu Liem District, Hanoi, Vietnam ;3.Center for Mining, Electro-Mechanical Research, Hanoi University of Mining and Geology, 18 Vien Street, Duc Thang Ward, Bac Tu Liem District, Hanoi, Vietnam ;4.Institute of Research and Development, Duy Tan University, Da Nang, 550000, Vietnam ;5.Department for Management of Science and Technology Development, Ton Duc Thang University, Ho Chi Minh City, Vietnam ;6.Faculty of Civil Engineering, Ton Duc Thang University, Ho Chi Minh City, Vietnam ; |
| |
Abstract: | This study aims to develop a new artificial intelligence model for analyzing and evaluating slope stability in open-pit mines. Indeed, a novel hybrid intelligent technique based on an optimization of the cubist algorithm by an evolutionary method (i.e., PSO), namely PSO-CA technique, was developed for predicting the factor of safety (FS) in slope stability; 450 simulations from the Geostudio software for the FS of a quarry mine (Vietnam) were used as the datasets for this aim. Five factors include bench height, slope angle, angle of internal friction, cohesion, and unit weight were used as the input variables for estimating FS in this work. To clarify the performance of the proposed PSO-CA technique in slope stability analysis, SVM, CART, and kNN models were also developed and assessed. Three performance indices, such as mean absolute error (MAE), root-mean-squared error (RMSE), and determination coefficient (R2), were computed to evaluate the accuracy of the predictive models. The results clarified that the proposed PSO-CA technique was the most dominant accuracy with an MAE of 0.009, RMSE of 0.025, and R2 of 0.981, in estimating the stability of slope. The remaining models (i.e., SVM, CART, kNN) obtained poorer performance with MAE from 0.014 to 0.038, RMSE 0.030–0.056, and R2 0.917–0.974. |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|