Prediction of the uniaxial compressive strength of sandstone using various modeling techniques. (May 2016)

• Record Type: Journal Article
• Authors: Jahed Armaghani, Danial; Mohd Amin, Mohd For; Yagiz, Saffet; Faradonbeh, Roohollah Shirani; Abdullah, Rini Asnida
• Is Part Of: International journal of rock mechanics and mining sciences. Volume 85(2016:May)
• Page Start: 174
• Page End: 186
• Publication Date: 2016-05
• Subjects: Uniaxial compressive strength -- Artificial neural network -- Imperialist competitive algorithm -- Non-destructive tests -- Point load index; Rock mechanics -- Periodicals; Soil mechanics -- Periodicals; Mining engineering -- Periodicals; Roches, Mécanique des -- Périodiques; Sols, Mécanique des -- Périodiques; Technique minière -- Périodiques; 624.151305
• DOI: 10.1016/j.ijrmms.2016.03.018
• Languages: English
• ISSNs: 1365-1609

Abstract

Abstract: Sandstone blocks were collected from Dengkil site in Malaysia and brought to laboratory, and then intact samples prepared for testing. Rock tests, including Schmidt hammer rebound number, P-wave velocity, point load index, and UCS were conducted. The established dataset is composed of 108 cases. Consequently, the established dataset was utilized for developing the simple regression, linear, non-linear multiple regressions, artificial neural network, and a hybrid model, developed by integrating imperialist competitive algorithm with ANN. After performing the relevant models, several performance indices i.e. root mean squared error, coefficient of determination, variance account for, and total ranking, are examined for selecting the best model and comparing the obtained results. It is obtained that the ICA–ANN model is superior to the others. It is concluded that the hybrid of ICA–ANN could be used for predicting UCS of similar rock type in practice. Graphical abstract: After performing the relevant models, several performance indices including the coefficient of determination ( R 2 ), root mean squared error (RMSE) and value account for (VAF) and total ranking are examined for selecting the best model. It is obtained that the ICA–ANN model is superior to others in terms of R 2, RMSE, VAF and ranking herein. Highlights: We measured several rock index parameters of sandstone as well as their UCS. Several LMR and NLMR models were developed for prediction of UCS. Two intelligent systems i.e., ANN and ICA–ANN were developed to predict UCS. A comparison between models was made to select the best UCS predictive model.