Rock strength assessment based on regression tree technique. (April 2016)

• Record Type: Journal Article
• Authors: Liang, Maybelle; Mohamad, Edy; Faradonbeh, Roohollah; Jahed Armaghani, Danial; Ghoraba, Saber
• Is Part Of: Engineering with computers. Volume 32:Number 2(2016)
• Page Start: 343
• Page End: 354
• Publication Date: 2016-04
• Subjects: Rock strength -- Sandstone -- Simple regression -- Multiple regression -- Regression tree; Engineering design -- Data processing -- Periodicals; Computer-aided design -- Periodicals; Conception technique -- Informatique -- Périodiques; Conception assistée par ordinateur -- Périodiques; Electronic journals; 620.00285
• DOI: 10.1007/s00366-015-0429-7
• Languages: English
• ISSNs: 0177-0667

Abstract

Abstract Uniaxial compressive strength (UCS) is one of the most important parameters for investigation of rock behaviour in civil and mining engineering applications. The direct method to determine UCS is time consuming and expensive in the laboratory. Therefore, indirect estimation of UCS values using other rock index tests is of interest. In this study, extensive laboratory tests including density test, Schmidt hammer test, point load strength test and UCS test were conducted on 106 samples of sandstone which were taken from three sites in Malaysia. Based on the laboratory results, some new equations with acceptable reliability were developed to predict UCS using simple regression analysis. Additionally, results of simple regression analysis show that there is a need to propose UCS predictive models by multiple inputs. Therefore, considering the same laboratory results, multiple regression (MR) and regression tree (RT) models were also performed. To evaluate performance prediction of the developed models, several performance indices, i.e. coefficient of determination (R 2 ), variance account for and root mean squared error were examined. The results indicated that the RT model can predict UCS with higher performance capacity compared to MR technique.R 2 values of 0.857 and 0.801 for training and testing datasets, respectively, suggests the superiority of the RT model in predicting UCS, while these values are obtained as 0.754 and 0.770 for MR model, respectively.