Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Acta Geophysica

Powiadomienia systemowe

Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Assessment of rock geomechanical properties and estimation of wave velocities

Guo Shaoqiang, Zhang Yao, Iraji Amin, Gharavi Hoorman, Deifalla Ahmed Farouk

Acta Geophysica

2023

Vol. 71, no. 2

649--670

Wave velocity is used to determine rock material, porosity, degree of petrification, fluid type, and mechanical and behavioral properties. In this study, after assessing the relationship between the static elastic modulus (Es) and the dynamic elastic modulus (Ed), various models using statistical and intelligent methods were presented for predicting shear wave velocity (Vs) and compressional wave velocity (Vp) based on porosity (P), Brazilian tensile strength (BTS), density (D), point load index (PLI), and water absorption (A) of sedimentary rocks. The Vp and Vs were estimated using simple and multiple regression, back-propagation artificial neural network (BPANN), support vector regression (SVR), and adaptive neuro-fuzzy inference system (ANFIS) methods. The examination of necessary assumptions of the models such as analysis of variance (ANOVA), variance inflation factor (VIF), mean absolute percentage error (MAPE), root-mean-square error (RMSE), variance accounted for (VAF), and independence of errors showed the high accuracy of the obtained model using multiple linear regression. The SVR approach using the radial basis kernel function with R2=100% and 99% showed the best accuracy in estimating Vs and Vp, respectively. The average ratio of Ed/Es, dynamic-to-static Poisson ratio ( νd∕νs ) , and Vp/Vs were obtained as 2.52, 2.92, and 2.82, respectively. The most accurate relationship between Ed and Es was developed in the form of a power function with R2=0.88.

Estimation of dynamic properties of sandstones based on index properties using artifcial neural network and multivariate linear regression methods

Alizadeh Sayed Mehdi, Iraji Amin, Tabasi Somayeh, Ahmed Alim Al Ayub, Motahari Mohammad Reza

Acta Geophysica

2022

Vol. 70, no 1

225--242

The dynamic properties of the rock are very important for the design of geotechnical structures and the modeling of deep drilling. In the present study, the velocity of compressional and shear waves (Vp and Vs) and the dynamic elastic modulus (Ed) of sandstones were estimated based on index tests using artificial neural network (ANN) and multivariate linear regression analysis (MVLRA) methods. For this purpose, petrographic, physical, mechanical and dynamic tests were performed on 54 specimens. Petrographic results showed that the samples were classified as feldspathic litharenite. The results showed that the Vp/Vs ratio was equal to 1.78. Also, the effect of mineralogy on mechanical properties was more than dynamic properties and the effect of quartz on dynamic properties was more than other minerals. The presented relationships were evaluated using R-squared (R2 ), root-mean-square error (RMSE), mean absolute relative prediction error (MARPE), variance account for (VAF) and performance index (PI). The results of the ANN to estimate the Ed, Vp and Vs showed that it is possible to estimate these parameters based on inputs with high accuracy. The accuracy of the ANN was higher than the MVLRA. Estimation of Vs, Vp and Ed by ANN showed correlation coefficients of 0.97, 0.86 and 0.92 and RMSE of 0.10, 0.31, and 3.98, respectively. The ANN was also conservative in predicting these variables, while MVLRA was conservative only in estimating the Vs and Ed of the studied sandstones.