A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Research on Rock Strength Prediction Based on Least Squares Support Vector Machine
Abstract In order to estimate the strength parameters of rock, as the direct method by conducting rock mechanical tests is time-consuming and expensive, an indirect method based on soft computing technique is proposed. Least squares support vector machine (LS-SVM) is utilized to develop rock uniaxial compressive strength (UCS) and shear strength (SS) prediction models by considering indirect parameters such as rock density, point load strength, P-wave velocity and slake durability index. The results show that according to the rock physical and mechanical parameters of four rock types, empirical relationships based on statistical regression method are rock type specific, only linear relations existed between point load strength and rock strengths are acceptable with high determination coefficients for whole rock types. The LS-SVM models built for rock UCS and SS prediction have greater determination coefficients than the regression models. The prediction values based on LS-SVM prediction models for rock UCS and SS are both extremely close to the measured values, which indicates the applicability of LS-SVM is supported for estimation of strength parameters of rock.
Research on Rock Strength Prediction Based on Least Squares Support Vector Machine
Abstract In order to estimate the strength parameters of rock, as the direct method by conducting rock mechanical tests is time-consuming and expensive, an indirect method based on soft computing technique is proposed. Least squares support vector machine (LS-SVM) is utilized to develop rock uniaxial compressive strength (UCS) and shear strength (SS) prediction models by considering indirect parameters such as rock density, point load strength, P-wave velocity and slake durability index. The results show that according to the rock physical and mechanical parameters of four rock types, empirical relationships based on statistical regression method are rock type specific, only linear relations existed between point load strength and rock strengths are acceptable with high determination coefficients for whole rock types. The LS-SVM models built for rock UCS and SS prediction have greater determination coefficients than the regression models. The prediction values based on LS-SVM prediction models for rock UCS and SS are both extremely close to the measured values, which indicates the applicability of LS-SVM is supported for estimation of strength parameters of rock.
Research on Rock Strength Prediction Based on Least Squares Support Vector Machine
Li, Wen (author) / Tan, Zhuoying (author)
2016
Article (Journal)
English
Research on Rock Strength Prediction Based on Least Squares Support Vector Machine
| British Library Online Contents | 2017
Research on Rock Strength Prediction Based on Least Squares Support Vector Machine
| Online Contents | 2016
Forest Coverage Prediction Based on Least Squares Support Vector Regression Algorithm
| British Library Conference Proceedings | 2012