Research on Rock Strength Prediction Based on Least Squares Support Vector Machine

详细信息    查看全文

• 作者：Wen Li ; Zhuoying Tan
• 关键词：Uniaxial compressive strength (UCS) ; Shear strength (SS) ; Prediction model ; Soft computing technique ; Least squares support vector machine (LS ; SVM)
• 刊名：Geotechnical and Geological Engineering
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：35
• 期：1
• 页码：385-393
• 全文大小：
• 刊物类别：Earth and Environmental Science
• 刊物主题：Geotechnical Engineering & Applied Earth Sciences; Hydrogeology; Terrestrial Pollution; Waste Management/Waste Technology; Civil Engineering;
• 出版者：Springer International Publishing
• ISSN：1573-1529
• 卷排序：35

文摘

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.