Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Modelling of Tensile Strength Ratio of Bituminous Concrete Mixes Using Support Vector Machines and M5 Model Tree
https://orcid.org/http://orcid.org/0000-0002-1335-8111
Bituminous pavements are greatly vulnerable to moisture damage. Most of the studies all over the world conclude that presence of moisture on road surface contributes significantly to pavement failures. Sustainable bituminous pavement needs high quality bitumen material. In roadway design, the tensile strength of bituminous pavements is an important engineering property. Indirect tensile strength (ITS) tests are performed on bituminous mixes for evaluating tensile strength ratio (TSR). Knowledge of TSR is helpful in determining the moisture susceptibility of bituminous concrete (BC) mixes for highway pavements. In the past different modelling techniques were developed to predict the TSR of bituminous mixes. In this study, support vector machines (SVM), M5 model tree and regression-based technique were used to estimate the TSR value of BC mixes. Two kernel functions, i.e. polynomial and radial-based kernel function were used with SVM model. Cross validation technique with 10-fold analysis was used for testing the models. SVM model with radial basis function (RBF) outclasses M5P model all in terms of correlation coefficient and R2 values. This paper proposes a simple linear equation for the prediction of the TSR, which is based on ITS tests performed on different types of bituminous mixes.
Modelling of Tensile Strength Ratio of Bituminous Concrete Mixes Using Support Vector Machines and M5 Model Tree
https://orcid.org/http://orcid.org/0000-0002-1335-8111
Bituminous pavements are greatly vulnerable to moisture damage. Most of the studies all over the world conclude that presence of moisture on road surface contributes significantly to pavement failures. Sustainable bituminous pavement needs high quality bitumen material. In roadway design, the tensile strength of bituminous pavements is an important engineering property. Indirect tensile strength (ITS) tests are performed on bituminous mixes for evaluating tensile strength ratio (TSR). Knowledge of TSR is helpful in determining the moisture susceptibility of bituminous concrete (BC) mixes for highway pavements. In the past different modelling techniques were developed to predict the TSR of bituminous mixes. In this study, support vector machines (SVM), M5 model tree and regression-based technique were used to estimate the TSR value of BC mixes. Two kernel functions, i.e. polynomial and radial-based kernel function were used with SVM model. Cross validation technique with 10-fold analysis was used for testing the models. SVM model with radial basis function (RBF) outclasses M5P model all in terms of correlation coefficient and R2 values. This paper proposes a simple linear equation for the prediction of the TSR, which is based on ITS tests performed on different types of bituminous mixes.
Modelling of Tensile Strength Ratio of Bituminous Concrete Mixes Using Support Vector Machines and M5 Model Tree
https://orcid.org/http://orcid.org/0000-0002-1335-8111
Bituminous pavements are greatly vulnerable to moisture damage. Most of the studies all over the world conclude that presence of moisture on road surface contributes significantly to pavement failures. Sustainable bituminous pavement needs high quality bitumen material. In roadway design, the tensile strength of bituminous pavements is an important engineering property. Indirect tensile strength (ITS) tests are performed on bituminous mixes for evaluating tensile strength ratio (TSR). Knowledge of TSR is helpful in determining the moisture susceptibility of bituminous concrete (BC) mixes for highway pavements. In the past different modelling techniques were developed to predict the TSR of bituminous mixes. In this study, support vector machines (SVM), M5 model tree and regression-based technique were used to estimate the TSR value of BC mixes. Two kernel functions, i.e. polynomial and radial-based kernel function were used with SVM model. Cross validation technique with 10-fold analysis was used for testing the models. SVM model with radial basis function (RBF) outclasses M5P model all in terms of correlation coefficient and R2 values. This paper proposes a simple linear equation for the prediction of the TSR, which is based on ITS tests performed on different types of bituminous mixes.
Modelling of Tensile Strength Ratio of Bituminous Concrete Mixes Using Support Vector Machines and M5 Model Tree
Int. J. Pavement Res. Technol.
Goel, Gourav (Autor:in) / Sachdeva, S. N. (Autor:in) / Pal, Mahesh (Autor:in)
01.01.2022
12 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Modelling Concrete Strength Using Support Vector Machines
| British Library Conference Proceedings | 2013
Bituminous concrete mixes : 6 reports
| TIBKAT | 1967
Plant control of bituminous concrete mixes
| Engineering Index Backfile | 1956
Strength Characteristics of Bituminous Mixes Using Modified Binders
| British Library Conference Proceedings | 2000
Characterization of Fly Ash Bituminous Concrete Mixes
| Online Contents | 2010