View in EDS

Modelling of Tensile Strength Ratio of Bituminous Concrete Mixes Using Support Vector Machines and M5 Model Tree.

Saved in:
Bibliographic Details
Title: Modelling of Tensile Strength Ratio of Bituminous Concrete Mixes Using Support Vector Machines and M5 Model Tree.
Authors: Goel, Gourav1 gouravgoelshinu@gmail.com, Sachdeva, S. N.1, Pal, Mahesh1
Source: International Journal of Pavement Research & Technology. Jan2022, Vol. 15 Issue 1, p86-97. 12p.
Subjects: Support vector machines, Tensile strength, Concrete mixing, Bituminous pavements, Bituminous materials, Radial basis functions, Pavement management
Abstract: 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. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Pavement Research & Technology is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract: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. [ABSTRACT FROM AUTHOR]
ISSN:19971400
DOI:10.1007/s42947-021-00013-5