No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Stiffness performance of polyethylene terephthalate modified asphalt mixtures estimation using support vector machine-firefly algorithm
Abstract
Predicting asphalt pavement performance is an important matter which can save cost and energy. To ensure an accurate estimation of performance of the mixtures, new soft computing techniques can be used. In this study, in order to estimate the stiffness property of Polyethylene Terephthalate (PET) modified asphalt mixture, different soft computing methods were developed, namely: support vector machine-firefly algorithm (SVM-FFA), genetic programming (GP), artificial neural network (ANN) and support vector machine. The support vector machine-firefly algorithm (SVM-FFA) is a metaheuristic search algorithm developed according to the socially dashing manners of fireflies in nature. To develop the models, experiments were performed. The process, which simulates the mixtures' stiffness, was created with a soft computing method, the inputs being PET percentages, stress levels and environmental temperatures. The performance of the proposed system was confirmed by the simulation results. Soft computing methodologies show very good learning and prediction capabilities and the results obtained in this study indicate that the SVM-FFA contributed the most significant effect on stiffness performance estimation since the SVM-FFA model had a better correlation coefficient than the SVM, ANN and GP approaches. R-2 and RMSE were utilized for making comparisons between the expected and actual values of SVM-FFA, GP, ANN and SVM. The proposed SVM-FFA methodology predicted the output values with 254.4743 (mm/day) and 0.9957 RMSE and R-2 respectively. (C) 2014 Elsevier Ltd. All rights reserved.
Dear readers,
If you like to have the full paper, please send an email request to pejtdr_fkej@um.edu.my. We will email the paper to you. Thank You.
... Then the fatigue and rutting lives can be estimated with respect to critical strain values. Artificial intelligence (AI) techniques, such as, Artificial Neural Networks (ANN), Fuzzy Logic (FL), Genetic Algorithm (GA), Support Vector Machines (SVM) or hybrid methods of these techniques are successfully used to solve complex problems associated with Pavement engineering[Goktepe, Agar and Lav, 2006;Maalouf et al. 2008;Gopalakrishnan and Kim 2010;Lin and Liu, 2010;Patil, Mandal and Hegde, 2012;Terzi 2013;Gopalakrishnan et al. 2013;Fakhri and Ghanizadeh 2014;Soltani et al 2015]. If we can determine the critical responses of pavement using AI techniques, it is possible to increase the speed of pavement analysis several times faster than that of analysis using software ...
This paper aims to assess the application of Support Vector Machine (SVM) regression in order to analysis flexible pavements. To this end, 10000 Four-layer flexible pavement sections consisted of asphalt concrete layer, granular base layer, granular subbase layer, and subgrade soil were analyzed under the effect of standard axle loading using multi-layered elastic theory and pavement critical responses including maximum tensile strain at the bottom of asphalt layer and maximum compressive strain at the top of subgrade soil were calculated. Then the support vector machine regression was used to predict these two critical responses. Results of this study show that the SVM can be used as a reliable tool to predict critical responses of flexible pavements. Analysis of flexible pavements using SVM needs less computing time and the SVM can be used as a quick tool for predicting fatigue and rutting lives of different pavement sections in comparison with multi-layer elastic theory and finite element method.
This paper presents the effects of different amounts of steel fibre on the volumetric properties of stone mastic asphalt (SMA) mixtures. Central composite design (CCD) method was used to design the experiments based on the response surface method (RSM) using Design Expert Software. Steel fibre (SF) content (0.3, 0.5 and 0.7%), degree of compaction (%) and stiffness (kg/mm) were selected as independent variables, while bulk specific gravity, Marshall stability, flow and air void of asphalt mixtures were chosen as dependent variables. In this research study, volumetric properties of SMA mixtures were measured by using Marshall Mix Design. The RSM analyses showed that all independent variables were significant factors for influencing the volumetric properties of the mixtures. In addition, analysis of the test results showed that the mixtures containing 0.3% steel fibre are the most optimum value to be used as a modifier in the SMA mixture. Furthermore, the developed models between the independent and dependent variables demonstrated acceptable levels of correlation. It was concluded that optimization using RSM is an effective approach for providing an appropriate empirical model for relating parameters and predicting the optimum performance of an asphaltic mixture.
ResearchGate has not been able to resolve any references for this publication.