The use of SVM-FFA in estimating fatigue life of polyethylene terephthalate modified asphalt mixtures
Introduction
Deterioration in the asphalt pavement service life has been identified as a result of an increase in weight as well as excessive usage of heavy vehicles. Two design solutions have been proposed for this problem: first is to employ a thicker pavement layer which is not a cost effective solution and second is modifying the characteristics of asphalt mixture which can potentially be more cost effective when compared to constructing a thicker pavement layer [1].
Due to potentially lower construction cost of pavement structure with modified characteristics when compared to thicker pavement, the strategy gained interest by pavement engineers and practitioners. There have been previous studies attempting to evaluate various performance measures of modified pavement mixtures [2], [3], [4], [5], [6], [7]. Researchers have recently focused on using reusable modifier for modified pavement mixture as using virgin materials to improve the characteristic makes the final product more costly which is not of interest to practitioners [8], [9], [10], [11], [12], [13], [14].
To avoid costly test used for determining pavement performance, one might resort to using soft computing-based prediction techniques. These techniques are capable of learning the relationship between inputs and outputs from a limited set of known data and predict the outputs for an input for which they are not trained on.
One of the novel soft computing learning algorithms is support vector machine (SVM) that has recently found wide application in the field of computing, hydrology and environmental researches [15], [16], [17], [18], [19]. Further, it majorly has been used in, forecasting, pattern recognition, regression analysis and classification [26], [27], [28] and its application has proven its superiority over other conventional statistical models e.g. neural network [20], [21], [22], [23], [24], [25]. In the study of Liu et al. [29], soft computing based methods were employed to deal with early construction warning system. The methods were association rule mining, support vector machine classifiers, and variable fuzzy qualitative and quantitative change criterion modes. The results of the study showed that the methods can be used together to provide a safe construction early warning system. In another application Zhou et al. [30] developed a cluster-in-cluster firefly algorithm and applied that to wired and wireless sensor placement problems for structural health monitoring. It was concluded that the proposed method performs more accurately and efficiently compared to Genetic Algorithm (GA) approach.
In this study, a prediction model is developed to predict the fatigue life of unmodified and modified asphalt mixtures using SVM coupled with Firefly Algorithm (FFA). Polyethylene Terephthalate (PET) which has been obtained from waste PET bottles was used as modifier. The prediction accuracy of SVM-FFA is compared with that of ANN and Genetic Algorithm (GA).
Section snippets
Application of soft computing-based approaches in pavement engineering
This section of the paper attempts to review the previous conducted studies on soft computing based techniques in pavement engineering.
Bianchini and Bandini [31] used a neuro-fuzzy model to predict the performance of flexible pavement given the falling weight deflectometer tests’ parameters; these parameters are mostly provided by agencies for pavement performance evaluation. The neuro-fuzzy method was found to be leading to satisfactory results efficiently. Another use of fuzzy logic for
Materials
The penetration grade for asphalt mixtures is set to be 80/100. In this research, Granite-rich aggregate particles are used. Several experiments are conducted on the aggregate particles and asphalt cement to get familiar with the characteristics of the test materials; the results of the experiments are summarized in Table 1.
In this research, waste PET bottles are used in the mixture of modified asphalt. A crushing machine is used to transform the waste PET bottle flakes into small particles so
Performance analysis
To check the benefits of the proposed SVM-FFA method, its performance is compared with that of other commonly used soft computing based methods such as ANN, GA, and SVM. The development of the traditional methods to which the performance of the proposed method is compared, are briefly described in this section. Next, the performance comparisons of the proposed method with those of the traditional methods are presented.
As mentioned before, the performance of the SVM technique is very sensitive
Conclusions
This study focused on presenting an application of SVM-FFA method for prediction of fatigue life of PET modified asphalt mixtures given PET percentages, stress levels and environmental temperatures as inputs to the model. SVM-FFA is different from other commonly used methods (ANN and GP) in their objective; SVM-FFA focuses on structural minimization in its learning process while other methods focus on minimization of error between observed and predicted outputs. Statistical measures are
Acknowledgement
This research is supported by University of Malaya under UMRG grant (Project no. RP036B-15AET: Measurement of the Flood Waste Volume based on the Digital Image).
References (50)
- et al.
The effect of waste tire thread mesh on the dynamic behaviour of asphalt mixtures
Constr. Build. Mater.
(2010) - et al.
Investigation of the dynamic and fatigue properties of fiber-modified asphalt mixtures
Int. J. Fatigue
(2009) - et al.
Evaluation of permanent deformation of unmodified and SBS modified asphalt mixtures using dynamic creep test
Constr. Build. Mater.
(2009) - et al.
Investigation of rutting performance of asphalt mixtures containing polymer modifiers
Constr. Build. Mater.
(2007) - et al.
Laboratory performance comparison of the elastomer-modified asphalt mixtures
Build. Environ.
(2008) - et al.
Use of waste high density polyethylene as bitumen modifier in asphalt concrete mix
J. Mater. Lett.
(2004) - et al.
Development of a recycled polymer modified binder for use in stone mastic asphalt
J. Resour. Conserv. Recy.
(2008) - et al.
The effect of waste tire thread mesh on the dynamic behaviour of asphalt mixtures
J. Constr. Build. Mater.
(2010) - et al.
Experimental investigation of the fatigue behaviour of asphalt concrete mixtures containing waste iron powder
J. Mater. Sci. Eng. A – Struct.
(2011) - et al.
Using waste plastic bottles as additive for stone mastic asphalt
J. Mater. Des.
(2011)
Potential assessment of the “support vector machine” method in forecasting ambient air pollutant trends
Chemosphere
Multi-time scale stream flow predictions: the support vector machines approach
J. Hydrol.
Multitask multiclass support vector machines: model and experiments
Pattern Recogn.
Safety early warning research for highway construction based on case-based reasoning and variable fuzzy sets
Sci. World J.
Fuzzy logic and statistical-based modelling of the Marshall Stability of asphalt concrete under varying temperatures and exposure times
Adv. Eng. Softw.
Adaptive neuro-fuzzy inference approach for prediction the stiffness modulus on asphalt concrete
Adv. Eng. Softw.
Artificial neural network based modelling of the Marshall Stability of asphalt concrete
Expert Syst. Appl.
Neural network model for resilient modulus of emulsified asphalt mixtures
Constr. Build. Mater.
Prediction of Marshall test results for polypropylene modified dense bituminous mixtures using neural networks
Expert Syst. Appl.
Permanent deformation analysis of asphalt mixtures using soft computing techniques
Expert Syst. Appl.
Stiffness performance of polyethylene terephthalate modified asphalt mixtures estimation using support vector machine-firefly algorithm
Measurement
An experimental study on fatigue properties of emulsion and foam cold recycled mixes
Constr. Build. Mater.
Support vector regression methodology for storm surge predictions
Ocean Eng.
Localized support vector regression for time series prediction
Neurocomputing
Choosing the kernel parameters for support vector machines by the inter-cluster distance in the feature space
Pattern Recogn.
Cited by (30)
Viscoelastic fracture mechanics-based fatigue life model in asphalt-filler composite system
2023, Engineering Fracture MechanicsA boom damage prediction framework of wheeled cranes combining hybrid features of acceleration and Gaussian process regression
2023, Measurement: Journal of the International Measurement ConfederationAutomatic pavement damage predictions using various machine learning algorithms: Evaluation and comparison
2022, Results in EngineeringA new cyclical generative adversarial network based data augmentation method for multiaxial fatigue life prediction
2022, International Journal of FatigueCitation Excerpt :A new wave of applying deep learning methods in both academic and industrial fields has been inspired because of their superior visualization or classification performance. Correspondingly, more and more advanced machine learning (ML) models have been applied to multiaxial fatigue life research [10–20]. Their multilayer nonlinear structure emphasizes the importance of extracted features layer by layer, which can deal with the complex relationship between loading, material properties with fatigue life.
Use of data mining techniques to explain the primary factors influencing water sensitivity of asphalt mixtures
2022, Construction and Building Materials