Artificial Intelligence Prediction of Rutting and Fatigue Parameters in Modified Asphalt Binders

Uwanuakwa, Ikenna D.; Ali‬, Shaban Ismael Albrka; Hasan, Mohd Rosli Mohd; Akpınar, Pınar; Sani, Ashiru; Shariff, Khairul Anuar

doi:10.3390/app10217764

Cited by 27 publications

(10 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AI plays an important role in predicting rutting and fatigue parameters in modified asphalt binders as shown by Uwanuakwa et al [11]. Hosseinzadeh et al [12] use ML algorithms to predict Marshall asphalt stability.…”

Section: Literature Reviewmentioning

confidence: 99%

Application of AI Techniques for Asphalt Concrete Mix Production Optimization

Uaissova,

Zharlykassov

2024

JESA

View full text Add to dashboard Cite

In present-day conditions of road infrastructure development, ensuring the high quality of asphalt concrete mixes contributes to the durability and reliability of road pavements. This article investigates the application of artificial intelligence techniques to analyze asphalt quality aimed at optimizing production and improving the reliability of road pavements. This study introduces a pioneering approach to asphalt concrete mix quality enhancement using artificial intelligence (AI) techniques, specifically artificial neural networks (ANN) and least-squares support vector machine (LS-SVM). The application of these methods allows for carrying out efficient analysis of data, reflecting asphalt quality, predicting asphalt characteristics, and optimizing production processes. The authors conducted experiments using real asphalt properties, which were used to train and set ANN and LS-SVM models. The obtained results were compared with existing methods of asphalt quality analysis. The conducted analysis confirmed the effectiveness of using ANN and SVM to analyze asphalt quality. This approach provides an opportunity for accurate prediction of asphalt performance characteristics and production process optimization, contributing to the improvement of the durability and reliability of road pavements. The obtained results have practical significance for engineers and specialists in the field of road infrastructure construction and maintenance. The results of the study validate the superiority of AI-driven models in achieving precise and reliable asphalt mix designs, marking a considerable advancement over traditional methods.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Application of AI Techniques for Asphalt Concrete Mix Production Optimization

Uaissova,

Zharlykassov

2024

JESA

View full text Add to dashboard Cite

show abstract

“…To overcome and mitigate the effects of climatic factors and vehicular loading, AC is expected to possess certain physical and rheological properties. These properties include; higher stiffness under low frequencies and high temperatures and higher elasticity in high frequencies and low and intermediate temperature conditions [1]. Modification of AC by common materials such as polymers, nanomaterials and polymer nanocomposites is a regularly employed process in the pavement industry to improve the performance characteristics of AC [2].…”

Section: Introductionmentioning

confidence: 99%

Multi Criteria Performance Analysis for Nano-Iron Oxide Modified Asphalt Cement by Using Fuzzy Promethee II

Alas

2023

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

This study aimed to investigate the intermediate and high temperature performance characteristics of asphalt cement (AC) modified by iron-oxide nanoparticles (ION). Moreover, Fuzzy PROMETHEE-II technique was employed in order to evaluate the performance of base and ION modified AC by considering multiple criteria; physical properties, rheological characteristics, durability and economic aspects. Excluding the control sample (base AC); three different blends that contained 1%, 3% and 5% ION by the weight of AC were prepared. By conducting rheological testing procedures, isochronal plots were constructed and rutting and fatigue resistance parameters were evaluated. In addition to rheological properties, physical properties were also investigated under unaged and aged conditions and they were utilised in the Fuzzy PROMETHEE-II analysis. According to the experimental outcomes, the optimum concentration of ION was found to be 1% by the weight of AC at high temperatures and above this concentration the improvement of viscoelastic behaviour was hindered to due agglomeration. In other respects, addition of ION in the AC resulted in degrading of the elastic properties, meaning lower fatigue resistance against cracking. The findings of Fuzzy PROMETHEE-II also demonstrated similar trend of results with minor deviations indicating that, not only considering a single parameter but also as a complete ranking evaluation considering multiple criteria, the findings of the current study were reinforced.

show abstract

“…Researchers have paid a lot of attention to the use of artificial intelligence (AI) for determining the mechanical behavior of asphalt concrete materials because of its easiness and reliability. Assessing the impact of non-linear data and non-factors on recurrent neural networks is a common application of machine intelligence techniques such as gaussian process regression, random forest, random tree, M5P tree, gene expression program (GEP), support vector machine (SVM), Gaussian process (GP), fuzzy logic, and ANFIS [16,[18][19][20][21][22][23][24][25][26]. The ANN approach [18] was implemented to predict the sustainability of asphalt concrete at various temperatures, which is better at predicting non-linear data.…”

Section: Introductionmentioning

confidence: 99%

Marshall Stability Prediction with Glass and Carbon Fiber Modified Asphalt Mix Using Machine Learning Techniques

et al. 2022

View full text Add to dashboard Cite

Pavement design is a long-term structural analysis that is required to distribute traffic loads throughout all road levels. To construct roads for rising traffic volumes while preserving natural resources and materials, a better knowledge of road paving materials is required. The current study focused on the prediction of Marshall stability of asphalt mixes constituted of glass, carbon, and glass-carbon combination fibers to exploit the best potential of the hybrid asphalt mix by applying five machine learning models, i.e., artificial neural networks, Gaussian processes, M5P, random tree, and multiple linear regression model and further determined the optimum model suitable for prediction of the Marshall stability in hybrid asphalt mixes. It was equally important to determine the suitability of each mix for flexible pavements. Five types of asphalt mixes, i.e., glass fiber asphalt mix, carbon fiber asphalt mix, and three modified asphalt mixes of glass-carbon fiber combination in the proportions of 75:25, 50:50, and 25:75 were utilized in the investigation. To measure the efficiency of the applied models, five statistical indices, i.e., coefficient of correlation, mean absolute error, root mean square error, relative absolute error, and root relative squared error were used in machine learning models. The results indicated that the artificial neural network outperformed other models in predicting the Marshall stability of modified asphalt mix with a higher value of the coefficient of correlation (0.8392), R2 (0.7042), a lower mean absolute error value (1.4996), and root mean square error value (1.8315) in the testing stage with small error band and provided the best optimal fit. Results of the feature importance analysis showed that the first five input variables, i.e., carbon fiber diameter, bitumen content, hybrid asphalt mix of glass-carbon fiber at 75:25 percent, carbon fiber content, and hybrid asphalt mix of glass-carbon fiber at 50:50 percent, are highly sensitive parameters which influence the Marshall strength of the modified asphalt mixes to a greater extent.

show abstract

Artificial Intelligence Prediction of Rutting and Fatigue Parameters in Modified Asphalt Binders

Cited by 27 publications

References 44 publications

Application of AI Techniques for Asphalt Concrete Mix Production Optimization

Application of AI Techniques for Asphalt Concrete Mix Production Optimization

Multi Criteria Performance Analysis for Nano-Iron Oxide Modified Asphalt Cement by Using Fuzzy Promethee II

Marshall Stability Prediction with Glass and Carbon Fiber Modified Asphalt Mix Using Machine Learning Techniques

Contact Info

Product

Resources

About