Estimating the Bitumen Ratio to be Used in Highway Asphalt Concrete by Machine Learning

Author:

Çodur Muhammed YasinORCID,Kasil Halis BahadirORCID,Kuşkapan EmreORCID

Abstract

Hot mix asphalt, which is frequently used in road pavements, contains bitumen in certain proportions. This bitumen ratio varies according to the layers in the road pavements. The bitumen ratio in each pavement is usually estimated by the Marshall design method. However, this method is costly as well as time-consuming. In this study, the Naive Bayes method, which is a machine learning algorithm, was used to estimate the bitumen ratio practically. In the study, a total of 102 asphalt concrete designs were examined, which were taken from the wearing course, binder course, and asphalt concrete base course and stone mastic asphalt wearing course layers. Each road pavement layer was divided into three different classes according to the bitumen ratios and the algorithm was trained with machine learning. Then the bitumen ratio was estimated for each data set. As a result of this process, the bitumen ratios of the layers were estimated with an accuracy between 75% and 90%. In this study, it was revealed that the bitumen ratio in the road pavement layers could be estimated practically and economically.

Publisher

Riga Technical University

Reference35 articles.

1. Aljassar, A. H., Ali, M. A., & Alzaabi, A. (2002). Modeling Marshall test results for optimum asphalt-concrete mix design. Kuwait J Sci Engrg, 29(1), 181–195.

2. Asorhakt, U. (1993). Mix design methods for asphalt concrete and other hot-mix types. Asphalt Institute.

3. Atmaca, K. (2020, January 10). Naive Bayesian algorithm. https://kenanatmaca.com/naive-bayesian-algoritmasi/

4. Baldo, N., Manthos, E., & Pasetto, M. (2018). Analysis of the mechanical behaviour of asphalt concretes using artificial neural networks. Advances in Civil Engineering, 2018, Article 1650945. https://doi.org/10.1155/2018/1650945

5. Barczyszyn, G. L., De Camenar, L. M. O., De Do Nascimento, D. F., Kozievitch, N. P., Da Silva, R. D., Almeida, L. D. A., De Santi, J., & Minetto, R. (2018). A collaborative system for suitable wheelchair route planning. ACM Transactions on Accessible Computing, 11(3), Article 18. https://doi.org/10.1145/3237186

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3