A Simulation-Optimization Model to Minimize the Bitumen of Asphalt Mixture Using LINGO

Document Type : Original Article

Authors
Mohsen Amouzadeh Omrani 1
Rezvan Babagoli 2
Amir Izadi 3
Ali Hassannejad Esfandani 4
1 Department of Civil Engineering, Sava.C., Islamic Azad University, Savadkooh, Iran.
2 Assistant Professor, Department of Civil Engineering, University of Science and Technology of Mazandaran, Behshahr, Iran.
3 Assistant Professor, Civil Department, Shomal University, Amol, Iran.
4 Ph.D., Student, Department of Civil Engineering, Am.C., Islamic Azad University, Amol, Iran.
10.22034/road.2025.490138.2335
Abstract
One of the most important features considered in asphalt mixing design is the Marshall strength of asphalt. A low Marshall strength of asphalt reduces its efficiency and causes problems such as fatigue and cracks. Given the high impact of bitumen content on the compressive strength of asphalt and its high cost, the main goal of hot asphalt mix design is to select the most optimal bitumen content so that it can maintain the technical specifications of asphalt concrete within certain limits. Given the high costs of asphalt and its maintenance, the need to use new and more advanced methods in asphalt design and quality control is becoming more and more apparent. In this study, initially, information on 160 asphalt concrete laboratory samples was obtained from the Soil Mechanics Laboratory of Mazandaran Province, and then the compressive strength of asphalt was successfully and accurately modeled using an artificial neural network. Subsequently, the optimal bitumen content was obtained for 4 different aggregate conditions with the help of LINGO optimization software. The results showed that proper grading has a significant impact on reducing the amount of bitumen used and, consequently, the cost of asphalt.
Keywords
Compressive Strength of Asphalt
Artificial Neural Network
Optimization
LINGO
-رمضانپور ن، گوران اوریمی م. (1389). پیش­بینی مقاومت فشاری آسفالت و بررسی تاثیر تغییرات میزان فیلر، درصد قیر مصرفی، درصد جذب قیر مصالح و درصد شکستگی مصالح در مقاومت فشاری آسفالت با استفاده از شبکه­های عصبی مصنوعی. اولین کنفرانس  منطقه­ای مهندسی عمران، دانشگاه آزاد اسلامی واحد قائمشهر.
-فخری، منصور و غنی زاده، علیرضا  (1385). تعیین درصد بهینه قیر در روش طرح اختلاط مارشال با استفاده از یک مدل برنامه­ریزی خطی. پژوهشنامه حمل و نقل، سال سوم، شماره چهارم، 314-305.
-Amouzadeh Omrani, M. (2023). Laboratory comparison of mechanical properties of emulsified cold recycled asphalt containing cement kiln dust and steel slag with recycled asphalt containing cement. Journal of Transportation Infrastructure Engineering, 9(3), 57-79.
-AmouzadehOmrani, M., Hadizadeh, E., & Hajimirzajan, A. (2024). Investigating the causes and factors of railway accidents caused by the escape of a train carrying dangerous goods and its role in the Khayyam station accident. Road, 32(118), 75-90.
-Baghaee Moghaddam T. Soltani M. Karim MR, Shamshirband S, Petkovic D, Baaj H. (2015). Estimation of the rutting performance of Polyethylene Terephthalate modified asphalt mixtures by adaptive neuro-fuzzy methodology. Construction and Building Materials, 96, 550–555.
-Berthelot C. Crockford B. Lytton R. (1999). Comparison of Alternative Test Methods for Predicting Asphalt Concrete Rut Performance. 44th Annual Conference Canadian Technical Asphalt Association Proceedings. Canada,
405-434.
-Cao, P. Jin F. Zhou C. Feng D. Song W. (2016). Steady-state dynamic method: An efficient and effective way to predict dynamic modulus of asphalt concrete. Construction and Building Materials, 111, 54–62.
-Garson, G.D. (1991). Interpreting neural-networks connection weight, AI Expert, 6(7), 47-51.
-Karlaftis AG, Badr A. (2015). Predicting asphalt pavement crack initiation following rehabilitation treatments. Transportation Research Part C.
-Mirzahosseini MR, Aghaeifar A. Alavi AH. Gandomi AH, Seyednour R. (2011). Permanent Ogundipe OM. 2016. Marshall Stability and flow of lime-modified asphalt concrete. Transportation Research Procedia, 14, 685-693.
-Ozgan E, Saruhan H. (2010). Modeling of asphalt concrete via simulated annealing. Advances in Engineering Software, 41,
680-683.
-Ozgan H. (2011). Artificial neural network based modelling of the Marshall Stability of asphalt concrete. Expert Systems with Applications, 38, 6025–6030.
-Ozsahin TS, Oruc S. (2008). Neural network model for resilient modulus of emulsified asphalt mixtures. Construct Build Mater. 22, 1436–1445.
-Pourtahmasb MS, Karim MR, Shamshirband S. (2015). Resilient modulus prediction of asphalt mixtures containing Recycled Concrete Aggregate using an adaptive neuro-fuzzy methodology. Construction and Building Materials, 82, 257–263.
-Shafabakhsh, G. A., Ani, O. J., & Talebsafa, M. (2015). Artificial neural network modeling (ANN) for predicting rutting performance of nano-modified hot-mix asphalt mixtures containing steel slag aggregates. Construction and Building Materials, 85, 136-143.
-Soltani M, Baghaee Moghaddam T, Karim MR, Shamshirband S. Sudheer C. (2015). Stiffness performance of polyethylene terephthalate modified asphalt mixtures estimation using support vector machine-firefly algorithm. Measurement, 63, 232–239.
-Tigdemir MS, Kalyoncuoglu F, Kalyoncuoglu UY. 2004. Application of ultrasonic method in asphalt concrete testing for fatigue life estimation. NDT&E Inernational, 8(7), 597–602.
-Yu B, Gu. X. Ni F, Guo R. (2015). Multi-objective optimization for asphalt pavement maintenance plans at project level: Integrating performance, cost and environment. Transportation Research Part D, 41, 64–74.
-Zavrtanik N. Prosen J. Tušar M. Turk G. (2016). The use of artificial neural networks for modeling air void content in aggregate mixture. Automation in Construction, 63, 155–161.