Remaining life approximation of hot mix asphalt pavement with the help of artificial neural networks

Abstract

Hot Mix Asphalt pavements may require maintenance and repair as a result of deterioration due to various reasons. The remaining life of the existing pavement is not known, delaying maintenance and repair times and accelerating deterioration. In order to avoid such problems, the remaining life of road pavements can be calculated with different methods. Different prediction models can be created by determining material properties using non-destructive testing methods in calculating the remaining life of pavements. In this study, the remaining life of flexible pavements was calculated with the help of Artificial Neural Networks method. In the approximation method, the number of layers, elasticity moduli of layers, layer thicknesses, number of load repetitions were used as model inputs. The remaining life of the flexible pavement is estimated as output. Estimated results and calculated results were compared. It was observed that the remaining life estimated by the model and the remaining life calculated based on field data were closely aligned.

Keywords

• Flexible pavements
• Remaining life
• Artificial neural network methods
• Hot mix asphalt pavement

Yapay sinir ağları yardımı ile sıcak karışım asfalt kaplamaların kalan ömrünün tahmini

Öz

Sıcak Karışım Asfalt kaplamalar çeşitli nedenlerden dolayı meydana gelen bozulmalar sonucunda bakım ve onarım gerektirebilmektedir. Mevcut kaplamanın kalan ömrünün bilinmemesi bakım onarım sürelerinin gecikmesine ve bozulmaların hızlanmasına sebep olmaktadır. Bu gibi sorunların önüne geçebilmek için yol kaplamalarının kalan ömürleri farklı yöntemlerle hesaplanabilmektedir. Kaplamaların kalan ömrünün hesaplanmasında tahribatsız muayene yöntemleri kullanılarak malzeme özellikleri belirlenip farklı tahmin modelleri oluşturulabilmektedir. Bu çalışmada esnek kaplamaların kalan ömrü Yapay Sinir Ağları yöntemi yardımıyla hesaplanmıştır. Yaklaşım yönteminde, tabaka sayısı, tabakaların elastisite modülleri, tabaka kalınlıkları ve yük tekrar sayısı model girdileri olarak kullanılmıştır. Esnek üstyapının kalan ömrü çıktı olarak tahmin edilmiştir. Tahmin edilen sonuçlar ile hesaplanan sonuçlar karşılaştırılmıştır. Model tarafından tahmin edilen kalan ömür ile saha verilerine dayalı olarak hesaplanan kalan ömrün birbirine oldukça yakın olduğu gözlemlenmiştir.

Anahtar Kelimeler

• Esnek kaplamalar
• Kalan ömür
• Yapay zekâ metotları
• Sıcak karışım asfalt kaplama

Kaynakça

1. [1] The Republic of Türkiye Presidency, Presidency of Strategy and Budget, General Directorate of Budget. Citizen's Budget Guide. Ankara, Türkiye, 2024.
2. [2] The Republic of Türkiye Presidency, Presidency of Strategy and Budget, General Directorate of Budget. Citizen's Budget Guide. Ankara, Türkiye, 2025.
3. [3] Öcal A. Back calculation of Pavement Layer Properties Using Artificial Neural Network Based Gravitational Search Algorithm. MSc Thesis, Middle East Technical University, Ankara, Türkiye, 2014.
4. [4] Kırbaş U, Karaşahin M, Ünal EN, Komut M, Demir B, Öcal K. “Development of pavement performance prediction model for bituminous hot mix asphalt on interurban road networks”. Pamukkale Univ Müh Bilim Derg, 23(6), 718-725, 2017.
5. [5] Ferregut C, Abdallah I, Melchor O and Nazarian S. “Artificial Neural Network-Based Methodologies for Rational Assessment of Remaining Life of Existing Pavements”. Texas Department of Transportation, The University of Texas at El Paso El Paso, Texas, Research Report, 1711-1, 1999.
6. [6] Saltan M, Tığdemir M, Karaşahin M. “Artificial Neural Network Application for Flexible Pavement Thickness Modeling”. Turkish J. Eng. Env. Sci., 26, 243-248, 2002.
7. [7] Sollazzo G, Fwa TF, Bosurgi G. “An ANN Model to Correlate Roughness and Structural Performance in Asphalt Pavements”. Construction and Building Material, 134, 684-693, 2017.
8. [8] Yao H, Han K, Liu Y, Wang D, You Z. “Research and comparison of pavement performance prediction based on neural networks and fusion transformer architecture”. Electronic Research Archive, 32(2): 1239-1267, 2024.

9. [9] Nivedya MK, Mallick RB, Tirado C, Saremi SG, Nazarian S. “Use of Artificial Neural Network to Monitor Pavement Structural Strength during Adverse Weather Conditions”. Indian Geotechnical Conference, 2017 GeoNEst, 2017.
10. [10] Huang YH. Pavement analysis and design. 2nd ed. Upper Saddle River, NJ: Prentice Hall, 2004.
11. [11] Basnet KS, Shrestha JK, Shrestha RN. “Pavement performance model for road maintenance and repair planning: A review of predictive techniques”. Digital Transportation and Safety, 2(4): 253–267, 2023.
12. [12] Wu Z, Liu Y, Zhang Z. “Prediction of road condition and smoothness for flexible and rigid pavements in Louisiana using neural networks”. Louisiana Transportation Research Center, (Report No. 694), 2024.
13. [13] El-Badawy SM, Abaza KA. “Evaluation of Machine Learning Models for Pavement Roughness Prediction Using NDT Data”. Transportation Research Record, 2677(2), 314–326, 2023.
14. [14] Koç ML, Balas CE, Arslan A. “Preliminary design of Stone fill breakwaters with Artificial Neural Networks”. İMO Technical Journal, 15(4), 3351-3375, 2004.
15. [15] Elmas Ç. Artificial Neural Networks. Ankara, Türkiye, Seçkin Broadcasting, 2003.
16. [16] Öztemel E. Artificial Neural Network. 3rd ed. İstanbul, Türkiye, Papatya Broadcasting, 2006.
17. [17] Yıldız B. “Use of Artificial Neural Networks in Prediction of Financial Failure and an Empirical Practice in Public Companies”. İMKB Journal, 5 (17), 51-67, 2001.
18. [18] Benli Y. “The Use of Artificial Neural Networks in Prediction of Financial Failure and an Application in ISE”. Accounting Science World Journal, 4 (4), 17-30, 2002.
19. [19] Altrock CV. Fuzzy Logic and Neuro Fuzzy Applications Explained. Prentice Hall, Englewood Cliffs, NJ, USA, 1995.
20. [20] Shook JF, Finn FN, Witczak MW, Monismith CL. “Thickness design of asphalt pavements—the Asphalt Institute method”. Proceedings of the 5th international conference on the structural design of asphalt pavements, Delft University of Technology, The Netherlands, I, 17–44, 1982.
21. [21] Asphalt Institute. Research and Development of The Asphalt Institute's Thickness Design Manual (MS-1). 9th ed. Research Report 82-2, 1982.
22. [22] Claussen AIM, Edwards JM, Sommer P, Uge P. "Asphalt Pavement Design-The Shell Method". Proceedings of 4th International Conference on the Structural Design of Asphalt Pavements, 1, 39-74, 1977.
23. [23] Shell International Petroleum Company. Shell Pavement Design Manual: Asphalt Pavements and Overlays for Road Traffic. London, 1978.
24. [24] Thompson MR, Nauman D. “Rutting Rate Analyses of the AASHO Road Test Flexible Pavements”. Transportation Research Record 1384. National Research Council, Washington D.C., 36–48, 1993.
25. [25] Claros G, Carmicheal RF, Harvey J. Development of Pavement Evaluation Unit and Rehabilitation Procedure for Overlay Design Method. Vol. 2, Overlay Design Manual. Texas Research and Development Foundation for the Nigeria Federal Ministry of Works and Housing, Lagos, 1986.
26. [26] Brown SF, Pell PS, Stock AE. "The Application of Simplified, Fundamental Design Procedures for Flexible Pavement". Proceedings, 4th International Conference on the Structural Design of Asphalt Pavements, 1, 321-341, 1977.
27. [27] IRC: 37-2001. Guidelines for the Design of Flexible Pavements (second revision), Indian Roads Congress, New Delhi, 2001.
28. [28] Verstraeten JV, Veverka T, Francken L. “Rational and Practical Designs of Asphalt Pavements to Avoid Cracking and Rutting”. Proceedings, 5th International Conference on the Structural Design of Asphalt Pavements, ISAP, Lexington, 1984.
29. [29] Hazra S. Calibration of prediction models for remaining life of flexible pavements in Arkansas. Phd Thesis, University of Arkansas, 2009.
30. [30] Yaseen, FA. Availability of Anfis Method in Structural Analysis of Flexible Road Pavements. MSc Thesis, Süleyman Demirel University, Isparta, Türkiye, 2016.
31. [31] Saltan M, Alaefary F. “Usability of Adaptive Neuro-Fuzzy Inference System (Anfis) for Structural Analysis of Highway Flexible Pavements”. Journal of Engineering Sciences and Design, 6(3): 396-405, 2018.
32. [32] Lek S, Delacoste M, Baran P, Dimopoulos I, Lauga J, Aulagnier S. “Application of neural networks to modelling nonlinear relationships in ecology”. Ecological Modelling, 90(1), 39-52, 1996.
33. [33] Paruelo JM, Tomasel F. “Prediction of functional characteristics of ecosystems: a comparison of artificial neural networks and regression models”. Ecological Modelling, 98, 173-186, 1999.
34. [34] Ramos-Nino ME, Ramirez-Rodriguez CA, Clifford MN, Adams MR. “A comparison of quantitative structure-activity relationships for the effect of benzoic and cinnamic acids on Listeria monocytogenes using multiple linear regression, artificial neural network and fuzzy systems”. Journal of Applied Microbiology, 82, 168-176, 1997.
35. [35] Manel S, Dias JM, Ormerod SJ. “Comparing discriminant analysis, neural networks and logistic regression for predicting species distributions: a case study with a Himalayan river bird”. Ecological Modelling, 120, 337-347, 1999.
36. [36] Starrett SK, Adams GL. “Using artificial neural networks and regression to predict percentage of applied nitrogen leached under turfgrass”. Communications in Soil Science Plant Analytical, 28, 497-507, 1997.
37. [37] Özesmi SL, Özesmi U. “An artificial neural network approach to spatial habitat modelling with interspecific interaction”. Ecological Modelling, 116, 15-31, 1999.
38. [38] Çodur MY, Kasil HB, Kuşkapan E. “Estimating the bitumen ratio to be used in highway asphalt concrete by machine learning”. The Baltic Journal of Road and Bridge Engineering, 19(2), 23-42, 2024.
39. [39] Çodur MY, Kasil HB, Kuşkapan E. “Utilizing Machine Learning to Minimize Sample Height Errors in Marshall Asphalt Mixture Design Method”. Engineering, Technology & Applied Science Research, 15(4), 24511-24515, 2025.
40. [40] Gevrey M, Dimopoulos I, Lek S. “Review and comparison of methods to study the contribution of variables in artificial neural network models”. Ecological Modelling, 160 (2003) 249-264, 2003.
41. [41] Ertuğrul S, Hizal NA. “Neuro-fuzzy controller design via modelling human operator actions”. Journal of Intelli¬gent Fuzzy Systems, 16, 133-140, 2005.
42. [42] Çodur MY, Tortum A. “An Artificial Neural Network Model for Highway Accident Prediction: A Case Study of Erzurum, Türkiye”. Promet–Traffic & Transportation, 27(3), 217-225, 2015.
43. [43] Silva IN, Spatti DH, Flauzino RA, Liboni LHB, Alves SFR. “Artificial Neural Network Architectures and Training Processes”. Artificial Neural Networks, 21-28, Springer International Publishing Switzerland, 2017.
44. [44] Hamed M, Khalafallah M, Hassanien E. “Prediction of Wastewater Plant Performance Using Artificial Neu¬ral Networks”. Environmental Modelling and Software. 19(10), 919-928, 2004.
45. [45] Ilie C, Ploae C, Melnic LV, Cotrumba MR, Gurau AM, Alexandra C. “Sustainability through the Use of Modern Simulation Methods—Applied Artificial Intelligence”. Sustainability, 11(8), 2384, 2019.
46. [46] Kovacheva ZS. “Application of Neural Networks to Data Mining”. SQU Journal for Science, 12(2), 75-85, 2007.
47. [47] Ilie C, Ploae C, Melnic LV, Cotrumba MR, Gurau AM, Alexandra C. “Sustainability through the Use of Modern Simulation Methods—Applied Artificial Intelligence”. Sustainability, 11, 2384, 2019.
48. [48] User Manual. Version 2.1. In Alyuda NeuroIntelligence UserManual: London, UK, 1–132, 2002.
49. [49] General Directorate of Highways. “Pavement Management System Guideline”. Ankara, Turkey: KGM Publications, 2024.