Determining International Irregularity Index (IRI) Values Through Artificial Neural Network (ANN) Modelling

Abstract

The quality of a pavement's level of service is generally determined by measuring the combinations of some important factors which affect the speed, travel time, freedom to maneuver, user comfort and convenience. In this study, a feed-forward back-propagation artificial neural network (ANN) algorithm is proposed based on the acquired International Irregularity Index (IRI) data for the highway structures, bridges and culverts, obtained through laser profilometer measurements on the surface irregularity of the bituminous hot mix roads. Analysis of ANN results were carried out through training various hidden number of neural networks for the output prediction, which is the best estimation of the surface irregularity of the roads. Results produced by artificial neural network have been compared with experimental and numerical results through extensive sets of non-training experimental data. As the comparison of results with ANN study having average absolute mean relative errors as 12.68% for bridges and 12.90% for culverts provided very accurate results, the model proposed could be used to obtain the surface irregularity of the roads by avoiding heavy duty of collecting numerous field data. The results obtained through ANN model were found more accurate than the results produced by numerical models.

Keywords

• International Irregularity Index
• laser profilometer
• Artificial Neural Networks
• Numerical Analysis

References

1. Wen, T., Ding, S., Lang, H., Lu, J.J., Yuan, Y., Peng, Y., Chen, J., Wang, A., “Automated pavement distress segmentation on asphalt surfaces using a deep learn-ing network”. International Journal of Pavement En-gineer-ing,2022,doi:10.1080/10298436.2022.2027414.
2. Kırbas, U, System Establishment of Superstructure Maintenance Management on Urban Roads, The case study of Turkey, 2013, PhD thesis, Istanbul University
3. AASHTO, Pavement Management Guide, 2nd ed. American Association of State Highway and Transpor-tation Officials; Washington, DC, USA, 2012.
4. Ángela Alonso Solórzano, Heriberto Pérez Acebo, Alaitz Linares Unamunzaga, Hernán Gonzalo Orden., “Probabilistic International Roughness Index (IRI) prediction model for a climate homogeneous region”.. Transportation Research Procedia 71, 46–52, 2023.
5. Haas, R., & Hudson, W. R. “Pavement asset manage-ment”. John Wiley & Sons, 2015.
6. Siper. M., “Superstructure Performance Estimation with Artificial Intelligence Methods”, MSc Thesis, Necmettin Erbakan University, Department of Indus-trial Engineering, 2021.
7. Kulkarni, R. B., & Miller, R. W. “Pavement manage-ment systems: Past, present, and Future”. Transporta-tion Research Record, 1853(1), 65-71, 2003.
8. G. Valdés-Vidal, A. Calabi-Floody , E. Sanchez-Alonso , C. Díaz , C. Fonseca, “Highway trial sections: Performance evaluation of warm mix asphalt and re-cycled warm mix asphalt”, Construction and Building Materials Volume 262, 120069, 30 November 2020.

9. Heriberto Pérez-Aceboa, Miren Isasab, Itziar Gurrutx-agab, Harkaitz Garcíab, Aimar Insaustib, “Internation-al Roughness Index (IRI) prediction models for free-ways”, XV Conference on Transport Engineering, CIT2023, Transportation Research Procedia 71, 292–299, 2023.
10. Jiangyu Zeng, Mustafa Gül, Qipei Mei, “A computer vision-based method to identify the international roughness index of highway pavements”, Journal of Infrastructure Intelligence and Resilience 1, 100004, 2022.
11. Jian Liu, Fangyu Liu, Chuanfeng Zheng, Ebenezer O. Fanijo, , Linbing Wang., “ Improving asphalt mix de-sign considering international roughness index of as-phalt pavement predicted using autoencoders and machine learning” Construction and Building Mate-rials Volume 360, 129439, 19 December 2022.
12. G. Sollazzo, T.F. Fwa, G. Bosurgi, “An ANN model to correlate roughness and structural performance in as-phalt pavements”, Construction and Building Materi-als Volume 134, 1 March 2017, Pages 684-693.
13. Erkmen ,F., Akdas,M.Emrah., Ruzgar, Y., Komut, M., and Altıok, S., “The surface irregularity analysis of the road sections approaching to the constructional struc-tures in highways”,The 5th highway national congress and exhibition”, Ankara-Turkey, pp.365-379, 2023.
14. Abdualmtalab Abdualaziz Ali, Abdalrhman Milad, Amgad Hussein, Nur Izzi Md Yusoff, Usama Heneash “Predicting pavement condition index based on the utilization of machine learning techniques: A case study”, Journal of Road Engineering Volume 3, Issue 3, Pages 266-278, September 2023.
15. Nima Sholevar, Amir Golroo, Sahand Roghani Esfa-hani “Machine learning techniques for pavement condition evaluation”, Automation in Construction, Volume 136, 104190, April 2022.
16. Muhammad Imran Khan, Nasir Khan, Syed Roshan Zamir Hashmi, Muhamad Razuhanafi Mat Yazid, Nur Izzi Md Yusoff, Rai Waqas Azfar, Mujahid Ali, Roman Fediuk, “Prediction of compressive strength of ce-mentitious grouts for semi-flexible pavement applica-tion using machine learning approach”, Case Studies in Construction Materials, Volume 19, e02370, De-cember 2023.
17. Mosbeh R. Kaloop, Sherif M. El-Badawy , Jong Wan Hu, Ragaa T. Abd El-Hakim, “International Rough-ness Index prediction for flexible pavements using novel machine learning techniques”, Engineering Applications of Artificial Intelligence Volume 122, 106007, June 2023.
18. Yanan Wu., Yafeng Pang., Xingyi Zhu, “Evolution of prediction models for road surface irregularity: Trends, methods and future”, Construction and Build-ing Materials, Volume 449, 138316, 2024.
19. Mansour Fakhri., Reza Shahni Dezfoulian., “Pave-ment structural evaluation based on roughness and surface distress survey using neural network model”, Construction and Building Materials, Volume 204, Pages 768-780, 2023.
20. Ermis, K., Erek, A., and Dincer, I., “Heat transfer anal-ysis of phase change process in a finned-tube thermal energy storage system using Artificial Neural Net-work,” International Journal of Heat and Mass Trans-fer, 50, 3163-3175, 2007.
21. Ermis, K., A. Midilli, I. Dincer ve M. A. Rosen, “Arti-ficial Neural Network analysis of world green energy use,” Energy Policy, 35, 1731-1743, 2007.
22. Ermis, K., “ANN Modeling of compact heat exchang-ers,”, International Journal of Energy Research, 32, 581-594, 2008.
23. Reed R.D., Marks R.J., Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks, MIT Press, London, 1999.
24. Rojas R., Neural Networks, Springer-Verlag, Berlin, 1996.
25. Haykin S., Neural Networks: A Comprehensive Foundation, Prentice Hall, New Jersey, 1999.
26. Fausett L., Fundamentals of Neural Networks: Archi-tecture Algorithms and Applications, Prentice Hall, Englewood Cliffs, N.J., 1994.
27. Nasr G.E., Badr E.A. and Joun C., “Backpropagation neural networks for modeling gasoline consumption”, Energy Conversion and Management, 44, 893–905, 2003.
28. Sablani S.S., Kacimov A., Perret J., Mujumdar A.S. and Campo A., “Non-iterative estimation of heat transfer coefficients using artificial neural network models”, International Journal of Heat and Mass Transfer 48, 665–679, 2005.