Equivalent Axle Load Factor Prediction Based on Artificial Neural Networks

Document Type : Civil Article

Authors

1 Payam Noor University

2 Professor Assistant, Department of Engineering, Payame Noor University, PO BOX 19395-3697 Tehran, IRAN, mrkeymanesh@pnu.ac.ir

3 Ferdowsi University, Mashhad, Iran

4 Civil Department, Payame Noor University, Mashhad, Iran.

Abstract

Lack of accurate knowledge of pavement behavior under moving loads is the one of the most important disadvantages in calculation of Equivalent Axle Load Factor (EALF) in roads pavement. Among the many researches, the most comprehensive method is based on the AASHTO road test. As the main weakness of this method, the results are limited to the experimented axles, which makes it impossible to determine the EALF for all existing axles, hence reducing the accuracy of the results, causing premature failure, and leading to higher maintenance costs. Today, although numerous software packages are available for EALF calculation, they require various parameters, are time-consuming, and can only simulate one section at a time . On the other hand, artificial neural networks, as an artificial intelligence subcategory, have many advantages such as reduced input data, increased modeling process speed, ability of parallel modeling of several pavements with different conditions, etc. In this paper, after verifying the simulation of flexible pavements in ABAQUS, a model based on Artificial Neural Network (ANN) was presented to calculate EALF using the back-propagation architecture. Finally, from among the reviewed ANN configurations, the network with the 7-13-1 architecture incorporating the sigmoid function was selected as the optimum network.

Keywords


[1] Y. R. Kim, “Modeling of asphalt concrete”, ASCE Press, 2008.
[2] R. D. Cook, “Concepts and applications of finite element analysis”, John Wiley & Sons, 2007.
[3] S. I. R. Amorim et, J. C. Pais, A. C. Vale, and M. J. C. Minhoto, “A model for equivalent axle load factors”, International Journal of Pavement Engineering, Vol. 16, No. 10, 2015, pp. 881–893.
[4] J. Judycki, “Determination of Equivalent Axle Load Factors on the Basis of Fatigue Criteria for Flexible and Semi-Rigid Pavements”, Road Materials and Pavement Design, Vol. 11, No. 1, 2010, pp. 187–202.
[5] J. N. Boone, “Comparison of Ontario Pavement Designs Using the AASHTO 1993 Empirical Method and the Mechanistic-Empirical Pavement Design Guide Method”, Waterloo, 2013.
[6] American Association of State Highway and Transportation Officials (AASHTO), "Mechanistic – Empirical Pavement Design Guide A Manual of Practice", AASHTO, 2008.
[7] S. Zaghloul and T. D. White, “Guidelines for Permitting Overloads; Part 1: Effect of Overloaded Vehicles on the Indiana Highway Network”, 1994.
[8] K. Chatti, D. Lee, and T. Kim, “Truck Damage Factors Using Dissipated Energy versus Peak Strains”, 6th international Symposium on Heavy Vehicle Weights and Dlmensiolns, 2000, pp. 175–183.
[9] M. E. Abdel-Motaleb, “Impact of high-pressure truck tires on pavement design in Egypt”, Emirates Journal for Engineering Research, Vol. 12, No. 2, 2007, pp. 65–73.
[10] R. Chaudry and A. B. Memon, “Effects of Variation in Truck Factor on Pavement Performance in Pakistan”, Journal of Engineering and Technology, Vol. 32, No. 1, 2013, pp. 19–30.
[11] L. F. Macea, L. Marquez, and H. LLinas, “Improvement of Axle Load Spectra Characterization by a Mixture of Three Distributions”, Journal of Transportion Engineering, Vol. 141, No. 12, 2015.
[12] F. Homsi, D. Bodin, S. Yotte, D. Breysse, and J. M. Balay, “Multiple axle loadings: Shape parameters and their effect on the fatigue life of asphalt mixtures”, Europe Journal of Environment Civil Engineering, Vol. 15, No. 5, 2011, pp. 743–758.
[13] D. Rys, J. Judycki, and P. Jaskula, “Determination of vehicles load equivalency factors for polish catalogue of typical flexible and semi-rigid pavement structures”, Transportation Research Procedia, Vol. 14, 2016, pp. 2382–2391.
[14] H. Zhang, M. Gong, and T. Yu, “Modification and application of axle load conversion formula to determine traffic volume in pavement design”, International Journal of Pavement Research and Technology, Vol. 11, No. 6, 2018, pp. 582–593.
[15] A. K. Singh and J. P. Sahoo, “Analysis and design of two layered flexible pavement systems: A new mechanistic approach”, Computer and Geotechnic, Vol. 117, No. April 2019, 2020.
[16] Y. Deng, X. Luo, Y. Zhang, and R. L. Lytton, “Evaluation of Flexible Pavement Deterioration Conditions Using Deflection Profiles Under Moving Loads”, Transportation and Geotechnic, 2020.
[17] غلامعلی شفابخش، فریبرز فتحی و علی زایرزاده، "اولویت‌بندی اصلاح نقاط پرحادثه راه‏ها با کمک شبکه عصبی مصنوعی"، نشریه مدل‌سازی در مهندسی، دوره 8، شماره 20، بهار 89، صفحه 71-81.
[18] غلامعلی شفابخش، حسین نادرپور و فاضل فصیحی، "انتخاب الگوریتم بهینه شبکه عصبی در تحلیل روسازی‏های انعطاف‌پذیر راه‏ها"، نشریه مدل‌سازی در مهندسی، دوره 8، شماره 21، تابستان 89، صفحه 45-56.
[19] H. Adeli, “Neural Networks in Civil Engineering: 1989−2000”, Computer‐Aided Civil and Infrastructure Engineering, Vol. 16, No. 2, 2001, pp. 126–142.
[20] S. Lee, “Application of Artificial Neural Networks in Geoinformatics” Basel, Switzerland, 2018.
[21] J. Gajewski and T. Sadowski, “Sensitivity analysis of crack propagation in pavement bituminous layered structures using a hybrid system integrating Artificial Neural Networks and Finite Element Method”, Computational Materials Science, Vol. 82, 2014, pp. 114–117.
[22] I. Nunes, D. Hernane, R. A. Flauzino, L. H. Bartocci Liboni, and S. F. dos Reis Alves, “Artificial Neural Networks (A Practical Course) ”, Switzerland: Springer International Publishing, 2017.
[23] محمد باقر منهاج، "مبانی شبکه های عصبی"، انتشارات دانشگاه صنعتی امیرکبیر تهران، ایران، 1397.
[24] V. A. Profillidis and G. N. Botzoris, “Modeling of Transport Demand”, Elsevier, 2018.
[25] I. L. Al-qadi, H. Wang, and E. Tutumluer, “Dynamic Analysis of Thin Asphalt Pavements by Using Cross-Anisotropic Stress-Dependent Properties for Granular Layer”, Transportation Research Board, Vol. 2154.1, 2010, pp. 156–163.
[26] Y. Chen, “Viscoelastic modeling of flexible pavement”, Akron, 2009.
[27] Z. A. Alkaissi, “Effect of High Temperature and Traffic Loading on Rutting Performance of Flexible Pavement”, Journal of King Saud University - Engineering Sciences, Vol. 32, No. 1, 2020, pp. 1-4.
[28] S. M. Zaghloul and T. White, “Use of a three-dimensional, dynamic finite element program for analysis of flexible pavement”, Transportation research record, No. 1388, 1993.
[29] غلامعلی شفابخش، حسین نادرپور و مانا معتمدی، “مدل سازی پاسخ بهینه روسازی آسفالتی به کمک روش اجزای محدود”، نشریه مدل سازی در مهندسی، دوره 14، شماره 47، زمستان 95، صفحه 33-40.
[30] Y. H. Huang, “Pavement Analysis and Design”, 2nd Ed. Pearson Education, 2004.
[31] M. Kim, “Three-Dimensional Finite Element Analysis Of Flexible Pavements Considering Nonlinear Pavement Foundation Behavior” , University of Illinois, 2007.
[32] B. Zarei and G. A. Shafabakhsh, “Dynamic Analysis of Composite Pavement using Finite Element Method and Prediction of Fatigue Life”, Vol. 04, No. June 2018, pp. 33–37.
[33] D. Cebon, “Handbook of vehicle-road interaction”, 1999.
[34] A. Papagiannakis, T. N. A. Oancea, J. Chan, and A. T. Bergman, “Application of ASTM E1049-85 in Calculating Load Equivalence Factors from In Situ Strains”, Transportation Research Record, Vol. 1307, 1991, pp. 82–89.
[35] W. Uddin and S. Garza, “3D-FE modeling and simulation of airfield pavements subjected to FWD impact load pulse and wheel loads”, Airfield Pavements: Challenges and New Technologies, 2004, pp. 304–315.
[36] P. E. Sebaaly, N. Tabatabaee, B. Kulakowski, and T. Scullion, “Instrumentation for flexible pavements—Field performance of selected sensors”, Federal Highway Administration, Washington DC, 1991.
[37] J. E. Angus, “Criteria for choosing the best neural network”, Sandiego, 1991.