پیش‌بینی خرابی شیار شدگی در روسازی‌های انعطاف‌پذیر با استفاده از شبکه عصبی مصنوعی و الگوریتم ژنتیک

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشکده مهندسی عمران و محیط زیست، دانشگاه صنعتی امیرکبیر (پلی‌تکنیک تهران)، تهران، ایران

چکیده

شیار شدگی یکی از خرابی‌های مهم عملکردی در روسازی‌های آسفالتی است. توسعه مدل‌های پیش‌بینی به منظور جلوگیری و کنترل آسیب‌های ناشی از این خرابی در سیستم مدیریت روسازی ضروری است. در این مطالعه با کمک الگوریتم‌ شبکه عصبی مصنوعی، مدل‌هایی برای پیش‌بینی مقدار خرابی شیار شدگی با استفاده از پایگاه داده برنامه بلند مدت روسازی (LTPP) توسعه داده شده است. این مدل‌ها برای اقلیم‌های آب و هوایی سرد و مرطوب، گرم و خشک و سرد و خشک ارائه شده‌اند. از آنجا که دقت مناسب در عین سادگی جزء مهم‌ترین ویژگی­های یک مدل پیش­بینی به شمار می­رود، با استفاده از روش بهینه­سازی چند‌هدفه NSGA ІІ-MLP متغیرهایی که میزان اهمیت بیشتری در پیش‌بینی خرابی شیار شدگی دارند، مشخص و به عنوان ورودی مدل در نظر گرفته شدند. سپس با استفاده از متغیر‌های ترافیکی، آب و هوایی و سازه‌ای انتخاب شده توسط الگو ریتم ژنتیک، مدل‌های پیش‌بینی خرابی شیار شدگی ساخته شده‌اند. مقدار ضریب تعیین و میانگین مربعات خطا برای مدل ساخته شده در مناطق سرد و مرطوب و مدل مشترک مناطق گرم و خشک و سرد و خشک به ترتیب برابر 0/96، 2/05، 0/94 و3/45 می‌باشد. همچنین با انجام تحلیل حساسیت، متغیر‌هایی که بیشترین اثرگذاری را بر خرابی شیار شدگی در اقلیم سرد و مرطوب دارند، به ترتیب اهمیت سن و اختلاف دمای حداکثر و حداقل روزانه با تاثیر مستقیم و ضخامت روسازی با تاثیر معکوس مشخص گردید. همچنین در اقلیم گرم و سرد خشک به ترتیب متغیر‌های بار ترافیکی و نفوذ‌پذیری قیر با تاثیر مستقیم و ضخامت روسازی با تاثیر معکوس بر خرابی از بیش‌ترین اهمیت برخورداراند.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Prediction of rutting deterioration in flexible pavements using artificial neural network and genetic algorithm

نویسندگان [English]

  • Alireza Askari
  • Pouria Hajikarimi
  • Mehrdad Ehsani
  • Fereidoon Moghadas Nejad
Amirkabir University of TechnologyDepartment of Civil & Environmental Engineering, Amirkabir University of Technology (Tehran Polytechnic), Iran.
چکیده [English]

Rutting is one of the major deteriorations of asphalt pavement, significantly impacts road safety and service quality. Prediction models are necessary to prevent and control the damage caused by this deterioration in the pavement management system. In this study, using the artificial neural network algorithm, models have been developed to predict the amount of rutting deterioration using the long-term pavement performance (LTPP) database. These models have been developed for wet freeze, dry freeze, and dry no-freeze climates. Since proper accuracy and simplicity are the most important features of a prediction model, using the NSGA ІІ-MLP multi-objective optimization method, the more important variables in predicting rutting deterioration are identified and selected as the model input. Then, using traffic, climatic and structural variables selected from the genetic algorithm, rutting deterioration prediction models were developed. The coefficient of determination and the mean squared error for the model made in the wet freeze zone and the model of dry freeze and dry no freeze zones are equal to 0. 96, 2.05, 0.94 and 3.45, respectively. Also, by performing sensitivity analysis, the effect of input data of each model on rutting deterioration was determined. The cumulative maximum and minimum daily temperature difference per year, pavement age, asphalt layer thickness, annual equivalent single axle loads, and bitumen penetration are the most impactful variables that have the greatest impact on rutting deterioration.

کلیدواژه‌ها [English]

  • Rutting
  • Flexible pavement
  • Artificial neural network
  • Multi-objective optimization
  • Genetic algorithm
[1] T.F. Fwa, The handbook of highway engineering, CRC press, 2005.
[2] K.H. McGhee, Automated pavement distress collection techniques, Transportation Research Board, 2004.
[3] K.A. Abaza, Deterministic performance prediction model for rehabilitation and management of flexible pavement, International Journal of Pavement Engineering, 5(2) (2004) 111-121.
[4] J.A. Prozzi, F. Hong, Transportation infrastructure performance modeling through seemingly unrelated regression systems, Journal of Infrastructure Systems, 14(2) (2008) 129-137.
[5] K.A. Zimmerman, D.M. Testa, An Evaluation of Idaho Transportation Department Needs for Maintenance Management and Pavement Management Software Tools,  (2008.(
[6] A. Miege, Tyre model for truck ride simulations, CPGS Dissertation, University of Cambridge,  (2004).
[7] A.R. Archilla, Development of rutting progression models by combining data from multiple sources, University of California, Berkeley, 2000.
[8] B. Ali, Numerical Model for the Mechanical Behavior of Pavement: Application to the Analysis of Rutting, PhD, University of Science and Technology Lille, France,  (2006.(
[9] M. Anyala, J. Odoki, C. Baker, Hierarchical asphalt pavement deterioration model for climate impact studies, International Journal of Pavement Engineering, 15(3) (2014) 251-266.
[10] J.D. Porras-Alvarado, Z. Zhang, L.G.L. Salazar, Probabilistic approach to modeling pavement performance using IRI data, 2014.
[11] I. ARA, ERES Consultants Division, Guide for Mechanistic–Empirical Design of New and Rehabilitated Pavement Structures, Final Rep., NCHRP Project 1-37A,  (2004).
[12] A. Isa, D. Ma’Soem, L.T. Hwa, Pavement performance model for federal roads, in:  Proceedings of the Eastern Asia Society for Transportation Studies, Citeseer, 2005, pp. 428-440.
[13] A.K. Naiel, Flexible pavement rut depth modeling for different climate zones,  (2010).
[14] M. Svensson, Modeling pavement performance based on data from the Swedish LTPP database: predicting cracking and rutting, KTH Royal Institute of Technology, 2013.
[15] M. RADWAN, A.-H. Mostafa, M. HASHEM, H. FAHEEM, Modeling pavement performance based on LTPP database for flexible pavements, Teknik Dergi, 31(4) (2020) 10127-10146.
[16] A. Fathi, M. Mazari, M. Saghafi, A. Hosseini, S. Kumar, Parametric study of pavement deterioration using machine learning algorithms, in:  Airfield and highway pavements 2019: Innovation and sustainability in highway and airfield pavement technology, American Society of Civil Engineers Reston, VA, 2019, pp. 31-41.
[17] S. Inkoom, J. Sobanjo, A. Barbu, X. Niu, Prediction of the crack condition of highway pavements using machine learning models, Structure and Infrastructure Engineering, 15(7) (2019) 940-953.
[18] W. Zeiada, S.A. Dabous, K. Hamad, R. Al-Ruzouq, M.A. Khalil, Machine learning for pavement performance modelling in warm climate regions, Arabian Journal for Science and Engineering,  (2020) 1-19.
[19] X. Cai, P. Wang, L. Du, Z. Cui, W. Zhang, J. Chen, Multi-objective three-dimensional DV-hop localization algorithm with NSGA-II, IEEE Sensors Journal, 19(21) (2019) 10003-10015.
[20] P. Lu, D. Tolliver, Pavement treatment short-term effectiveness in IRI change using long-term pavement program data, Journal of transportation engineering, 138(11) (2012) 1297-1302.
[21] FHWA, LONG-TERM PAVEMENT PERFORMANCE Information Management System Pavement Performance Database User Reference Guide, 088 (2003).
[22] G.E. Elkins, P.N. Schmalzer, T. Thompson, A. Simpson, Long-term pavement performance information management system: Pavement performance database user reference guide, Turner-Fairbank Highway Research Center, 2003.
[23] https://infopave.fhwa.dot.gov, in.
[24] H.J. Adèr, G.J. Mellenbergh, Advising on research methods.: Proceedings of the 2007 KNAW colloquium, Johannes van Kessel Publ., 2008.
[25] R.J. Little, D.B. Rubin, Statistical analysis with missing data, John Wiley & Sons, 2019.
[26] F. Yu, X. Xu, A short-term load forecasting model of natural gas based on optimized genetic algorithm and improved BP neural network, Applied Energy, 134 (2014) 102-113.
[27] V. Safak, Min-mid-max scaling, limits of agreement, and agreement score, arXiv preprint arXiv:2006.12904,  (2020).
[28] G. Shafabakhsh, O.J. Ani, M. Talebsafa, 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 (2015) 136-143.
[29] A. Moniri, H. Ziari, A. Amini, M. Hajiloo, Investigating the ANN model for cracking of HMA in terms of temperature, RAP and fibre content, International Journal of Pavement Engineering,  (2020) 1-13.
[30] J. Domitrović, H. Dragovan, T. Rukavina, S. Dimter, Application of an artificial neural network in pavement management system, Tehnički vjesnik, 25(Supplement 2) (2018) 466-473.
[31] E. Heidari, M.A. Sobati, S. Movahedirad, Accurate prediction of nanofluid viscosity using a multilayer perceptron artificial neural network (MLP-ANN), Chemometrics and intelligent laboratory systems, 155 (2016) 73-85.
[32] M. Jalal, Z. Grasley, C. Gurganus, J.W. Bullard, A new nonlinear formulation-based prediction approach using artificial neural network (ANN) model for rubberized cement composite, Engineering with Computers,  (2020) 1-18.
[33] A. Kostopoulos, T. Grapsa, Self-scaled conjugate gradient training algorithms, Neurocomputing, 72(13-15) (2009) 3000-3019.
[34] K. Gopalakrishnan, Effect of training algorithms on neural networks aided pavement diagnosis, International Journal of Engineering, Science and Technology, 2(2) (2010) 83-92.
[35] M.H. Esfe, H. Hajmohammad, R. Moradi, A.A.A. Arani, Multi-objective optimization of cost and thermal performance of double walled carbon nanotubes/water nanofluids by NSGA-II using response surface method, Applied Thermal Engineering, 112 (2017) 1648-1657.
[36] S. Ramesh, S. Kannan, S. Baskar, Application of modified NSGA-II algorithm to multi-objective reactive power planning, Applied Soft Computing, 12(2) (2012) 741-753.
[37] M. Ehsani, Development of a prediction model for concrete pavement failures using the LTPP data, Amirkabir University of Technology, 2021.
[38] Z. He, X. Wen, H. Liu, J. Du, A comparative study of artificial neural network, adaptive neuro fuzzy inference system and support vector machine for forecasting river flow in the semiarid mountain region, Journal of Hydrology, 509 (2014) 379-386.
[39] J.-L. Chen, H.-B. Liu, W. Wu, D.-T. Xie, Estimation of monthly solar radiation from measured temperatures using support vector machines–a case study, Renewable Energy, 36(1) (2011) 413-420.
[40] H. Adeli, Neural networks in civil engineering: 1989–2000, Computer‐Aided Civil and Infrastructure Engineering, 16(2) (2001) 126-142.
[41] J.D. Olden, D.A. Jackson, Illuminating the “black box”: a randomization approach for understanding variable contributions in artificial neural networks, Ecological modelling, 154(1-2) (2002) 135-150.
[42] M. Gevrey, I. Dimopoulos, S. Lek, Review and comparison of methods to study the contribution of variables in artificial neural network models, Ecological modelling, 160(3) (2003) 249-264.
[43] J.H. Choi, T.M. Adams, H.U. Bahia, Pavement Roughness Modeling Using Back‐Propagation Neural Networks, Computer‐Aided Civil and Infrastructure Engineering, 19(4) (2004) 295-303.