پیوندهای مفید
آمار
| تعداد نشریات | 7 |
| تعداد شماره‌ها | 399 |
| تعداد مقالات | 5,389 |
| تعداد مشاهده مقاله | 5,288,027 |
| تعداد دریافت فایل اصل مقاله | 4,882,770 |
پیش‌بینی خرابی پلکانی شدن در روسازی‌های بتنی غیرمسلح درزدار و تعیین پارامترهای موثر بر این خرابی با استفاده از شبکه‌های عصبی مصنوعی | ||
| نشریه مهندسی عمران امیرکبیر | ||
| مقاله 6، دوره 54، شماره 7، مهر 1401، صفحه 2547-2568 اصل مقاله (1.46 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22060/ceej.2021.19406.7161 | ||
| نویسندگان | ||
| مهرداد احسانی؛ فریدون مقدس نژاد* ؛ پوریا حاجی کریمی | ||
| دانشکده مهندسی عمران و محیط زیست، دانشگاه صنعتی امیرکبیر (پلی‌تکنیک تهران)، تهران، ایران | ||
| چکیده | ||
| یکی از خرابی‌های مهم عملکردی در روسازی‌های بتنی، خرابی پلکانی شدن است. پیش‌بینی مقدار این خرابی می‌تواند در طراحی بهینه روسازی بتنی و نیز استقرار سامانه مدیریت تعمیر و نگهداری روسازیها مورد استفاده قرار گیرد. در این مطالعه از شبکه‌های عصبی مصنوعی برای پیش‌بینی مقدار این خرابی بر اساس دادههای عملکرد طولانی مدت روسازی (LTPP) استفاده شده است. ابتدا با استفاده از 32 متغیر انتخابی ورودی شامل داده های ترافیکی، آب و هوایی و سازهای، معماری شبکه عصبی مصنوعی با روش آزمون و خطا تعیین شده و سپس معماری مشخص شده به درستی آموزش داده شده است. علاوه بر متغیرهای مورد استفاده در مطالعات گذشته، متغیرهای ورودی جدیدی نظیر ضریب پواسون و مدول الاستیسیته دال بتنی که تاکنون بررسی نشده‌اند نیز در بین این 32 متغیر مد نظر قرار گرفته است. سپس با به کارگیری روش جدید NSGA2-MLP، 19 متغیر مهم شناسایی شده و یک مدل شبکه عصبی جدید با این تعداد متغیر ساخته شده است. مقدار ضریب همبستگی، میانگین مربعات خطا و میانگین خطای مطلق برای مدل ساخته شده با 32 متغیر و 19 متغیر به ترتیب برابر 0/97، 0/45، 0/43، 0/95، 0/54 و 0/6 می‌باشد. در انتها با استفاده از روش جنگل تصادفی میزان اهمیت 19 متغیر بر اساس درصد تعیین گردید. چهار متغیری که بیشترین اهمیت را دارند بر اساس سهم درصد اهمیت متغیر از 100 به ترتیب عبارتند از تعداد تجمعی روزهای با بارش بیشتر از 12/7 میلی‌متر با 24%، مدول الاستیسته دال بتنی با %14، عمر روسازی با 12% و ضخامت اساس با 10% اهمیت. | ||
| کلیدواژه‌ها | ||
| پلکانی شدن؛ روسازی بتنی غیرمسلح درزدار؛ شبکه عصبی مصنوعی؛ انتخاب ویژگی؛ الگوریتم‌های فراابتکاری | ||
| موضوعات | ||
| انواع خرابی روسازی صلب | ||
| عنوان مقاله [English] | ||
| Faulting Prediction Model in Jointed Plain Concrete Pavement and determining the parameters affecting this failure with Artificial Neural Networks | ||
| نویسندگان [English] | ||
| Mehrdad Ehsani؛ Fereidoon Moghadas Nejad؛ Pouria Hajikarimi | ||
| a Department of Civil & Environmental Engineering, Amirkabir University of Technology, Tehran, | ||
| چکیده [English] | ||
| Faulting is one of the most common functional failures in concrete pavements. Pavement design and pavement management systems can both benefit from predicting this failure. Therefore, predicting this failure can be very useful. Artificial neural networks, a powerful technique, were utilized in this study to predict this failure. The artificial neural network architecture was first determined by trial and error using 32 input variables such as traffic, weather, and structural data, and then the defined architecture was appropriately trained. New input factors that have not been explored before, such as Poisson's ratio and elastic modulus of concrete slabs, have been considered among these 32 variables, in addition to the variables utilized in earlier studies. After that, 19 input variables were discovered using a new method, and a new neural network model with 19 variables was created. Notably, the feature selection method used in this study has been developed using the metaheuristic optimization algorithm. For the model with 32 variables and 19 variables, the correlation coefficient, mean square error, and mean absolute error are 0.97, 0.45, 0.43, 0.95, 0.54, and 0.6, respectively. Random forest is recognized in data mining as a powerful technique for identifying the importance of input variables. Finally, the importance of 19 variables was assessed using the random forest approach, with the four most important variables being the yearly cumulative number of days with precipitation more than 12.7 mm (24%), elastic modulus (14%), pavement life (12%), and base thickness (10%). It is found that elastic modulus is an essential input factor that has not been considered in prior studies. | ||
| کلیدواژه‌ها [English] | ||
| Jointed Plain Concrete Pavement (JPCP), Faulting Failure, Artificial Neural Networks (ANN), Feature Selection, Machine Learning | ||
|
سایر فایل های مرتبط با مقاله
|
||
| مراجع | ||
|
[1] V. Yepes, C. Torres-Machi, A. Chamorro, E. Pellicer, Optimal pavement maintenance programs based on a hybrid greedy randomized adaptive search procedure algorithm, Journal of Civil Engineering and Management, 22(4) (2016) 540-550. [2] M.G. Augeri, S. Greco, V. Nicolosi, Planning urban pavement maintenance by a new interactive multiobjective optimization approach, European Transport Research Review, 11(1) (2019) 1-14. [3] Z. Mao, Life-Cycle Assessment of Highway Pavement Alternatives in Aspects of Economic, Environmental, and Social Performance, Texas A & M University, 2012. [4] M. Hossain, L.S.P. Gopisetti, M.S. Miah, Artificial neural network modelling to predict international roughness index of rigid pavements, International Journal of Pavement Research and Technology, (2020) 1-11. [5] D.G. Mapa, M. Gunaratne, K.A. Riding, A. Zayed, Evaluating Early-Age Stresses in Jointed Plain Concrete Pavement Repair Slabs, ACI Materials Journal, 117(4) (2020). [6] L.F. Facts, National Asphalt Pavement Association (NAPA), Landham, MD, no date, in, 2007. [7] M.Y. Shahin, Pavement management for airports, roads, and parking lots, 1994. [8] X. Yang, Z. You, J.E. Hiller, M.R. Mohd Hasan, A. Diab, S. Luo, Sensitivity of Rigid Pavement Performance Predictions to Individual Climate Variables using Pavement ME Design, Journal of Transportation Engineering, Part B: Pavements, 146(3) (2020) 04020028. [9] W.A. Van, Rigid pavement pumping:(1) subbase erosion and (2) economic modeling: informational report, (1985). [10] J.-H. Jeong, D.G. Zollinger, Characterization of stiffness parameters in design of continuously reinforced and jointed pavements, Transportation Research Record, 1778(1) (2001) 54-63. [11] Y. Chen, R.L. Lytton, Development of a new faulting model in jointed concrete pavement using LTPP data, Transportation Research Record, 2673(5) (2019) 407-417. [12] Y.S. Jung, D.G. Zollinger, New Laboratory-Based Mechanistic–Empirical Model for Faulting in Jointed Concrete Pavement, Transportation research record, 2226(1) (2011) 60-70. [13] K.N. Bakhsh, D. Zollinger, Faulting prediction model for design of concrete pavement structures, in: Pavement Materials, Structures, and Performance, 2014, pp. 327-342. [14] A. Simpson, J. Rauhut, P. Jordahl, E. Owusu-Antwi, M. Darter, R. Ahmad, O. Pendleton, Y. Lee, Early analyses of LTPP general pavement studies data, Sensitivity Analyses for Selected Pavement Distresses, (1993). [15] H. Yu, K. Smith, M. Darter, J. Jiang, L. Khazanovich, Performance of concrete pavements. Volume III: Improving concrete pavement performance, 1998. [16] Aashto, Guide for the local calibration of the mechanistic-empirical pavement design guide, in, American Association of State Highway and Transportation Officials …, 2010. [17] H.-W. Ker, Y.-H. Lee, C.-H. Lin, Development of faulting prediction models for rigid pavements using LTPP database, Statistics, 218(0037.0) (2008) 0037.0030. [18] B. Saghafi, A. Hassani, R. Noori, M.G. Bustos, Artificial neural networks and regression analysis for predicting faulting in jointed concrete pavements considering base condition, International Journal of Pavement Research and Technology, 2(1) (2009) 20-25. [19] W.-N. Wang, Y.-C.J. Tsai, Back-propagation network modeling for concrete pavement faulting using LTPP data, International Journal of Pavement Research and Technology, 6(5) (2013) 651. [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] https://infopave.fhwa.dot.gov/. [22] V. Safak, Min-Mid-Max Scaling, Limits of Agreement, and Agreement Score, arXiv preprint arXiv:2006.12904, (2020). [23] 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. [24] M. Younos, R. Abd El-Hakim, S. El-Badawy, H. Afify, Multi-input performance prediction models for flexible pavements using LTPP database, Innovative Infrastructure Solutions, 5(1) (2020) 1-11. [25] 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. [26] G. Sollazzo, T. Fwa, G. Bosurgi, An ANN model to correlate roughness and structural performance in asphalt pavements, Construction and Building Materials, 134 (2017) 684-693. [27] A. Kostopoulos, T. Grapsa, Self-scaled conjugate gradient training algorithms, Neurocomputing, 72(13-15) (2009) 3000-3019. [28] A.A. Suratgar, M.B. Tavakoli, A. Hoseinabadi, Modified Levenberg-Marquardt method for neural networks training, World Acad Sci Eng Technol, 6(1) (2005) 46-48. [29] R. Dhaigude, S. Ajmera, Modelling of Groundwater Level Using Artificial Neural Network. [30] 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. [31] T. Vo-Duy, D. Duong-Gia, V. Ho-Huu, H.C. Vu-Do, T. Nguyen-Thoi, Multi-objective optimization of laminated composite beam structures using NSGA-II algorithm, Composite Structures, 168 (2017) 498-509. [32] A. Kumar, H. Majumder, K. Vivekananda, K. Maity, NSGA-II approach for multi-objective optimization of wire electrical discharge machining process parameter on inconel 718, Materials Today: Proceedings, 4(2) (2017) 2194-2202. [33] 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. [34] 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. [35] R. Genuer, J.-M. Poggi, C. Tuleau-Malot, Variable selection using random forests, Pattern recognition letters, 31(14) (2010) 2225-2236. [36] U. Grömping, Variable importance assessment in regression: linear regression versus random forest, The American Statistician, 63(4) (2009) 308-319. [37] W. Zhang, C. Wu, Y. Li, L. Wang, P. Samui, Assessment of pile drivability using random forest regression and multivariate adaptive regression splines, Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards, 15(1) (2021) 27-40. [38] H. Gong, Y. Sun, X. Shu, B. Huang, Use of random forests regression for predicting IRI of asphalt pavements, Construction and Building Materials, 189 (2018) 890-897. [39] H. Gong, Y. Sun, W. Hu, P.A. Polaczyk, B. Huang, Investigating impacts of asphalt mixture properties on pavement performance using LTPP data through random forests, Construction and Building Materials, 204 (2019) 203-212. [40] D. Daneshvar, A. Behnood, Estimation of the dynamic modulus of asphalt concretes using random forests algorithm, International Journal of Pavement Engineering, (2020) 1-11. [41] C. Strobl, A.-L. Boulesteix, T. Kneib, T. Augustin, A. Zeileis, Conditional variable importance for random forests, BMC bioinformatics, 9(1) (2008) 1-11. | ||
|
آمار تعداد مشاهده مقاله: 584 تعداد دریافت فایل اصل مقاله: 802 |
||
