ارزیابی ترک خوردگی سدهای بتنی با استفاده از الگوریتم های فراابتکاری و روش‌ شبکه ی عصبی مصنوعی

نوع مقاله : علمی - پژوهشی

نویسندگان

1 دانشجوی دکتری سازه های آبی دانشگاه تبریز

2 استادیار گروه علوم و مهندسی آب دانشگاه تبریز، تبریز، ایران

3 گروه مهندسی کامپیوتر دانشگاه بناب

چکیده

با توجه به حساسیت موضوع ترک خوردگی در سدهای بتنی، نیاز به انجام آنالیز کامل و دقیق در خصوص رفتار ترک در این سدها با استفاده از روش‌های نوین احساس می‌شود. در این بین، الگوریتم‌های فرا ابتکاری از کارایی و دقت بسیار مناسبی در خصوص ارزیابی و پیش‌بینی مسائل نسبت به دیگر روش‌های نوین برخوردار می‌باشند. در این پژوهش با استفاده از الگوریتم فرا ابتکاری انتخابات (EA) و با لحاظ داده‌های تراز آب و دمای بتن طی سال‌های 1392-1379 به‌عنوان پارامترهای ورودی و مقدار تغییر مکان افقی و قائم ترک‌ها به‌عنوان پارامترهای خروجی، نحوه‌ی تغییرات ترک‌های سد بتنی قوسی زاینده‌رود مورد ارزیابی قرار گرفت و نتایج با روش الگوریتم ژنتیک (GA) و شبکه‌ی عصبی مصنوعی (ANN) مقایسه گردید. برای ارزیابی عملکرد روش پیشنهادی، از سه آماره شامل ضریب تبیین (R2)، جذر میانگین مربعات خطا (RMSE) و معیار نش- ساتکلیف (NSE) استفاده شده است. نتایج به‌دست آمده نشان می‌دهد الگوریتم EA با کسب مقادیر R2=0.96، RMSE=0.022 و NSE=0.74 در مقایسه با دو روش الگوریتم GA و شبکه‌ی عصبی مصنوعی (ANN)، از کارایی بالاتری برخوردار است و البته مقدار ضریب رگرسیون برای ترک‌های سرریز به دلیل عدم وجود داده‌های کافی، کم‌تر از ترک‌های سد حاصل شد. به طور کلی می‌توان نتیجه گرفت که برای ارزیابی تغییرات ترک‌های سدهای بتنی و پیش‌بینی روند تغییرات آن‌ها در آینده، الگوریتم‌های فرا ابتکاری روشی بسیار دقیق و قدرتمند محسوب شده و به‌وسیله این روش‌ها می‌توان دید بسیار خوبی بر وضعیت آسیب دیدگی سدهای بتنی پیدا نمود.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Evaluating Cracks in Concrete Dams using Meta-heuristic Algorithms and Artificial Neural Networks

نویسندگان [English]

  • Somayeh Emami 1
  • Javad Parsa 2
  • Hojjat Emami 3
1 Ph.D. Student of Hydraulic Structures, Department of Water Engineering, University of Tabriz, Tabriz, Iran
2 Assistant Professor of Hydraulic Structures, Department of Water Engineering, University of Tabriz, Tabriz, Iran
3 University of Bonab, Bonab, Iran
چکیده [English]

Necessity to a complete and accurate analysis of the crack behavior in concrete dams using new methods is felt due to the sensitivity of the cracking problem in these dams. Meanwhile, meta-heuristic algorithms have a very good performance and accuracy in evaluating and predicting problems rather than other methods. In this study, Zayandehrood arch concrete dam has been chosen as the case study and the displacements in the cracks of this dam have been investigated by using election algorithm (EA). Water level and concrete temperature from 2000 to 2013 were considered as input parameters and also horizontal and vertical displacement of cracks were selected as output parameters. The results were compared with genetic algorithm (GA) and artificial neural networks (ANN). To evaluate the performance of the proposed method, three statistical criteria including correlation coefficient (R2), root mean square error (RMSE) and Nash-Sutcliff efficiency (NSE) were utilized. The results show that EA has a higher efficiency with R2 = 0.96, RMSE = 0.022 and NSE = 0.74, compared to GA and ANN. However, due to the lack of sufficient data, the amount of regression coefficient for spillway cracks was lower than the dam cracks. It is concluded that for evaluating the displacements of cracks in concrete dams and predicting their variations in future, meta-heuristic algorithms can be utilized as a very exact and powerful method. These methods can help dam managers and decision-makers in monitoring and vulnerability analysis of dams during their operation.

کلیدواژه‌ها [English]

  • Cracking
  • Concrete Dam
  • Displacement
  • Election Algorithm
  • Zayandehrood Dam
[1] Khalilianpour, M. R. (2016). Evaluation of the concrete dams cracking using neural networks. MSc. of Hydraulic Structures. Faculty of Civil Engineering, University of Shahrkord.
[2] Tonakian, A., Najafnia, N., and Azizian, Gh. R. (2013). Preliminary location of cracks in concrete dams by weighted artificial neural networks. In: 7th National Congress on Civil Engineering. Shahid Nikbakht Engineering University, Zahedan.
[3] Nawayeniya, B., Naseri, N., Kalani Sarokalaji, L., and Vaseghi Amiri, C. (2014). Evaluation of nonlinear response of concrete concrete weights with cracking modeling using rotary and fixed method. In: The first national congress of engineering structures of Iran. 21 and 22 January, Tehran.
[4] Petroski, H. (1981). Simple static and dynamic models for the cracks elastic beam. International Journal of Fracture, 17(4), 71-76.
[5] Gudmundson, P. (1982). Eigenfrequency changes of structures due to cracks, notches or other geometrical changes. Journal of the Mechanics and Physics of Solids, 30(5), 339-353.
[6] Dimarogonas, A. and Paipets, S. (2013). Analytical Methods in Rotor Dynamics: Second Edition. Elsevier Applied Sciences, 2-12.
[7] Douka, E. Loutridis, S., and Trochidis, A. (2003). Crack identification in beams using wavelet analysis. International Journal of Solids and Structures, 40(13), 3557-3569.
[8] Calayir, Y. and Karaton, M. (2005). Seismic Fracture Analysis of Concrete Gravity Dams including Dam-Reservoir Interaction. Computers and Structures, 83, 1595-1606.
[9] Jia, J. S. and Li, X. Y. (2008). Dam heel cracking problem in high arch dams and new measure for solution. Journal of Hydraulic Engineering, 39, 1183–1188.
[10] Hariri-Ardebili, M. A. and Seyed-Kolbadi, S. M. (2015). Seismic cracking and instability of concrete dams: Smeared crack approach. Engineering Failure Analysis, 52, 45–60.
[11] Lin, P. Liu, X. L. Hu, S. Y., and Li, P. J. (2016). Large deformation analysis of a high steep slope relating to the Laxiwa reservoir, China. Rock Mechanics and Rock Engineering, 49, 2253–2276.
[12] Wang, W. and Huang, H. (2018). Cracking Risk and Overall Stability Analysis of Xulong High Arch Dam: A Case Study. Applied Sciences, 8(12), doi.org/10.3390/app8122555.
[13] Zhang, X. F., Wang, X. P., Y. Huang, S., and Li, Y. (2018). Simulation study on temperature stress of RCC arch dam under cold wave conditions. Water Resources and Water Engineering, 29, 192–197.
[14] Lin, P., Shi, J., Zhou, W. Y., and Wang, R. K. (2018). 3D geomechanical model tests on asymmetric reinforcement and overall stability relating to the Jinping I super-high arch dam, International Journal of Rock Mechanics and Mining Sciences, 102, 28–41.
[15] Khaji, N. and Javaherzadeh, M. (2017). Application of Neural Networks in Determining the Cracking Severity of Beam-shaped Beams. In: The third National Civil Engineering Congress
[16] Lotfollahi Yaghin, M., Shamsaie, A., and Hesari, M. A. (2011). The use of static wavelet transform (SWT) to identify the cracking of arched concrete dams, under frequency analysis. Journal of Civil Engineering, 11(3), 27-40. 
[17] Alijani Ardeshir, M., Nawayeniya, B., & Ahmadi, M. T. (2016). Nonlinear analysis of concrete concrete weights under normal gradient fault of the site. Journal of Structural and Construction Engineering (JSCE), 3(2), 133-155.
[18] Pirboudaghi, S., Tarinejad, R. and Alami, M. T. (2016). 2D Seismic cracking identification of concrete gravity dams based on extended finite element method and wavelet transform. Modares Mechanical Engineering, 16, 207-217.
[19] Ahmadi, M. T. and Amini Mazraennoo, M. (2017). Water pressure inside the crack in the behaviour of concrete concrete weighing under the influence of flood load. Sharif Journal of Civil Engineering, 33(1.4), 22-37.
[20] Ghazi Marashi, A. and Hussein, H. (2017). Turkeys analysis in concrete concrete weights using finite element method and using nonlinear failure mechanics criterion. In: 8th National Congress of Civil Engineering, Faculty of Civil Engineering, Babol, Iran. 
[21] Pirooznia, A. and Mordloo, A. J. (2017). Seismic Improvement of Concrete Gravity Dam Strengthened by Asphalt Buttressing. Journal of Structural and Construction Engineering (JSCE), Available at: doi.10.22065/JSCE.2018.104564.1374.
[22] Derikvand, Z., Kiamanesh, H. and Hedayat, N. (2018). Investigating the effect of crack length and angle on the behavior of concrete weights: a case study of Gotvand deviation regulation dam. Journal of Structural and Construction Engineering (JSCE), Available at: doi.10.22065/JSCE.2019.145317.1663.
[23] Elshafey, A. A., Dawood, N., Marzouk, H., and Haddara, M. (2013). Predicting of crack spacing for concrete by using neural networks. Engineering Failure Analysis, 31, 344-359.
[24] Elshafey, A. A., Dawood, N., Marzouk, H., and Haddara, M. (2013). Crack width in concrete using artificial neural networks. Engineering Structures, 52, 676-686.
[25] Alijani-Ardeshir, M., Navayinia, B., and Ahmadi, M. T. (2016). Comparative study of different smeared crack models for concrete dam. Journal of Gradevinar, 71(4), 305-318.
[26] Wu, B., Wu, Zh., Chen, B., and Su, H. (2016). Crack status analysis for concrete dams based on measured entropy.  Science in Technological Sciences, 59(5), 777-782. 
[27] Dasilva, W. R. L. and Lucena, D. S. (2018). Concrete Cracks Detection Based on Deep Learning Image Classification. Proceedings, 2(489).
[28] Rahimi, D. and Mohammadi, Z., (2017). Hydrological Drought Evaluation of Zayandeh Rood Dam Basin with SWSI Index. Geography Space Journal, 7(25), 221-234. 
[29] Emami, H. and Derakhshan, F. (2015). Election algorithm: A new socio-politically inspired strategy. AI Communications, 28, 591–603.
[30] Goldberg, D. E. (1989). Genetic algorithms in search, optimization, and machine learning, addison-wesley, reading, ma. NN Schraudolph and J3(1).
[31] Eshghi, K. and Karimi Nasab, M. (2016). Analysis of Algorithms and design of meta-heuristic methods. Sharif University Press.
[32] Menhaj, M. B. (1998). Computational Intelligence. No. 1. The Basic of Artificial Neural Networks, Amirkabir University.
[33] Demuth, H. and Beale, M. (2006). Neural network toolbox users guide: for use with MATLAB. The Math. Works.
[34] Heidari, A., Tavakoli, D., & Fakharian, P. (2013). Approximate eigenvalue of plate by artificial neural networks. Journal of Modeling in Engineering, 11, 49-62.
[35] Taghizadeh Mehrjardi R.,  Sarmadian, F., Savaghebi, Gh. R., O, M., Nourayer, T., Rousta, M. J., and Rahimiyan, M. H. (2013). (Comparison of Neuro-Fuzzy, Genetic Algorithm, Artificial Neural Network and Multivariate Regression for Prediction of Soil Salinity (Case study: Ardakan City). Journal of Range and Watershed Management, 66, 207-222.
[36] Tabatabaienejad, S. A. R., Barjasteh, M., & Kamari, M. (2016). Application of artificial neural networks and genetic optimization algorithm to estimate the ratio of dissolved gas to oil bubble point in south-western Iran. Scientific Journal of Oil & Gaz Exploration & Production, 134, 62-67.
[37] Larose, D. T. (2005). Discovering knowledge in data: an introduction to data mining. Jhon Wiley & Sons Inc, 240 p.
[38] Gorbani, M. A., Shahabboddin, Sh., Zare Haghi, D., Azani, A., Bonakdari, H., and Ebtehaj, I. (2017). Application of Firefly Algorithm-Based Support Vector Machines for Prediction of Filed Capacity and Permanent Wilting Point. Soil and Tillage Research, 172, 32-38.