پیوندهای مفید
آمار
| تعداد نشریات | 7 |
| تعداد شماره‌ها | 405 |
| تعداد مقالات | 5,424 |
| تعداد مشاهده مقاله | 5,544,351 |
| تعداد دریافت فایل اصل مقاله | 5,027,722 |
پیش‌بینی دبی ورودی روزانه سد سفیدرود با الگوریتم‌های فراابتکاری ترکیبی با سیستم استنتاج عصبی فازی | ||
| نشریه مهندسی عمران امیرکبیر | ||
| مقاله 1، دوره 56، شماره 1، 1403، صفحه 3-22 اصل مقاله (2.12 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22060/ceej.2024.21634.7784 | ||
| نویسندگان | ||
| حسین حکیمی خانسر1؛ جواد پارسا* 2؛ عمران مومنی کلشتری1؛ نوربخش کرمی3؛ معین خوشدل سنگده1 | ||
| 1شرکت سهامی آب منطقه‌ای گیلان، ایران | ||
| 2گروه علوم و مهندسی آب، دانشگاه تبریز، تبریز، ایران | ||
| 3سازمان بهره‌برداری و نگهداری از سد و نیروگاه سفیدرود، ایران | ||
| چکیده | ||
| تخمین مقادیر دبی ورودی به سیستم منابع آبی یکی از اقدامات اساسی برای آگاهی از برنامه‌ریزی و تخصیص بهینه منابع آب به بخش‌های مختلف مصرف، در آینده است. در این مطالعه، از ترکیب الگوریتم‌های فراابتکاری شامل الگوریتم‌های فراابتکاری چرخه‌ی آب (WCA)، گرگ خاکستری (GOW)، وال (WOA)، الگوریتم شبکه عصبی (NNA) و ملخ (GOA) برای آموزش سیستم عصبی- فازی و به‌روزرسانی پارامترهای آن استفاده گردید و در نهایت بهترین مدل‌ها برای پیش‌بینی دبی ورودی روزانه سد مخزنی سفیدرود، توسعه داده شد. در مرحله آزمون، مدل ANFIS-WCA کمترین مقادیرSI ، MAE وNRMSE به ترتیب برابر 0/0736، 0/5048 و 0/0736و بیش‌ترین مقدار برابر 0/9840را ارائه می‌کند که نشان‌دهنده برتری آن نسبت به سایر مدل‌ها است. بر اساس شاخص عملکرد جهانی (GPI)، مدلANFIS-WCA به عنوان بهترین مدل و پس از آن مدل‌هایANFIS-NNA ، ANFIS-GOA و ANFIS-WOA رتبه‌بندی شدند درحالی‌که بدترین دقت از طریق مدل ANFIS-GOA به دست آمد. نتایج نشان داد که مدل ANFIS-WCA با توجه به شاخص SI، 1/3 ٪ در مقایسه با ANFIS-NNA و 1/6 ٪ در مقایسه با ANFIS-GOA کاهش را نشان می دهد. علاوه بر این، بر اساسGPI ، مدل ANFIS-WCA تا 11 درصد در مقایسه با مدل ANFIS-ANN و 20 درصد در مقایسه با مدل ANFIS-GOA بهبود را نشان می‌دهد. دقت بالای مدل ANFIS-WCA در مقایسه با سایر مدل‌های هیبریدی نشان‌دهنده عملکرد الگوریتم چرخه آب برای فرار از بهینه محلی در ترکیب با مدل ANFIS و پیچیدگی دبی ورودی است،که قادر کرده این الگوریتم به ابزاری قدرتمند برای تخمین دبی ورودی سد سفیدرود تبدیل شود. | ||
| کلیدواژه‌ها | ||
| الگوریتم فرا ابتکاری؛ الگوریتم چرخه آّب؛ سد سفیدرود؛ دبی ورودی؛ سیستم استنتاج فازی –عصبی- تطبیقی | ||
| موضوعات | ||
| آب و سازه های هیدرولیکی | ||
| عنوان مقاله [English] | ||
| Extended Estimation of daily inflow of Sefidroud dam using meta-heuristic algorithms combined with fuzzy neural inference system | ||
| نویسندگان [English] | ||
| Hosein Hakimi Khansar1؛ Javad Parsa2؛ Omran Momeni Keleshteri1؛ Noorbakhsh Karami3؛ Moein Khoshdel sangdeh1 | ||
| 1PhD candidate, Department of Science and Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, Iran | ||
| 2Department of Water Engineering, University of Tabriz, Iran | ||
| 34- MSc in Construction Management, and Head of Sefidrood Dam and Powerhouse and Maintenance Department | ||
| چکیده [English] | ||
| Estimating water inflows to water resource systems is crucial for effective planning and optimal allocation of water resources across various consumption sectors. This study proposes a novel approach that combines Meta Heuristic algorithms, namely Water Cycle Algorithms (WCA), Gray Wolf Optimizer (GWO), Whale Optimization Algorithm (WOA), Neural Network Algorithm (NNA), and Grasshopper Optimization Algorithm (GOA), with a Neural-Fuzzy System for training and updating parameters. The objective is to develop accurate models for predicting the daily inflow of the Sefidroud reservoir dam. Unlike gradient-based algorithms, this method overcomes the challenges associated with training. The Autocorrelation Function and Correlation function were utilized to select four features: dam lake area, reservoir volume, reservoir level of the dam during the previous 7 days, and inflow in the previous day. Various statistical indicators were employed to evaluate the performance of the developed models. In the test stage, the ANFIS-WCA model demonstrated superior performance with the lowest values of SI (0.0736), MAE (0.05048), NRMSE (0.0736), and the highest value of R2 (0.9840). Based on the GPI index, the ANFIS-WCA model was identified as the best model, followed by ANFIS-NNA, ANFIS-GOA, and ANFIS-WOA models. Conversely, the ANFIS-GOA model exhibited the least accuracy. The results indicated that the ANFIS-WCA model outperformed the ANFIS-NNA model by 31% in terms of SI, and the ANFIS-GOA model by 1.6% in terms of SI. Furthermore, the GPI index revealed an improvement of up to 11% compared to the ANFIS-ANN model, and 20% compared to the ANFIS-GOA model. The high accuracy of the ANFIS-WCA model, compared to other hybrid models, highlights the effectiveness of the water cycle algorithm in combination with the ANFIS model. This approach proves to be a powerful tool for estimating the input discharge of Sefidroud dam, as it successfully avoids local optima. | ||
| کلیدواژه‌ها [English] | ||
| Fuzzy-neural-adaptive inference system, inflow, Meta-heuristic algorithm, Sefidroud dam, Water cycle algorithm | ||
| مراجع | ||
|
[1] A. Ebrahimzadeh, M. Zarghami, V. Nourani, Evaluation of earth dam overtopping risk by system dynamics, Monte-Carlo simulation and Latin Hypercube Sampling methods (case study: Hajilarchay Dam, Iran), Iran-Water Resources Research, 15(1) (2019) 14-31. [2] Ö. Kişi, River flow forecasting and estimation using different artificial neural network techniques, Hydrology research, 39(1) (2008) 27-40. [3] K.I. Hsu, H.V. Gupta, S. Sorooshian, Artificial neural network modeling of the rainfall‐runoff process, Water resources research, 31(10) (1995) 2517-2530. [4] C. Imrie, S. Durucan, A. Korre, River flow prediction using artificial neural networks: generalisation beyond the calibration range, Journal of hydrology, 233(1-4) (2000) 138-153. [5] P. Fathi, Y. Mohammadi, M. Homaee, Intelligent modeling of monthly flow time series into vahdat dam in sanandaj city, Water and Soil, 23(1) (2009). [6] O. Kisi, H. Kerem Cigizoglu, Comparison of different ANN techniques in river flow prediction, Civil Engineering and Environmental Systems, 24(3) (2007) 211-231. [7] F. J. Chang, Y. C. Chen, A counterpropagation fuzzy-neural network modeling approach to real time streamflow prediction, Journal of hydrology, 245(1-4) (2001) 153-164. [8] P.C. Nayak, K. Sudheer, D. Rangan, K. Ramasastri, A neuro-fuzzy computing technique for modeling hydrological time series, Journal of Hydrology, 291(1-2) (2004) 52-66. [9] H. Sanikhani, O. Kisi, River flow estimation and forecasting by using two different adaptive neuro-fuzzy approaches, Water resources management, 26(6) (2012) 1715-1729. [10] A. Lohani, R. Kumar, R. Singh, Hydrological time series modeling: A comparison between adaptive neuro-fuzzy, neural network and autoregressive techniques, Journal of Hydrology, 442 (2012) 23-35. [11] H. Emami, S. Emami, S. Heydari, Prediction Suspended Sediment Load of River Using Meta-heuristic Algorithms, Iranian Journal of Irrigation & Drainage, 13(5) (2019) 1426-1438. [12] S. Emami, J. Parsa, Comparising performance of meta-heuristic algorithms with the sediment rate curve (case study: Zarrineh Rood River), Watershed Engineering and Management, 13(1) (2021) 43-54. (in Persian) [13] A. Vafaeinejad, Z. Chatsimab, S. Bloori, F Mirdar Harijani, Optimization equation sediment rating curves in sediment discharge rate using particle swarm algorithm (PSO) and annealing (SA) (Case Study Bijar station), Natural Ecosystems of Iran, 8(3) (2017) 69-82. [14] H. Hakimi Khansar, A. Shabani chafjiri, Determining Effective Features for Estimating the Volume of Water Delivered to the Irrigation and Drainage Network using Artificial Intelligence Methods (Case study: Irrigation and Drainage Network of Sefidrood Dam), Water Management in Agriculture, 8(2) (2022) 117-134. (in Persian) [15] H. Eskandar, A. Sadollah, A. Bahreininejad, M. Hamdi, Water cycle algorithm – A novel metaheuristic optimization method for solving constrained engineering optimization problems, Computers & Structures, 110-111 (2012) 151-166. [16] S. Mirjalili, S.M. Mirjalili, A. Lewis, Grey wolf optimizer, Advances in engineering software, 69 (2014) 46-61. [17] S. Mirjalili, A. Lewis, The whale optimization algorithm, Advances in engineering software, 95 (2016) 51-67. [18] A. Sadollah, H. Sayyaadi, A. Yadav, A dynamic metaheuristic optimization model inspired by biological nervous systems: Neural network algorithm, Applied Soft Computing, 71 (2018) 747-782. [19] S.Z. Mirjalili, S. Mirjalili, S. Saremi, H. Faris, I. Aljarah, Grasshopper optimization algorithm for multi-objective optimization problems, Applied Intelligence, 48(4) (2018) 805-820. [20] J. S. Jang, ANFIS: adaptive-network-based fuzzy inference system, IEEE Transactions on Systems, Man, and Cybernetics, 23(3) (1993) 665-685. [21] K. Tanaka, An introduction to fuzzy logic for practical applications, 1996. [22] C. Ma, M. Iqbal, Statistical comparison of solar radiation correlations monthly average global and diffuse radiation on horizontal surfaces, Sol. Energy, 33 (1984) 143–148. [23] M. Dasineh, A. Ghaderi, M. Bagherzadeh, M. Ahmadi, A. Kuriqi, Prediction of hydraulic jumps on a triangular bed roughness using numerical modeling and soft computing methods, Mathematics, 9(23) (2021) 3135. [24] C.J. Willmott, K. Matsuura, On the use of dimensioned measures of error to evaluate the performance of spatial interpolators, International Journal of Geographical Information Science, 20(1) (2006) 89-102. [25] M.S. Lewis-Beck, Election forecasting: Principles and practice, The British Journal of Politics and International Relations, 7(2) (2005) 145-164. [26] O. Behar, A. Khellaf, K. Mohammedi, Comparison of solar radiation models and their validation under Algerian climate – The case of direct irradiance, Energy Conversion and Management, 98 (2015) 236-251. [27] R. Daneshfaraz, E. Aminvash, A. Ghaderi, J. Abraham, M. Bagherzadeh, SVM performance for predicting the effect of horizontal screen diameters on the hydraulic parameters of a vertical drop, Applied sciences, 11(9) (2021) 4238. [28] M. F. Li, X. P. Tang, W. Wu, H.B. Liu, General models for estimating daily global solar radiation for different solar radiation zones in mainland China, Energy Conversion and Management, 70 (2013) 139-148. [29] R. Stone, Improved statistical procedure for the evaluation of solar radiation estimation models, Solar energy, 51(4) (1993) 289-291. [30] C.M. Patino, J.C. Ferreira, Confidence intervals: a useful statistical tool to estimate effect sizes in the real world, Jornal Brasileiro de Pneumologia, 41 (2015) 565-566. [31] H. Hakimi Khansar, Simulation of behavior of the Kabudval Dam during construction with 3D numerical modeling, Amirkabir Journal of Civil Engineering, 53(9) (2021) 20-20.(in Persian) [32] J. Parsa, H. Hakimi Khansar, A. Hoseinzadeh dalir, J. Shiri, Simulation of soil stress in earth dams using artificial intelligence models and determination of effective features, Amirkabir Journal of Civil Engineering, (2021). (in Persian) [33] S. Maroufpoor, E. Maroufpoor, O. Bozorg-Haddad, J. Shiri, Z.M. Yaseen, Soil moisture simulation using hybrid artificial intelligent model: Hybridization of adaptive neuro fuzzy inference system with grey wolf optimizer algorithm, Journal of Hydrology, 575 (2019) 544-556. | ||
|
آمار تعداد مشاهده مقاله: 500 تعداد دریافت فایل اصل مقاله: 722 |
||