پیوندهای مفید
آمار
| تعداد نشریات | 8 |
| تعداد شمارهها | 437 |
| تعداد مقالات | 5,648 |
| تعداد مشاهده مقاله | 7,660,865 |
| تعداد دریافت فایل اصل مقاله | 6,329,038 |
مدلسازی تنش خاک در سدهای خاکی با روشهای هوش مصنوعی و تعیین ویژگیهای موثر | ||
| نشریه مهندسی عمران امیرکبیر | ||
| دوره 54، شماره 1، فروردین 1401، صفحه 247-262 اصل مقاله (2.01 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22060/ceej.2021.18682.6925 | ||
| نویسندگان | ||
| حسین حکیمی خانسر؛ چواد پارسا* ؛ علی دلیر حسین زاده؛ جلال شیری | ||
| دانشکده کشاورزی، دانشگاه تبریز، تبریز، ایران. . | ||
| چکیده | ||
| هدف کلی این مقاله انتخاب ویژگیهای موثر و مدلسازی تنش خاک در سدهای خاکی در زمان ساخت با شبکه عصبی به کمک یک الگوریتم بهینهساز و در ادامه نتایج مدل هیبریدی با روشهای مرسومANFIS وGEP مقایسه شده است. پنج ویژگی شامل تراز خاکریزی، زمان ساخت سد، تراز مخزن (آبگیری)، سرعت آبگیری و سرعت خاکریزی به عنوان ورودیهای مدل هیبریدی انتخاب شده است. با اجرای الگوریتم هیبریدی و تحلیل حساسیت و روش انتخاب ویژگی، تراز خاکریزی و زمان ساخت سد، مؤثرترین ویژگیها در مدلسازی تنش کل در سلولهای منتخب بودند؛ زیرا ترکیب دوتایی شامل تراز خاکریزی و زمان ساخت در سلولهای TPC25.1 و TPC25.3 و TPC25.4 به ترتیب با مقادیر خطا (MSE) برابر 1/523، 2/747 و 0/750 موثرترین ویژگیها در این سلولها بودند. در سلول TPC25.2 انتخاب سه ویژگی تراز خاکریزی، زمان ساخت و تراز مخزن با توجه به مقدار خطای 5/245 بیشترین تأثیر را در مدلسازی تنش کل خاک در این سلول داراست. مقایسه بین مدل ANN با ANFIS و GEP نشان داد، هر چند که اختلاف در دقت مدلها بسیار ناچیز است، میتوان گفت هر سه مدل جواب قابل قبول و نزدیک به هم داشتهاند. همچنین نتایج نشان میدهد که هر چه پراکندگی دادههای ورودی مدل بیشتر باشد، مدل استنتاج عصبی- فازی تطبیقی دارای توانایی بیشتری در شبیهسازی نسبت به دو مدل ANN و GEP است، زیرا در سلول TPC25.4 مدل ANFIS در دوره آزمون با شاخصهای آماری ، RMSE ، MAEو NS به ترتیب برابر مقادیر 0/9955، 0/0227، 0/0185 و 0/9666 دارای عملکرد بهتری نسبت به دو مدل دیگر است. | ||
| کلیدواژهها | ||
| سد خاکی؛ الگوریتم هیبریدی PSO-ANN؛ انتخاب ویژگی؛ سیستم استنتاج عصبی- فازی تطبیقی؛ تنش قائم خاک | ||
| موضوعات | ||
| سدهای خاکی؛ شبکه های عصبی | ||
| عنوان مقاله [English] | ||
| Simulation of soil stress in earth dams using artificial intelligence models and determination of effective features | ||
| نویسندگان [English] | ||
| Arvand Hakimi Khansar؛ Javad Parsa؛ Ali Hoseinzadeh dalir؛ Jalal Shiri | ||
| PhD candidate, Department of Science and Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, Iran | ||
| چکیده [English] | ||
| The general purpose of this paper is to select effective features and model soil stress in earth dams during construction. Five features, including fill level, duration of construction, reservoir level (impoundment), impounding rate and fill rate, were selected as hybrid model inputs. By performing hybrid algorithm and sensitivity analysis and feature selection method, fill level and duration of construction were recognized as the most effective features in modeling the total stress in selected cells, because concurrent mean square error values for the fill level and duration of construction in TPC25.1, TPC25.3 and TPC25.4 cells were 1.523, 2.747 and 0.750, respectively. In TPC25.2 cell, three features including fill level, duration of construction and impoundment level, had the greatest effect in modeling the total soil stress based on the mean square error value of 5.245. Comparison of the results of the ANN model with ANFIS and GEP showed that although the difference in the accuracy of the models is very small, all three models had acceptable results in the test step, the ANFIS model results indicated that the statistical error measures of , RMSE, MAE and NS in TPC25.4 cell were 0.9955, 0.0227, 0.0185 and 0.9666, respectively. It showed that how much the input data are more scattered, the ANFIS model had more capability than ANN and GEP models to simulate the soil stress in the studied earth dam. | ||
| کلیدواژهها [English] | ||
| Earth dam, PSO-ANN hybrid algorithm, Feature selection, ANFIS, Soil vertical stress | ||
| مراجع | ||
|
[1] Nourani, E. Sharghi, MH. Aminfar. (2012). Integrated ANN model for earthfill dams seepage analysis: Sattarkhan dam in Iran. Artificial Intelligence Research, 1(2), 22-37. (In Persian) [2] A. Ebrahimzadeh, M. Zarghami and V. Nourani. (2019). Evaluation of Earth Dam Overtopping Risk by System Dynamics, Monte-Carlo Simulation and Latin Hypercube Sampling Methods (CaseStudy: Hajilarchay Dam, Iran). Iran-Water Resources, 15(1), 14-31. (In Persian) [3] Vafaeian. (2015). Earth dams & rockfill dams. Isfahan: Arkan Danesh. 464p. [4] Salmasi, H. Hakimi Khansar B. Norani, (2019). Investigation of the Structure of the Dam Body during Construction and its Comparison with the Analytical Results Using PLAXIS Software (the Case Study of Kaboodvall Dam). JWSS, 22(4), 155-171. (In Persian) [5] A. Zomoredian, H. Chochi. (2013). Numerical analysis of soil-gravel dam behavior during construction and first dewatering (Case study: Masjed Soleiman Dam). JWSS, 16(62), 229-242. (In Persian) [6] Vafaeian. (2015). Earth dams & rockfill dams. Isfahan: Arkan Danesh. 464p. [7] Komasi, B. Beiranvand. (2019). Study of Hydraulic Failure Mechanism in Core of Earth Dam (A Case Study: Taj-Amir Norabad Dam). Tectonics Journal, 9(3), 57-69(In Persian). [8] Hakimi Khansar, S.H. Golmai, M. Sheydaiyan. (2015). Kaboodval behavior earthen dam during construction of the finite element method with software PLAXIS and compared with data from instrumentation. Journal of water science engineering, 5(11), 77-92. (In Persian) [9] Tayfure, D. Swiatek, A. Wita, VP. Singh. (2005). Case study: finite element method and artificial neural network models for flow through Jeziorsko earthfill dam in Poland. Journal of Hydraulic Engineering, 131(6), 431–440. [10] Nourani. (2015). Basics of hydroinformatics ANFIS model for multi-station modelling of rainfall–runoff process. Journal of Hydrology, 490, 41-55(In Persian). [11] Sharghi, V Norani, N. Behfar. (2020). Implementation of Data Jittering Technique for Seepage Analysis of Earth fill Dam Using Ensemble of AI Models. Water and Soil Science- University of Tabriz, 30(1), 29-41. (In Persian) [12] Wu, C. Soci, P.P. Shum, I. Zheludev. (2014). Computing matrix inversion with optical networks. Optics Express, 22(1), 295–304. [13] Cucci, G. Lacolla, M. Pagliai and N. Vignozzi. (2015). Effect of reclamation on the structure of silty-clay soils. International Agrophysics Journal, 29, 23-30. [14] Chandrashekar, and F. Sahin. (2014). A survey on feature selection methods. Computers and Electrical, 40, 16–28. [15] Rankovic, N. Grujovic, D. Divac, N. Milivojevic. (2014). Development of support vector regression. Structural Safety, 48, 33-39. [16] Novakovic, V. Rankovic, N. Grujovic,D. Divac, N. Milivojevic. (2014). Development of neuro-fuzzy model for dam seepage analysis. Annals of the Faculty of Engineering Hunedoara, 12(2), 133-136. [17] Nourani, and A. Babakhani. (2013). Integration of Artificial Neural Networks with Radial Basis Function Interpolation in Earthfill Dam Seepage Modeling. Journal of Computing in Civil Engineering, 27(1), pp.183-195. (In Persian) [18] Salmasi, H. Hakimi Khansar. (2020). Simulation of behavior the Kabudval Dam during construction with 3D numerical modeling. Amirkabir Journal of Civil Engineering, doi: 10.22060/ceej.2020.18172.6790. (In Persian) [19] Regional Water Company of Golestan. (2013). Reporting the Behavior of Kabudwal Dam Golestan. Golestan: Kabudwal Dam Behavior Report.32-52. [20] Kennedy. (2010). Particle Swarm Optimization. Encyclopedia of Machine Learning, 760-766. [21] Kumar, and S. Minz. (2014). Feature selection, a literature review. Smart Computing Review, 4(3), 211-229. [22] R. Aghaebrahimi, H. Taherian, I. Nazer-Kakhki, M. Farshad, S. R. Goldani. (2014). Short Term Price Forecasting in Electricity Market Considering the Effect of Wind Units' Generation. Scientific Journal of Computational Intelligence in Electrical Engineering, 5(4), 105-122. (In Persian) [23] C. Hill. (1998). Methods and Guidelines for Effective Model Calibration. U.S. Geological Survey Water. [24] Jang, C.T. Sun, E. Mizutani. (1997). Neurofuzzy and Software Computing: a Computational Approach to Learning and Machine Intelligence. New Jersey. Prentice-Hall. [25] Nourani, o. Kisi, M. Komasi. (2011). Two hybrid artificial intelligence approaches for modeling rainfall–runoff process. Journal of Hydrology, 402, 41–59. (In Persian) [26] Kia. (2012). Soft computing in Matlab. ehran: Kian Publication. [27] Ferreira, (2001). Gene expression programming: a new adaptive algorithm for solving problems. 13, 87-129. [28] Nouri, and F. Salmasi. (2017). Predicting Seepage of Earth Dams using Artificial Intelligence Techniques. Irrigation Sciences and Engineering (JISE), 42(1), p. 83-97. (In Persian) [29] AmiriMijan, H. Shirani, I. Esfandiarpour1, A.Besalatpour and H. Shekofteh. (2019). Identifying the Determinant Factors Influencing S Index in Calcareous. Journal of Water and Soil Science, 23(3), 381-394(In Persian). [30] Can, I.C. Yerdelen. (2007). Stochastic modeling of Karasu River (Turkey) using the methods of Artificial Neural Networks. Hydrology Days, 138-144. | ||
|
آمار تعداد مشاهده مقاله: 1,046 تعداد دریافت فایل اصل مقاله: 1,264 |
||