هیدروفیزیک

هیدروفیزیک

مقایسه ضریب دبی سرریز کنگره‌ای قوسی وکلیدپیانویی قوسی با استفاده از روش‌های هوش مصنوعی

نوع مقاله : مقاله پژوهشی

نویسندگان
1 گروه عمران، دانشکده فنی و مهندسی، دانشگاه آزاد اسالمی، واحد ملکان، آذربایجان شرقی، ایران
2 دانشجوی دکتری، مهندسی عمران- آب و سازه‌های هیدرولیک - دانشگاه مراغه، مراغه، ایران
3 دانشیار دانشگاه مراغه - گروه مهندسی عمران، دانشگاه مراغه، مراغه، ایران
4 دانشجوی کارشناسی ارشد، مهندسی عمران - آب و سازه‌های هیدرولیکی - دانشگاه مراغه، مراغه، ایران
5 کارشناسی ارشد، مهندسی عمران - آب و سازه‌های هیدرولیکی-دانشگاه مراغه، مراغه، ایران
6 دانشجوی کارشناسی ارشد، مهندسی عمران - آب و سازه‌های هیدرولیکی-دانشگاه مراغه، مراغه، ایران
چکیده
در این پژوهش عملکرد الگوریتم‌‌های ANN و SVM در پیش‌بینی ضریب دبی سرریز کنگره‌ای قوسی و کلیدپیانویی قوسی به کمک 243 سری داده‌ی آزمایشگاهی کروکستون برای سناریو اول و 170 سری داده‌ی آزمایشگاهی دانشگاه مراغه برای سناریو دوم بررسی شده است. پارامترهای هندسی و هیدرولیکی مورد استفاده در این پژوهش شامل نسبت بار آبی کل(H_T/p) ، بزرگ نمایی (L_C/W)، زاویه سیکل قوسی (Ɵ)، زاویه دیواره سیکل(α) ، فرود(Fr) ، نسبت طول داخلی دماغه به عرض سرریز (A/W) و ضریب دبی (Cd) می‌باشد. نتایج هوش مصنوعی نشان داد که ترکیب پارامترهای(Cd, H_T/p, α, Ɵ) در الگوریتم‌‌های SVM وANN در مرحله‌ آموزش مربوط به سناریو‌ی اول به ترتیب برابر است با (9876/0=(R2، (0217/0=(RMSE، (9888/0=(DC و (9637/0=(R2، (0636/0=(RMSE، (8966/0=(DC و ترکیب پارامترهای(Cd, H_T/p, L_C/W, Ɵ, A/W, Fr) در الگوریتم‌‌های SVM وANN در مرحله‌ آموزش مربوط به سناریو‌ی دوم به ترتیب برابر است با (9876/0=(R2، (0217/0=(RMSE، (9888/0=(DC و (9637/0=(R2، (0636/0=(RMSE، (8966/0=(DC می‌باشند که در مقایسه با دیگر ترکیب‌ها منجر به بهینه‌ترین خروجی شده است که نشان‌دهنده دقت بسیار مطلوب هر دو الگوریتم‌ SVM وANN در پیش‌بینی ضریب دبی سرریز غیرخطی قوسی و کلیدپیانویی قوسی است. نتایج آنالیز حساسیت نشان داد که پارامتر موثر در تعیین ضریب دبی پارامتر نسبت بار آبی کل(H_T/p) می‌باشد.
کلیدواژه‌ها

موضوعات


عنوان مقاله English

Comparison of Discharge Coefficient of Arced labyrinth Weir and Arced Piano Key Weir Using Artificial Intelligence Methods

نویسندگان English

Mehdi Kougdaragh 1
Tohid Omidpour 2
Mehdi MajediAsl 3
Rahman Masoumpour 4
Morteza Ayami lord 5
َAghil Jasem Abil 6
1 Department of Civil Engineering, Faculty of Engineering, Malekan Islamic Azad University, East Azarbaijan, Iran
2 , Department of Civil Engineering, Faculty of Technology and Engineering, University of Maragheh, Maragheh, Iran
3 Associate Professor, Department of Civil Engineering, Maragheh University, Maragheh, Iran
4 , Department of Civil Engineering, Maragheh University, Maragheh, Iran
5 , Department of Civil Engineering, Maragheh University, Maragheh, Iran
6 , Department of Civil Engineering, Maragheh University, Maragheh, Iran
چکیده English

This research explores the effectiveness of Artificial Neural Networks (ANN) and Support Vector Machine (SVM) algorithms in predicting the discharge coefficient of arced Labyrinth weirs and arced piano key weirs. The analysis utilizes 243 laboratory data series from Crookston for a first scenario and 170 laboratory data series from Maragheh University Laboratory for a second scenario. The geometric and hydraulic parameters used in this research include total water load ratio (), magnification (), arc cycle angle (Ɵ), cycle wall angle (α), Froude Number (Fr), The ratio of the internal length of the nose to the width of each cycle () and the flow coefficient (Cd). The results of artificial intelligence show that the combination of parameters (Cd, , α, Ɵ) in ANN and SVM algorithms in the training phase related to the first scenario is respectively equal to (R2=0.9984(, (RMSE=0.0057), and (R2=0.9881), (RMSE=0.0190). Moreover, combination of parameters (Cd, , , Ɵ, , Fr) in ANN and SVM algorithms in the training phase of the second scenario are respectively equal to (R2=0.9924), (RMSE=0.0056), and (R2=0.9622), (RMSE=0.0156) which leads to the most optimal output compared to other combinations, and shows both ANN and SVM algorithms give very desirable accuracy in predicting the discharge coefficient of arced Labyrinth and arced piano key weirs. The results of the sensitivity analysis show that the effective parameter in determining the discharge coefficient of arced Labyrinth weir and the arced piano key weir is the total water load ratio parameter ().

کلیدواژه‌ها English

Sensitivity Analysis
Nonlinear Weir
Piano Keyboard Weir
Discharge Coefficient
ANN Software
SVM Software
[1] Gentilini B. Stramazzi con cresta a pianta obliqua e a zig-zag. Memorie e Studi dell instituto di Idraulica e Construzioni Idrauliche Del Regil Politecnico di Milano, 48, in Italian. 1949.
 [2] Taylor G. The performance of labyrinth weirs [Doctoral dissertation]. University of Nottingham; 1968.
[3] Darvas LA. Discussion of “Performance and design of labyrinth weirs”. Journal of the Hydraulics Division. 1971 Aug; 97(8):1246-51.
[4] Tullis JP, Amanian N, Waldron D. Design of labyrinth spillways. Journal of hydraulic engineering. 1995 Mar; 121(3):247-55.
[5] Ghodsian M. Stage–discharge relationship for a triangular labyrinth spillway. In: Proceedings of the Institution of Civil Engineers-Water Management. 2007; 162(3), 173-178.
[6] Crookston BM. Labyrinth weirs. [Ph.D. thesis]. Logan, UT: Utah State University; 2010.
[7] Crookston BM, Tullis BP. Hydraulic design and analysis of labyrinth weirs. I: Discharge relationships. Journal of Irrigation and Drainage Engineering. 2013 May 1; 139(5):363-70.
[8] Crookston BM, Tullis BP. Arced labyrinth weirs. Journal of Hydraulic Engineering. 2012 Jun 1; 138(6):555-62.
[9] Christensen NA, Tullis BP. Arced Labyrinth Weir Flow Characteristics. 4th International Junior Reasercher and Enginner Workshap on Hydraulic Structures. IJREWHS’ 12. B. Tullis and R. Janssen (Eds.), Logan, USA: Utah State University; 2012.
[10] Azarpeyvand H, Emadi A R and Sedghi Asl M. An Experimental Study of the Discharge of the Length Increase Effect on the Composite Trapezoidal Labyrinth Spillway. Journal of Water and Soil Science. 2019; 23 (1):405-418.
[11] Kabiri-Samani A, Javaheri A. Discharge coefficients for free and submerged flow over Piano Key weirs. Journal of hydraulic research. 2012 Feb 1; 50(1):114-20.
[12] Safarzadeh A, Noroozi B. Three dimensional hydrodynamics of arced piano key spillways. Journal of Hydraulics. 2014 Nov 22; 9(3):61-79. (In Persian)
[13] Abbaspour A, Arvanaghi H. Forecasting the flow on the triangular-rectangular compound overflow using planning. In: The 10th Iran Hydraulic Conference; 2011.
[14] Farrokhy A, Givachy A and Azhdary moghaddam M. Estimating Determining the Discharge Coefficient of lateral weirs with neural network and adaptive neural-inference system. 6th National Congress of Civil Engineering; 2009; Semnan, Iran. (In Persian)
[15] Majedi Asl M, Fuladipanah M. Application of the evolutionary methods in determining the discharge coefficient of triangular labyrinth weirs. JWSS-Isfahan University of Technology. 2019 Mar 10; 22(4):279-90.
[16] Haghiabi A, Parsaie A, Shamsi Z. Intelligent mathematical modeling of discharge coefficient of nonlinear weirs with triangular plan. AUT Journal of Civil Engineering. 2019 Dec 1; 3(2):149-56.
[17] Majedi Asl M, Valizadeh S. Application of SVM algorithm in predicting vertical pier scour depth. JWSS-Isfahan University of Technology. 2019 Dec 10; 23(4):165-81.
[18] Roushangar K, Majedi Asl M, Shahnazi S. Hydraulic performance of PK weirs based on experimental study and kernel-based modeling. Water Resources Management. 2021 Sep; 35:3571-92.
[19] Fuladipanah M, Majedi Asl M, Haghgooyi A. Application of intelligent algorithm to model head-discharge relationship for submerged labyrinth and linear weirs. Journal of Hydraulics. 2020 Jul 22; 15(2):149-64.
[20] Roushangar K, Alami MT, Shiri J, Majedi Asl M. Determining discharge coefficient of labyrinth and arced labyrinth weirs using support vector machine. Hydrology research. 2018 Jun 1; 49(3):924-38.
[21] Majedi Asl M, Fuladipanah M, Arun V, Tripathi RP. Using data mining methods to improve discharge coefficient prediction in Piano Key and Labyrinth weirs. Water Supply. 2022 Feb 1; 22(2):1964-82.
[22] Sohrabi F, Majedi Asl M, Omidpour Alavian T and Shamsi V.  Investigation of the effect of the prediction angle of the discharge coefficient in arced Labyrinth Weirs using vector machine tool (SVM). In: the first national conference of modern exhibitions. Civil and environmental engineering; 2022; Ramsar, Iran.
[23] Sohrabi F, Majedi Asl M, Omidpour Alavian T and Shamsi V.  Investigating the effect of angle in predicting the discharge coefficient in arced Labyrinth Weirs using the GEP gene expression programming algorithm.IN: the first national conference on modern approaches in civil engineering and environment; 2022; Ramsar, Iran.
[24] Omidpour Alavian T, Majedi Asl M, Soltani M, Mohammadi E, Shamsi V.  Comparison of the hydraulic efficiency of Labyrinth Weirs with quarter-circle and semi-circular crown shape using met model method (ANN). In: 8th International Congress on Civil Engineering, Architecture and Urban Development; 2023 March 07-09; Tehran, Iran.
[25] Omidpour Alavian T, Majedi Asl M, Sohrabi F, Shamsi V and Ayami M. Modeling and evaluation of the discharge coefficient of an arced Labyrinth with the ANN met model method. In: the first modern national conference in civil and environmental engineering. 2022; Ramsar, Iran.
[26] Omidpour Alavian T, Majedi Asl M, Soltani M, Shamsi V.  Comparison of the hydraulic efficiency of Labyrinth Weirs with quarter-circle and semi-circular crown shapes using met model methods (ANN). In: 8th International Congress on Civil Engineering, Architecture and Urban Development; 2023 March 07-09, Tehran, Iran.
[27] Majedi Asl M, Omidpour Alavian T, Kouhdaragh M, Shamsi V. Comparison of Hydraulic Efficiency of Arched Non-linear Weirs in Plan Using GEP and SVM Neural Networks. JWSS-Isfahan University of Technology. 2023 Dec 10; 27(3):179-99.
[29] Majedi Asl M, Omidpour Alavian T and Kouhdaragh M. Laboratory Investigation of the Effect of Wall Slope on the Discharge Coefficient of Trapezoidal Arced Labyrinth Weirs. Jwss 2023; 27 (4):281-297.
[30] Majedi Asl M, Ghaderi A, Kouhdaragh M, Omidpour Alavian T. A performance comparison of the Meta model methods for discharge coefficient prediction of labyrinth weirs. Flow Measurement and Instrumentation. 2024 Apr 1; 96:102563.
[31] Henderson FM. open channel flow. USA: New York; Macmillan; 1996
[32] Vapnik VN. The nature of statistical learning theory. USA: New York: Springer; 1995.

  • تاریخ دریافت 14 تیر 1403
  • تاریخ بازنگری 27 مرداد 1403
  • تاریخ پذیرش 28 شهریور 1403