IJE TRANSACTIONS C: Aspects Vol. 27, No. 6 (June 2014) 819-828   

downloaded Downloaded: 355   viewed Viewed: 2007

A. R. Davari, M. R. Soltani and S. Attarian
( Received: September 04, 2013 – Accepted: December 12, 2013 )

Abstract    A new approach based on a Generalized Regression Neural Network (GRNN) has been proposed to predict the planform surface pressure field on a wing-tail combination in low subsonic flow. Extensive wind tunnel results were used for training the network and verification of the values predicted by this approach. GRNN has been trained by the aforementioned experimental data and subsequently was used as a prediction tool to determine the surface pressure. Most of the previous applications of the GRNN in prediction problems were restricted to single or limited outputs, while in the present method the entire planform surface pressure was predicted at once. This highly decreases the calculation time while preserving a remarkable degree of accuracy. The wind tunnel results verify the accuracy of the data offered by the GRNN, which indicates that the present prediction and optimization tool provides sufficient accuracy with modest amount of experimental data.


Keywords    Canard, GRNN, POrediction, Flowfield


چکیده    در این مقاله یک روش جدید بمبنای شبکه عصبی مصنوعی GRNN پیشنهاد گردیده که برمبنای آن می توان توزیع فشار روی سطح یک بالک کنترلی را روی کل سطح به طور همزمان در جریان زیرصوت پیش بینی نمود. جهت آموزش شبکه و بررسی صحت نتایج پیش بینی شده، آزمایش های گسترده ایی در تونل باد روی یک ترکیب بدنه-بالک کنترلی انجام و یک بانک اطلاعاتی از نتایج آن تدوین گردید. در مسائل معمول تخمین با استفاده از شبکه GRNN، معمولا یک یا چند خروجی معدود از این شبکه استخراج می شود. یکی از نقاط قوت الگوریتم استفاده شده در این مقاله تخمین میدان جریان روی سطح بالک به طور کامل و همزمان است که در عین برخورداری از دقت مناسب، در کوتاه ترین زمان ممکن محاسبات مربوطه را به انجام می رساند. مقایسه نتایج تخمین GRNN و داد های تونل باد، دقت نتایج تخمین را تایید نموده اند.



1.        Mori, R. and Suzuki, S., "Neural network modeling of lateral pilot landing control", Journal of Aircraft,  Vol. 46, No. 5, (2009), 1721-1726.

2.        Basu, J.K., Bhattacharyya, D. and Kim, T.-h., "Use of artificial neural network in pattern recognition", International Journal of Software Engineering & Its Applications,  Vol. 4, No. 2, (2010).

3.        Austin, N., Kumar, P.S. and Kanthavelkumaran, N., "Artificial neural network involved in the action of optimum mixed refrigerant (domestic refrigerator)", International Journal of Engineering (1025-2495),  Vol. 26, No. 10, (2013)

4.        Deswal, S. and Pal, M., "Artificial neural network based modeling of evaporation losses in reservoirs", Proceedings of World Academy of Science: Engineering & Technology,  Vol. 41, (2008)

5.        WALSH, J. and ROGERS, J., "Aerodynamic performance optimization of a rotor blade using a neuralnetwork as the analysis",  (1992).

6.        McMillen, R.L., Steck, J.E. and Rokhsaz, K., "Application of an artificial neural network as a flight test data estimator", Journal of aircraft,  Vol. 32, No. 5, (1995), 1088-1094.

7.        Faller, W.E. and Schreck, S.J., "Real-time prediction of unsteady aerodynamics: Application for aircraft control and manoeuvrability enhancement", Neural Networks, IEEE Transactions on,  Vol. 6, No. 6, (1995), 1461-1468.

8.        Lo, C.F., Zhao, J.L. and DeLoach, R., "Application of neural networks to wind tunnel data response surface methods", in 21 st AIAA Aerodynamics Measurement Technology and Ground Testing Conference, (2000), 19-22.

9.        Berdahl, C., "Neural network detection of shockwaves", AIAA journal,  Vol. 40, No. 3, (2002), 531-536.

10.     Rae, W.H. and Pope, A., "Low-speed wind tunnel testing, John Wiley,  (1984)

11.     Beckwith, T.G., Marangoni, R.D. and Lienhard, J.H., "Mechanical measurements, Pearson Prentice Hall,  (2007)

12.     Davari, A.R., Hadi Dulabi, M., Soltani, M.R. and Askari, F., "Impact of body on the tail surface flowfield at high incidences", Journal of Aerospace Science and Technology; JAST,  Vol. 6, No. 1, (2009)

13.     Specht, D.F., "A general regression neural network", Neural Networks, IEEE Transactions on,  Vol. 2, No. 6, (1991), 568-576.

14.     Parzen, E., "On estimation of a probability density function and mode", Annals of mathematical statistics,  Vol. 33, No. 3, (1962), 1065-1076.

15.     Cacoullos, T., "Estimation of a multivariate density", Annals of the Institute of Statistical Mathematics,  Vol. 18, No. 1, (1966), 179-189.

16.     Bauer, M.M., "General regression neural network for technical use", Master's Thesis, University of Wisconsin-Madison, (1995).

International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir