Döner Kanatlı Uçak Soğutma Sisteminde Yapay Sinir Ağı Kullanımı

Bu çalışmada, döner kanatlı bir uçağın aviyonik bölmesinde bulunan aviyonik ekipmanın yüzey sıcaklıklarının belirlenmesinde bir Yapay Sinir Ağı (YSA) kullanılmıştır. Bu bölme, içeriye dış ortam havasını tedarik eden bir fan ve bir egzoz sistemi tarafından soğutulmaktadır. Fan ve egzoz yerleri ve fan debisi şeklindeki girdiler kullanılarak bir İleri Beslemeli Çok Katmanlı YSA’dan faydalanılmıştır. Ağın eğitiminde çok sayıda Hesaplamalı Akışkanlar Dinamiği (HAD) analizinden elde edilen sonuçlar kullanılmıştır. Farklı YSA mimarilerinin kullanımıyla YSA algoritmasının doğruluğu üzerine yapılan analiz sonucunda, gizli katmanda on beş sinir hücresi bulunan bir YSA’nın değerlendirilen diğer seçenekler içerisinde en iyi doğruluğu sağladığı ortaya çıkmıştır. Eğitim verisinin büyüklüğü dereceli olarak artırılmış ve bunun YSA algoritmasının tahmin doğruluğu üzerindeki etkisi de incelenmiştir. Daha sonra YSA’nın regresyon kabiliyeti, sıklıkla kullanılan bir tam karesel doğrusal model ile oluşturulan yanıt yüzeyi ile karşılaştırılmıştır. Karşılaştırma, YSA’nın aviyonik yüzey sıcaklıklarını çok daha iyi bir doğrulukla tahmin ettiğini göstermektedir.

Use of Artificial Neural Network in Rotorcraft Cooling System

In this study, an Artificial Neural Network (ANN) is used to determine the surface temperatures of the avionics equipment located in an avionics bay of a rotorcraft. The bay is cooled via a system of a fan that supplies ambient air to the interior of the bay and an exhaust. A Feedforward Multi-Layer ANN is used with the input parameters of the fan and exhaust locations and the air mass flow rate of the fan. For training of the network, the results obtained by a large number of Computational Fluid Dynamics (CFD) analyses are used. An analysis on the accuracy of the ANN algorithm through the use of different ANN architectures revealed that an ANN with fifteen neurons in the hidden layer provides the best accuracy among the considered options. The size of the training data is increased progressively and its effect on the prediction accuracy of the ANN algorithm is also observed. The regression capability of the ANN is later compared with a response surface built by a commonly used full quadratic linear model. The comparison shows that the ANN predicts the avionics surface temperatures with much better accuracy.

PDF

___

[1] U. K. Mallela and A. Upadhyay, “Buckling Load Prediction of Laminated Composite Stiffened Panels Subjected to In-Plane Shear Using Artificial Neural Networks,” Thin-Walled Structures, Vol. 102, pp. 158-164, 2016.
[2] A. Z. Al-Garni, “Neural Network-Based Failure Rate for Boeing-737 Tires,” Journal of Aircraft, Vol. 34, pp. 771-777, 1997.
[3] F. Mazhar, A. M. Khan, I. A. Chaudhry and M. Ahsan, “On Using Neural Networks in UAV Structural Design for CFD Data Fitting and Classification,” Aerospace Science and Technology, Vol. 30, pp. 210-225, 2013.
[4] S. J. Schreck, W. E. Faller and M. W. Luttges, “Neural Network Prediction of Three-Dimensional Unsteady Separated Flowfields,” Journal of Aircraft, Vol. 32, pp. 178-185, 1995.
[5] J. Yu and J. S. Hesthaven, “Flowfield Re-construction Method Using Artificial Neural Network,” AIAA Journal, Vol. 57, pp. 482-498, 2019.
[6] Z. Li, X. Sun, C. Hu, G. Liu and B. He, “Neural Network Based Online Predictive Guidance for High Lifting Vehicles,” Aerospace Science and Technology, Vol. 82-83, pp.149-160, 2018.
[7] L. Huang, C. Ma, Y. Li, J. Gao and M. Qi, “Applying Neural Networks (NN) to the Improvement of Gasoline Turbocharger Heat Transfer Modeling,” Applied Thermal Engineering, Vol. 141, pp. 1080-1091, 2018.
[8] R. G. Peyvandi and S. Z. I. Rad, “Precise Prediction of Radiation Interaction Position in Plastic Rod Scintillators Using a Fast and Simple Technique: Artificial Neural Network,” Nuclear Engineering and Technology, Vol. 50, pp.1154-1159, 2018.
[9] K. Ye, Y. Zhang, L. Yang, Y. Zhao, N. Li and C. Xie, “Modeling Convective Heat Transfer of Supercritical Carbon Dioxide Using an Artificial Neural Network,” Applied Thermal Engineering, Vol. 150, pp. 686-695, 2019.
[10] A. Mitra, A. Majumdar, P. K. Majumdar and D. Bannerjee, “Predicting Thermal Resistance of Cotton Fabrics by Artificial Neural Network Model,” Experimental Thermal and Fluid Science, Vol. 50, pp. 172-177, 2013.
[11] G. D. Nicola, M. Pierantozzi, G. Petrucci and R. Stryjek, “Equation for the Thermal Conductivity of Liquids and an Artificial Neural Network,” Journal of Thermophysics and Heat Transfer, Vol. 30, pp. 651-660, 2016.
[12] M. H. Esfe, M. R. H. Ahangar, D. Toghraie, M. H. Hajmohammad, H. Rostamian and H. Tourang, “Designing Artificial Neural Network on Thermal Conductivity of Al2O3-Water-EG (60-40%) Nano-fluid Using Experimental Data,” Journal of Thermal Analysis and Calorimetry, Vol. 126, pp. 837-843, 2016.
[13] D. C. Montgomery, “Design and Analysis of Experiments,” 8th ed. Hoboken, NJ: John Wiley & Sons, 2009.
[14] ANSYS Fluent User’s Guide, Release 18.1, Canonsburg, PA: ANSYS, Inc., 2017.
[15] SAE International, “Aerothermodynamics Systems Engineering and Design,” Warrendale, PA, SAE Aerospace Information Report, 1168/3, 1990.
[16] S. Marsland, “Machine Learning: An Algorithmic Perspective,” 2nd ed. Boca Raton, FL: CRC Press, 2015.
[17] D. Svozil, V. Kvasnicka and J. Pospichal, “Introduction to Multi-Layer Feed-Forward Neural Networks”, Chemometrics and Intelligent Laboratory Systems, Vol. 39, pp. 43-62, 1997.
[18] MATLAB User Guide, Release 2016a, Natick, MA: The MathWorks Inc., 2016.
[19] D. J. C. Mackay, “A Practical Bayesian Framework for Backpropagation Networks,” Neural Computation, Vol. 4, pp. 448-472, 1992.
[20] A. T. Goh, “Some Civil Engineering Applications of Neural Networks,” Proceedings of the Institution of Civil Engineers - Structures and Buildings, Vol. 104, pp. 463–469, 1994.