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.
Havacılık ve Uzay Teknolojileri Dergisi


Computational investigation of rotorcraft avionics bay cooling system
Akın, Altuğ; Kahveci, Harika Senem; Department of Aerospace Engineering (2019)
Computational investigation of a rotorcraft avionics bay cooling system is performed. Within the introduced system, the ambient air is supplied to the avionics-bay by a fan and exhausted back into the ambient after cooling the equipment inside. Depending on the fan and exhaust locations, hot zones may form around some of the equipment. The fan must provide a sufficiently high mass flow rate to keep the temperatures of the avionics equipment below the limits, while avoiding excessive amount of cooling to red...
Improving flow structure and natural convection within fin spacings of plate fin heat sinks
Özet, Mehmet Erdem; Tarı, İlker; Department of Mechanical Engineering (2015)
The main objectives of this thesis are to numerically investigate the previously observed recirculation zones and longitudinal vortices that occur in low fin height plate finned horizontal heat sinks and to improve the flow structures and heat transfer in these zones using various approaches with the help of simulations performed using commercially available CFD software. The approaches used for improvements are replacing the outer most fins with higher ones, introducing gaps on the length of the fins in va...
Application of numerical shape optimization to the runner blades of a francis turbine
Yalılı, Mehmet; Aksel, Mehmet Haluk; Department of Mechanical Engineering (2015)
The multi-objective design of hydraulic turbines using computational fluid dynamics software has been an important subject in turbomachinery area recently. Researches focus especially on obtaining higher turbine efficiency by the improvement of runner shapes. Thus in the present study, a multi-objective shape optimization procedure was applied to improve the runner blade shapes of a small Francis turbine named as GAMM turbine which was selected from the literature. CFD computations as well as blade generati...
Design and analysis of a vertical axis water turbine for river applications using computational fluid dynamics
Demircan, Eren; Aksel, Mehmet Haluk; Pınarcıoğlu, Mehmet Melih; Department of Mechanical Engineering (2014)
The main purpose of this study is to design a Darrieus rotor type vertical axis water turbine using Computational Fluid Dynamics (CFD) in order to be used in river currents. The CFD modeling is based on two dimensional numerical solution of the rotor motion using commercial Unsteady Reynolds Averaged Navier-Stokes solvers, Ansys Fluent and CFX. To validate the two dimensional numerical solution, an experimental Darrieus rotor type water turbine from literature is studied and performance of several turbulenc...
Development of artificial neural network based design tool for aircraft engine bolted flange connection subject to combined axial and moment load
Sanlı, Tahir Volkan; Kayran, Altan; Department of Aerospace Engineering (2018)
In this thesis, a design tool using artificial neural network (ANN) is developed for the bolted flange connections, which enables the user to analyze typical aircraft engine connections subjected to combined axial and bending moment in a fast yet very accurate way. The neural network trained for the design tool uses the database generated by numerous finite element analyses for different combinations of parametric design variables of the bolted flange connection. The defined parameters are the number of bol...
Citation Formats
A. Akin and H. S. Kahveci, “Use of artificial neural network in rotorcraft cooling system ,” Havacılık ve Uzay Teknolojileri Dergisi, pp. 157–170, 2019, Accessed: 00, 2021. [Online]. Available: