A deep learning methodology for the flow field prediction around airfoils

Download
2021-9-07
Duru, Cihat
This study aims to predict flow fields around airfoils using a deep learning methodology based on an encoder-decoder convolutional neural network. Neural network training and evaluation are performed from a set of computational fluid dynamics (CFD) solutions of the 2-D flow field around a group of known airfoils at a wide range of angles of attack. Reynolds averaged Navier-Stokes (RANS)-based CFD simulations are performed at a selected Mach number on the transonic regime on high-quality structured computational grids. The results of these simulations are utilized as training data set. For better shape learning, a distance map is generated from airfoil shape and provided to the algorithm at data locations of the flow quantities, i.e., pressure coefficient, Mach number, relative to the airfoil shape. The predictive ability of the model is scrutinized both qualitatively and quantitatively. The flow features associated with the transonic effects and the angle of attack variation, such as the shock waves and the flow separation, are well predicted. The results indicate that the presented model provides remarkably good flow field predictions at a fraction of the computational time of CFD simulations. The predicted flow field allows the computation of the aerodynamic coefficients, providing an accurate and fast airfoil selection tool for aircraft designers.

Suggestions

A deep learning approach for the transonic flow field predictions around airfoils
Duru, Cihat; Alemdar, Hande; Baran, Özgür Uğraş (2022-01-01)
Learning from data offers new opportunities for developing computational methods in research fields, such as fluid dynamics, which constantly accumulate a large amount of data. This study presents a deep learning approach for the transonic flow field predictions around airfoils. The physics of transonic flow is integrated into the neural network model by utilizing Reynolds-averaged Navier–Stokes (RANS) simulations. A detailed investigation on the performance of the model is made both qualitatively and quant...
Deep Learning-Based Hybrid Approach for Phase Retrieval
IŞIL, ÇAĞATAY; Öktem, Sevinç Figen; KOÇ, AYKUT (2019-06-24)
We develop a phase retrieval algorithm that utilizes the hybrid-input-output (HIO) algorithm with a deep neural network (DNN). The DNN architecture, which is trained to remove the artifacts of HIO, is used iteratively with HIO to improve the reconstructions. The results demonstrate the effectiveness of the approach with little additional cost.
A temporal neural network model for constructing connectionist expert system knowledge bases
Alpaslan, Ferda Nur (Elsevier BV, 1996-04-01)
This paper introduces a temporal feedforward neural network model that can be applied to a number of neural network application areas, including connectionist expert systems. The neural network model has a multi-layer structure, i.e. the number of layers is not limited. Also, the model has the flexibility of defining output nodes in any layer. This is especially important for connectionist expert system applications.
A Novel Neural Network Method for Direction of Arrival Estimation with Uniform Cylindrical 12-Element Microstrip Patch Array
Caylar, Selcuk; Dural, Guelbin; Leblebicioğlu, Mehmet Kemal (2008-01-01)
In this study a new neural network algorithm is proposed for real time multiple source tracking problem with cylindrical patch antenna array based on a previous v reported Modified Neural Multiple Source Tracking Algorithm(MN-MUST). The proposed algorithm, namely Cylindrical Microstrip Patch Array Modified Neural Multiple Source Tracking Algorithm (CMN-MUST) implements W-MUST algorithm on a cylindrical microsttip patch array structure. CMN-MUST algorithm uses the advantage of directive pattern of microstrip...
A digital neuron realization for the random neural network model
CERKEZ, CUNEYT; AYBAY, HADİ IŞIK; Halıcı, Uğur (1997-06-12)
In this study the neuron of the random neural network (RNN) model (Gelenbe 1989) is designed using digital circuitry. In the RNN model, each neuron accumulates arriving pulses and can fire if its potential at a given instant of time is strictly positive. Firing occurs at random, the intervals between successive firing instants following an exponential distribution of constant rate. When a neuron fires, it routes the generated pulses to the appropriate output lines in accordance with the connection probabili...
Citation Formats
C. Duru, “A deep learning methodology for the flow field prediction around airfoils,” Ph.D. - Doctoral Program, Middle East Technical University, 2021.