The Effect of Loss Functions on the Deep Learning Modeling for the Flow Field Predictions Around Airfoils

CNNFOIL is a CNN-based machine learning tool that solves flow around the airfoil with a machine learning methodology. CNNFOIL, which is being developed by our research group, can predict flowfield around airfoils from different families at transonic regimes. We have improved the training process and accuracy of the CNNFOIL solver by implementing new loss functions. In this study, the effects of an L2 -based loss function, a physics-informed loss function based on continuity equation and a gradient difference loss function on the flow field predictions around airfoils are investigated. The loss functions are implemented into an encoder-decoder based convolutional neural network model. The neural network model is trained with Reynolds-averaged Navier-Stokes (RANS) based computational fluid dynamics (CFD) simulation results for different airfoil shapes at zero angle of attack for 0.7 Mach number flow. Numerical experiments are carried out with an unseen airfoil shape to assess the effects of loss functions. The performance of each loss-functions are discussed.


A deep learning methodology for the flow field prediction around airfoils
Duru, Cihat; Baran, Özgür Uğraş; Alemdar, Hande; Department of Mechanical Engineering (2021-9-07)
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 computati...
A mathematical contribution of statistical learning and continuous optimization using infinite and semi-infinite programming to computational statistics
Özöğür-Akyüz, Süreyya; Weber, Gerhard Wilhelm; Department of Scientific Computing (2009)
A subfield of artificial intelligence, machine learning (ML), is concerned with the development of algorithms that allow computers to “learn”. ML is the process of training a system with large number of examples, extracting rules and finding patterns in order to make predictions on new data points (examples). The most common machine learning schemes are supervised, semi-supervised, unsupervised and reinforcement learning. These schemes apply to natural language processing, search engines, medical diagnosis,...
Adapted Infinite Kernel Learning by Multi-Local Algorithm
Akyuz, Sureyya Ozogur; Ustunkar, Gurkan; Weber, Gerhard Wilhelm (2016-05-01)
The interplay of machine learning (ML) and optimization methods is an emerging field of artificial intelligence. Both ML and optimization are concerned with modeling of systems related to real-world problems. Parameter selection for classification models is an important task for ML algorithms. In statistical learning theory, cross-validation (CV) which is the most well-known model selection method can be very time consuming for large data sets. One of the recent model selection techniques developed for supp...
A linear approximation for training Recurrent Random Neural Networks
Halıcı, Uğur (1998-01-01)
In this paper, a linear approximation for Gelenbe's Learning Algorithm developed for training Recurrent Random Neural Networks (RRNN) is proposed. Gelenbe's learning algorithm uses gradient descent of a quadratic error function in which the main computational effort is for obtaining the inverse of an n-by-n matrix. In this paper, the inverse of this matrix is approximated with a linear term and the efficiency of the approximated algorithm is examined when RRNN is trained as autoassociative memory.
Computational representation of protein sequences for homology detection and classification
Oğul, Hasan; Mumcuoğlu, Ünal Erkan; Department of Information Systems (2006)
Machine learning techniques have been widely used for classification problems in computational biology. They require that the input must be a collection of fixedlength feature vectors. Since proteins are of varying lengths, there is a need for a means of representing protein sequences by a fixed-number of features. This thesis introduces three novel methods for this purpose: n-peptide compositions with reduced alphabets, pairwise similarity scores by maximal unique matches, and pairwise similarity scores by...
Citation Formats
A. Doğan, C. Duru, H. Alemdar, and Ö. U. Baran, “The Effect of Loss Functions on the Deep Learning Modeling for the Flow Field Predictions Around Airfoils,” presented at the 11th ANKARA INTERNATIONAL AEROSPACE CONFERENCE, Ankara, Türkiye, 2021, Accessed: 00, 2022. [Online]. Available: