Evaluation and Replication of Wind Tunnel Data Using Artificial Intelligence Methods

The wind tunnel is a laboratory device used for aerodynamic tests. It models the airflow through probes placed on models or prototypes to evaluate the aerodynamic properties by controlling the airflow in different conditions. This study aims to train and test algorithms with data to reproduce the data obtained through probes by using certain artificial intelligence algorithms and to learn their accuracy. For this purpose, ANFIS (Adaptive Neuro-Fuzzy Inference System), ANN (Artificial Neural Networks), and RBFNN (Radial Basis Function Neural Network) models are used. The results obtained with these models are R
²
(R-square), RMSE (Root Mean Square Error) and MAE (Mean Absolute Error) parameters. According to these results, the most successful model in training and test data is ANFIS, and the least successful model is ANN. However, the success statistics of this entire model show that they can be used in the evaluation and replication of wind tunnel data.