Prediction of airfoil self-noise using polynomial regression, multivariate adaptive regression splines, gradient boosting technique and deep learning technique

Recently, studies have been made regarding airfoil self-noise, its generation, its prediction and how to curb the noise and the various ill-effects of it. Estimation of noise needs to be accurate so that the further studies to reduce noise from the airfoil models can be performed efficiently. Thus, the development of a coherent noise prediction tool is vital. This paper, proposes polynomial regression, multivariate adaptive regression splines, gradient boosting technique and deep learning model to estimate the airfoil self-noise noise prediction. It is observed that multivariate adaptive regression splines (MARS) and polynomial regression models have shown reasonable output whereas outstanding results have been obtained by applying deep neural networks and gradient boosting machine, for the airfoil self-noise prediction problem.