Research Article

A novel approach for noise prediction using Neural network trained with an efficient optimization technique

Department of Aeronautical Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai, TN, India

^* e-mail: shivaprasad047@gmail.com

Received: 4 March 2022
Accepted: 20 March 2023

Abstract

Aerofoil noise as self-noise is detrimental to system performance, in this paper NACA 0012 optimization parameters are presented for reduction in noise. Designing an aerofoil with little noise is a fundamental objective of designing an aircraft that physically and functionally meets the requirements. Aerofoil self-noise is the noise created by aerofoils interacting with their boundary layers. Using neural networks, the suggested method predicts aerofoil self-noise. For parameter optimization, the quasi-Newtonian method is utilised. The input variables, such as angle of attack and chord length, are used as training parameters for neural networks. The output of a neural network is the sound pressure level, and the Quasi Newton method further optimises these parameters. When compared to the results of regression analysis, the values produced after training a neural network are enhanced.