Study and Evaluation of Machine Learning algorithms for Aerospace applications

Abstract

Machine learning algorithms are being explored and employed for various applications and have become the most sought topic of research in the modern era. It is a well known and accepted fact that a single machine learning algorithm cannot perform well for different applications. In this paper, effort is made to explore, design and evaluate eleven machine learning algorithms for four aerospace applications: O-ring failure prediction (classification and regression), Airfoil self noise prediction test (regression), Dynamics test (regression) and steel plate fault detection (classification). The performances of all the eleven algorithms were compared using the metric classification accuracy for classifiers and R2, RMSE metric for regressors. The algorithms were ranked based on their performance for all the above mentioned applications and the performance of proposed models are also compared with the results reported in the literature to conclude that the performance of proposed models are on par with the results reported in the literature. The proposed work can be easily extended to other Aerospace applications too.