An optimized artificial neural network for estimating design effort of jigs and fixtures used in aviation industry

Abstract

This paper investigates the usefulness of the machine learning methods to predict the design effort of jigs and fixtures used in the aviation industry. Reaching the best possible result by determining the ideal machine learning model to obtain the best estimate and the most appropriate set of inputs and parameters forms the basis of this study. To that end, most popular machine learning models that can be used for regression are combined with various data encoding methods. The best combination is optimized as well. The results showed that an optimized Artificial Neural Network architecture with binary encoding applied to the input data can be applied satisfactorily in the aviation industry for the solution of the given problem.