Artificial neural Network-Based approaches for Bi-directional modelling of robotic wire arc additive manufacturing

Abstract

Additive manufacturing (AM) process has seen its usage go astronomically up in the recent years. One of the oldest additive manufacturing processes namely, wire arc additive manufacturing (WAAM) has seen many recent developments due to the urge of attaining high efficiency in manufacturing field. Not only is it a very simple process among the other AM processes, but also it can be used for manufacturing very complex structures with a very low budget. The process of robotic WAAM demands precise modelling of the relationship between the input and response parameters so as to guarantee desired output of fine quality. To meet the demands of the process, hybridized artificial neural network (ANN) models were developed in this study and used for forward and backward mappings. Gradient descent with momentum and grey wolf optimization (GWO) are the algorithms that have been coupled with the neural networks in this paper. The novelty of this paper lies with the performance comparison in bi-directional mapping by hybridizing ANN models with the aforementioned algorithms in robotic WAAM domain. The gradient descent with momentum algorithm has shown better results than the metaheuristic algorithm in both the mappings while taking much lesser execution time.