Prediction of the tensile strength of polylactic acid fused deposition models using artificial neural network technique

Abstract

Additive Manufacturing technology helps in building complex geometries without wastage of materials. Fused deposition modelling is the most widely used technology among them. In this paper, the tensile strength of fused deposition models with varying process parameters is predicted using Artificial Neural Network. Process parameters chosen are: nozzle temperature, layer thickness and infill speed. Design of experiments using Taguchi technique is made to create an L9 orthogonal array. Tensile strength of the Polylactic acid specimens developed using fused deposition modelling is experimentally investigated. This data set is used in Artificial Neural Network to train the network for predicting the tensile strength at various levels of nozzle temperature, layer thickness and infill speed. The effects of parameters influencing tensile strength is captured using Minitab software. Furthermore, confirmation experiment to validate the tensile strength predicted using Artificial Neural Network method is performed and is found to be in good agreement, within 5%. Property requirements of end use products depend on its application and its prediction will be useful for enhancing the potential of Additive Manufacturing from rapid prototyping to end product manufacturing.