Enhancement of the torsional strength of commercial ABS samples manufactured using a tabletop 3D printer: an application of innovative hybridised tools and techniques

This study focuses on performance enhancement of the fused filament fabrication (FFF) of ABS part using a tabletop 3D printer. The objective is accomplished by understanding the effects of raster width, raster angle, part orientation and layer thickness on build time, material consumption and maximum torsional stress by application of hybridised machine learning techniques like artificial neural network (ANN) and genetic algorithm (GA). Further, response surface methodology (RSM)-based Box-Behnken experimental design is followed to develop the initial regression model. Furthermore, multi-objective GA (MOGA) tool is deployed to determine the optimum parameter values. The study had shown that complex nonlinear relationship exists between the process parameters and performance measures and the ANN-GA technique had a better fit when compared to the RSM-GA model. Thus, ANN-GA could be a promising multi-objective approach for optimisation of the FFF process as an alternative commercial manufacturing technique to meet the contemporary industry needs.