Optimization of Manufacturing Parameters of PLA Components Using Taguchi and Neural Network (NN) Technique

The present paper is based upon the study of 3d printer material Polylactic acid used in fused deposition modeling method. The sustainable and building of a biodegradable filament called polylactic acid are vastly functioning and operative in the industry. The study inspects the effect of various printing process parameters on the impact strength on printed components using PLA filament. As per ASTM standards for impact specimen D 256 is used. For evaluation of strength purpose, selected printing parameters are layer height, print speed, infill pattern and shell thickness and ANOVA technique and L27 orthogonal array is used to find the best combination of parameters yield highest impact strength. Results expose that layer thickness is one of the most significant factors, as layer thickness increases impact strength also increases.  From this study possibly will be beneficial for enhancing printing parameters to yield. The predictions of impact strength by these models are evaluated against the data generated in experimental study. Results conclude that the model generated by Neural Network to get better parameters to fit for optimizing the FDM process.