The fused deposition modelling (FDM) technique involves the deposition of a fused layer of material according to the geometry designed in the software. Several parameters affect the quality of parts produced by FDM. This paper investigates the effect of FDM printing process parameters on tensile strength, impact strength, and flexural strength. The effects of process parameters such as printing speed, layer thickness, extrusion temperature, and infill percentage are studied. Polyactic acid (PLA) was used as a filament material for printing test specimens. The experimental layout is designed according to response surface methodology (RSM) and responses are collected. Specimens are prepared for testing of these parameters as per ASTM standards. A mathematical model for each of the responses is developed based on the nonlinear regression method. The desirability approach, nonlinear regression, as well as experimental values are in close agreement with each other. The desirability approach predicted the tensile strength, impact strength, and flexural strength with a less percentage error of 3.109, 6.532, and 3.712, respectively. The nonlinear regression approach predicted the tensile strength, impact strength, and flexural strength with a less percentage error of 2.977, 6.532, and 3.474, respectively. The desirability concept and nonlinear regression approach resulted in the best mechanical property of the FDM-printed part.

The advancement in technology has attracted researchers to electric discharge machining (EDM) for providing a practical solution for overcoming the limitations of conventional machining. The current study focused on predicting the Material Removal Rate (MRR) using machine learning (ML) approaches. The process parameters considered are namely, workpiece electrical conductivity, gap current, gap voltage, pulse on time and pulse off time. Cryo-treated workpiece viz, Nickel-Titanium (NiTi) alloys, Nickel Copper (NiCu) alloys, and Beryllium copper (BCu) alloys and cryo-treated pure copper as tool electrode was considered. In the present research work, four supervised machine learning regression and three supervised machine learning classification-based algorithms are used for predicting the MRR. Machine learning result showed that gap current, gap voltage and pulse on time are most significant parameters that effected MRR. It is observed from the results that the Gradient boosting regression-based algorithm resulted in the highest coefficient of determination value for predicting MRR while Random Forest classification based resulted in the highest F1-Score for obtaining MRR.