The Effect of Variable Extrusion Parameters on the Tensile Strength and Production Quality of ABS Filaments

Fused Filament Fabrication benefits from Akrilonitril Butadien Stiren due to its mechanical and thermal resistance, yet optimizing extrusion parameters for improved tensile strength and dimensional accuracy remains challenging. This study aims to analyze the impact of extrusion parameters on the tensile resistance and dimensional consistency of Akrilonitril Butadien Stiren filaments using machine learning methodologies to enhance 3D printing efficiency. Akrilonitril Butadien Stiren granules were extruded via a single-screw extruder at 225°C–245°C and screw speeds of 2–6 rpm, with the Taguchi method optimizing the experimental design. Machine learning models, including ensemble methods, were developed to predict tensile strength and filament diameter, with the Extra Trees algorithm achieving the highest accuracy (~99%). The optimal tensile strength (28.5 MPa) and filament diameter (±1.75 mm) were obtained at 235°C and 4 rpm, with temperature (81.6%) having a greater effect on tensile strength than screw speed (18.4%). This study demonstrates the successful integration of classical optimization and machine learning techniques, providing a framework for enhancing Akrilonitril Butadien Stiren filament production quality in 3D printing.