Performance Analysis of Acrylonitrile-Butadiene-Styrene-Polycarbonate Polymer Blend Filament for Fused Deposition Modeling Printing Using Hybrid Artificial Intelligence Algorithms

The performance of ABS-PC polymer filament utilized in 3D printing is highly dependent on blend composition, molecular weight, addition of additives and working parameters of the filament extrusion process. This paper aims to focus on optimizing the input parameters such as composition of ABS/PC, speed of the screw, and temperature of the extrusion barrel for enhancing the tensile properties of the blend filament. An experimental design matrix has been employed using face-centered central composite design (FCCD) approach. ABS-PC blend filaments of 2.85 +/- 0.05 mm diameter have been fabricated using single screw extrusion process and the tensile strength of all samples is investigated. Two hybrid intelligence systems, genetic algorithm (GA) with artificial neural networks (ANN) and GA with response surface methodology (RSM), have been used to optimize the input parameters. Algorithms GA-ANN and GA-RSM predicted the maximum tensile strength of 50.112 and 48.356 MPa respectively. Fractography of the ABS-PC specimens revealed that the optimized blend composition consists of partial miscibility, adequate flow properties, and well-bonded structure. In addition, a 38.4% increase in the tensile strength of the 3D-printed specimen was observed on using blend filament with 49.777 wt. % PC.