Artificial Neural Network Modeling of Mechanical Properties of 3D-Printed Polyamide 12 and Its Fiber-Reinforced Composites.

Abstract

Fused filament fabrication (FFF) has recently emerged as a sustainable digital manufacturing technology to fabricate polymer composite parts with complex structures and minimal waste. However, FFF-printed composite parts frequently exhibit heterogeneous structures with low mechanical properties. To manufacture high-end parts with good mechanical properties, advanced predictive tools are required. In this paper, Artificial Neural Network (ANN) models were developed to evaluate the mechanical properties of 3D-printed polyamide 12 (PA) and carbon fiber (CF) and glass fiber (GF) reinforced PA composites. Tensile samples were fabricated by FFF, considering two input parameters, such as printing orientation and infill density, and tested to determine the mechanical properties. Then, single- and multi-target ANN models were trained using the forward propagation Levenberg-Marquardt algorithm. Post-training performance analysis indicated that the ANN models work efficiently and accurately in predicting Young's modulus and tensile strength of the 3D-printed PA and fiber-reinforced PA composites, with most relative errors being far less than 5%. In terms of mechanical properties, such as Young's modulus and tensile strength, the 3D-printed composites outperform the unreinforced PA. Printing PA composites with 0° orientation and 100% infill density results in a maximum increase in Young's modulus (up to 98% for CF/PA and 32% for GF/PA) and tensile strength (up to 36% for CF/PA and 18% for GF/PA) compared to the unreinforced PA. This study underscores the potential of the ANN models to predict the mechanical properties of 3D-printed parts, enhancing the use of 3D-printed PA composite components in structural applications.