Leveraging Machine Learning for Predictive Modeling in 3D Printing of Composite Materials: A Comparative Study

Abstract

This study explores how additive manufacturing, commonly referred to as 3D printing, has transformed a number of industries by making it possible to precisely create intricate structures. By providing improved mechanical qualities and adaptability for a variety of uses, the incorporation of composite materials into 3D printing has further increased its potential. Composites can be engineered to attain particular features like improved strength, stiffness, or heat resistance. Composites are created by combining two or more different materials. When using composite materials in 3D printing, reinforcing agents like carbon fibres, glass fibres, or ceramics are usually combined with a matrix material, like thermoplastics. These reinforcements improve the material’s performance, enabling the production of parts that are both lightweight and durable. The research into composite 3D printing aims to improve material properties, reduce costs, and expand the range of applications, driving innovation and optimization in material science and engineering.the prediction of tensile strength (MPa) in 3D printing by evaluating the influence of key process parameters, including printing speed (mm/s), nozzle temperature (°C), and filler material percentage (%). Three regression models for machine learning The link between the input parameters and the output tensile strength is examined using Support Vector Machines (SVM), Random Forest Regression, and Linear Regression. The best predictive tool for maximising the mechanical qualities of printed materials is identified by comparing the performance of each model; this tool may be used to raise the calibre and dependability of 3D-printed parts.