Recently, additive manufacturing (AM) techniques like 3D printing have emerged as a potentially game-changing example of digital manufacturing. However, high entry barriers of a tiny material library, different processing defects, and unpredictable product quality are still holding back its widespread use in the industry. Due to its remarkable success in data tasks like classification, regression, and clustering, machine learning (ML) has recently gained a great deal of interest in the subject of the material library. This paper examines the current state of ML applications in several key areas of AM, including polymer matrix composite materials and machine parameter optimization. Composite filaments have been extruded using Polylactic Acid (PLA) as it is a biodegradable material and shows how High-Density Poly Ethylene (HDPE) enhances physical strength. All the parameters for the filament extruder have been designed by machine learning. Thermal stability is a significant concern for polymers that have been overcome by introducing Titanium Dioxide nanoparticles. The microstructure, surface texture, electro-mechanical behavior, and other general features of extruded filaments made from recycled plastics have been investigated. The extrusion temperature, approximated using ML, is in excellent agreement with the surface texture and microstructure of the polymers, as confirmed by FESEM, EDX, and Particle analysis. Extruded filaments experienced 2500 Vs and confirmed their non-conductivity up to 77.7GΩ. Tensile strength and elongation at break, two measures of mechanical properties, have been examined. Incorporation of Titanium Dioxide Nanoparticles improved mechanical properties significantly. When it comes to 3D printing, the physical properties and potential uses of each composite material are different.
Read full abstract