Development of ANN model for predicting mechanical properties of 3D printed PEEK polymer using FDM and optimization of process parameters for better mechanical properties.

Abstract Additive manufacturing (AM) has evolved from a proven technology to one with great potential and challenges. This technology is widely used in many industries such as automotive, aerospace, and medical; fused deposition modeling (FDM) is a popular technique for producing PEEK (polyether ether ketone) parts, including implant prosthetic teeth. This study delves into artificial neural network (ANN) modeling, parametric optimization, and experimental examination of PEEK 3D printing to enhance 3D printing processes. This research identifies four critical process factors (infill density, layer height, printing speed and infill pattern) that influence the surface roughness, mechanical strength and elastic modulus of the prints. Utilizing a 4-12-3 network design, the study demonstrates that an ANN model with an average error of less than 5% is optimal for all three responses. Furthermore, the study employs teaching and learning based optimization algorithm (TLBO) and non-dominated sorting genetic algorithm (NSGA) to optimize the printing process. The findings highlight TLBO's ability to minimize surface roughness to 6.01 µm and NSGA's capability to maximize the elastic modulus to 1253.35 MPa and ultimate tensile strength to 65.55 MPa. Microstructural studies supported the results obtained by parametric analysis and optimization.