Optimization of Resin Printing Parameters for Improved Surface Roughness Using Metaheuristic Algorithms: A Multifaceted Approach

Since the dawn of additive manufacturing in dentistry, there has been a continuous need to examine the influence of significant printing parameters for fabricating complex parts with enhanced precision and accuracy. Despite numerous attempts, achieving the optimal surface roughness of resin-printed parts is still a critical challenge due to the complex nature of the printing process and the numerous parameters involved. The proposed research evaluated the effect of layer thickness (LT), exposure duration (ED), print angle (PA), infill density (ID), and lift speed (LS) on specimens fabricated using resin 3D printer as per American Society for Testing Materials standards to determine the optimum SR. The central composite design methodology was employed to conduct thirty-two experimental runs. SR of the fabricated specimen has been tested using a surface roughness tester. The response surface methodology (RSM) has been used to establish a process model using regression that connect process input and output parameters. Furthermore, the RSM-particle swarm optimization (PSO) and RSM-genetic algorithm (GA) integrated machine learning approach are used to optimize the SR. Initially from performed experimental result, with a LT of 10 microns, PA of 90 degrees, ID of 100%, an ED of 5 sec, LS 1 mm/s and a post-processing time of 60 minutes held constant, a minimum SR of 0.226 microns is obtained. Conclusively, here RSM-PSO performs better when compared with RSM-GA in optimizing SR to 0.2042 microns at a PA of 77.25°, an ID of 93.58, an ED of 2.1 seconds, a LT of 19 microns and LS of 3.4641 mm/s, a post-processing time constant of 60 minutes and same has been validated experimentally.