A Method for Predicting Surface Finish of Polylactic Acid Parts Printed Using Fused Deposition Modeling

Accurately predicting the surface finish of fused deposition modeling (FDM) parts is an important task for engineering application FDM technology. So far, many prediction models have been proposed by establishing a mapping relationship between printing parameters and roughness. Each model can work well in its specific context; however, existing cannot meet requirements multi-factor multi-category cope with imbalanced data. Aiming at these issues, method based on combination adaptive particle swarm optimization K-nearest neighbor (APSO-KNN) algorithms this paper. Seven input variables, including nozzle diameter, layer thickness, number perimeters, flow rate, print speed, temperature, build orientation, are considered. The values each specimen determined using L27 Taguchi experimental design. A total 27 specimens printed data used training validation. results indicate that achieve minimum classification error 0.01 after two iterations, maximum accuracy 99.0%, high efficiency. It multiple factors categories handle In addition, demonstrates potential finish, actual industrial manufacturing.