Optimization of 3D Printing Time for Fused Deposition Modeling Based on Machine Learning

Given the importance of additive manufacturing (AM) printing systems and their advantages over systems based on conventional manufacturing, whether formative or subtractive, AM technology is being increasingly adopted in 3D printing, with usage rates rising sharply. This remarkable growth has had a significant and direct impact on a number of manufacturing costs, particularly printing time, resulting in significant additional production costs. Consequently, this problem has attracted the attention of industry actors and the research community, with several studies focusing on the evaluation, prediction and optimization of 3D printing time, thus becoming one of the main objectives of current research in the field of additive manufacturing, and in particular, for fused deposition modeling (FDM) printing, given its frequent use in 3D printing and the popularity of this process in the manufacturing industry. In this study, we focus on the study of 3D printing time, taking into account the orientation of the part to be manufactured, since different values of 3D object creation time can be obtained depending on the printing angle. In addition, the proposed model offers high performance with the most optimized statistical values.