Modeling the influence of the processing parameters of fused deposition 
modeling (FDM) on the mechanical properties of FDM fabricated parts is a 
challenging task due to the complex dynamics and the large number of factors 
that affect the quality of the fabricated parts. Therefore, optimizing the 
mechanical properties of parts fabricated using FDM usually requires a 
considerable number of test samples. In the presented work, the design of 
experiments (DOE) approach was utilized to minimize the number of tests 
needed to study the investigated parameters. Response surface methodology 
(RSM) and Taguchi’s orthogonal arrays were used to generate the training and 
testing data sets used to develop the neural network (NN) model and evaluate 
its performance. The investigated processing parameters are the layer 
thickness, nozzle temperature, infill percentage, and infill pattern. The tensile 
strength, stiffness, and ductility are the objective functions to be optimized. The 
coefficient of determination R2 indicates that the ANN models were more 
accurate at predicting the mechanical properties than DOE regression models. 
Multi-objective particle swarm optimization was implemented to obtain the nondominated 
Pareto optimal solutions. The Pareto front demonstrated the 
possibility of optimizing the strength and stiffness simultaneously, but the 
ductility must be sacrificed.

Data-Driven Modeling and Optimization of Fdm Processing Parameters

Paper Proceedings: https://asmedigitalcollection.asme.org/MSEC/MSEC2021/volume/85062

2021 International Manufacturing Science and Engineering Conference (MSEC2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.