Modeling, analysis, and optimization of dimensional accuracy of FDM-fabricated parts using definitive screening design and deep learning feedforward artificial neural network

Abstract

Additive manufacturing (AM) technologies such as fused deposition modeling (FDM) rely on the quality of manufactured products and the process capability. Currently, the dimensional accuracy and stability of any AM process is essential for ensuring that customer specifications are satisfied at the highest standard, and variations are controlled without significantly affecting the functioning of processes, machines, and product structures. This study aims to investigate the effects of FDM fabrication conditions on the dimensional accuracy of cylindrical parts. In this study, a new class of experimental design techniques for integrated second-order definitive screening design (DSD) and an artificial neural network (ANN) are proposed for designing experiments to evaluate and predict the effects of six important operating variables. By determining the optimum fabrication conditions to obtain better dimensional accuracies for cylindrical parts, the time consumption and number of complex experiments are reduced considerably in this study. The optimum fabrication conditions generated through a second-order DSD are verified with experimental measurements. The results indicate that the slice thickness, part print direction, and number of perimeters significantly affect the percentage of length difference, whereas the percentage of diameter difference is significantly affected by the raster-to-raster air gap, bead width, number of perimeters, and part print direction. Furthermore, the results demonstrate that a second-order DSD integrated with an ANN is a more attractive and promising methodology for AM applications.

Feasibility of Predictive Models for the Quality of Additive Manufactured Components Based on Artificial Neural Networks

“…Research studies by O.A.Mohamed et al [4] have been performed regarding the ability of artificial neural networks to predict dimensional characteristics of parts obtained through the FDM process by analysing parameters such as slice thickness, the number of perimeters, deposition angle, part print direction, and raster to raster air-gap. The study compared the precision of neural networks to classic regression techniques and showed that neural networks can account for dimensional deviations.…”

How generalisable are material extrusion additive manufacturing parameter optimisation studies? A systematic review

“…AG can also influence the defects listed: Geometrical accuracy, Porosity, and Surface Roughness. ↑ [ 12 , 21 , 22 , 44 , 86 , 110 , 119 , 56 ] ↓ [ 22 , 45 , 46 , 120 ] Raster angle (RA) The angle between deposited adjacent strands with respect to the X axis. RA can also influence the defects listed: Geometrical accuracy and Surface Roughness.…”

“…RA can also influence the defects listed: Geometrical accuracy and Surface Roughness. ↑ [ 21 , 44 , 60 , 88 , 119 , 120 , 121 ], ↓ [ 12 , 22 , 45 , 46 , 56 , 66 , 70 , 78 , 104 , 110 ] Road width (RW) Also known as raster width, the width of a deposited stand, which is a function of the extruder nozzle diameter and toolpath parameters. RW can also influence the defects listed: Geometrical accuracy and Surface Roughness.…”

Parametric Study and Optimization of End-Milling Operation of AISI 1522H Steel Using Definitive Screening Design and Multi-Criteria Decision-Making Approach

“…Definitive screening design (DSD), a three-level fractional factorial design, has been developed recently [32]. It performed better than other traditional experimental designs, such as full factorial design and response surface methodology (RSM), in estimating the main effect, interaction, and quadratic effect [33,34]. Compared to traditional methods, it reduces the experimental runs and, therefore, reduces experimentation time and cost.…”

“…Mohammad et al [35] successfully modeled the effect of various fused deposition modeling (FDM) process parameters on the creep and recovery behavior of 3D printed parts using DSD. In another study [33], they modeled and optimized the dimensional accuracy of FDM parts using DSD and deep learning. Luzanin et al [36] investigated the effect of build parameters of FDM on the flexural force of FDM manufactured parts.…”