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.

Keywords

Artificial neural network (ANN) / Optimization / Definitive screening design (DSD) / Analysis of variance (ANOVA) / Fused deposition modeling (FDM) / Dimensional accuracy

References

[1.] Carneiro O, Silva A, Gomes R. Fused deposition modeling with polypropylene. Mater Des, 2015, 83: 768-776.

[2.] Onuh SO, Yusuf YY. Rapid prototyping technology: applications and benefits for rapid product development. J Intell Manuf, 1999, 10(3–4): 301-311.

[3.] Chua CK, Leong KF. 3D printing and additive manufacturing: principles and applications (with companion media pack), 2014, Singapore: World Scientific Publishing Co Inc..

[4.] Gibson I, Rosen D, Stucker B. Additive manufacturing technologies: 3D printing, rapid prototyping, and direct digital manufacturing, 2014, Berlin: Springer

[5.] Lindemann C, Jahnke U, Moi M et al (2012) Analyzing product lifecycle costs for a better understanding of cost drivers in additive manufacturing. In: 23th annual international solid freeform fabrication symposium—an additive manufacturing conference. Austin Texas, USA, Aug 6–8

[6.] Garg A, Bhattacharya A, Batish A. On surface finish and dimensional accuracy of FDM parts after cold vapor treatment. Mater Manuf Process, 2016, 31(4): 522-529.

[7.] Byun HS, Shin HJ, Lee KH (2002) Design of benchmarking part and selection of optimal rapid prototyping processes. In: Proceedings of the second international conference on rapid prototyping and manufacturing, pp 469–477

[8.] Mohamed OA, Masood SH, Bhowmik JL. Optimization of fused deposition modeling process parameters: a review of current research and future prospects. Adv Manuf, 2015, 3(1): 42-53.

[9.] Camposeco-Negrete C. Optimization of FDM parameters for improving part quality, productivity and sustainability of the process using Taguchi methodology and desirability approach. Prog Addit Manuf, 2020, 5(1): 59-65.

[10.] Mahmood S, Qureshi A, Talamona D. Taguchi based process optimization for dimension and tolerance control for fused deposition modelling. Addit Manuf, 2018, 21: 183-190.

[11.] Maurya NK, Rastogi V, Singh P. Investigation of dimensional accuracy and international tolerance grades of 3D printed polycarbonate parts. Mater Today Proc, 2020, 25: 537-543.

[12.] Aslani KE, Kitsakis K, Kechagias JD, et al. On the application of grey Taguchi method for benchmarking the dimensional accuracy of the PLA fused filament fabrication process. SN Appl Sci, 2020, 2: 1-11.

[13.] Nieciąg H, Kudelski R, Dudek P et al (2020) An exploratory study on the accuracy of parts printed in FDM processes from novel materials. Acta Mech Autom 14(1):59–68

[14.] Ahmad MN, Mohamad AR (2020) Analysis on dimensional accuracy of 3D printed parts by Taguchi approach. In: Advances in mechatronics, manufacturing, and mechanical engineering. Springer, pp 219–231

[15.] Armillotta A, Bellotti M, Cavallaro M. Warpage of FDM parts: experimental tests and analytic model. Robot Comput Integr Manuf, 2018, 50: 140-152.

[16.] Dilberoglu UM, Simsek S, Yaman U. Shrinkage compensation approach proposed for ABS material in FDM process. Mater Manuf Process, 2019, 34(9): 993-998.

[17.] Haghighi A, Li L. Study of the relationship between dimensional performance and manufacturing cost in fused deposition modeling. Rapid Prototyp J, 2018, 24(2): 395-408.

[18.] Jafari-Marandi R, Khanzadeh M, Tian W, et al. From in-situ monitoring toward high-throughput process control: cost-driven decision-making framework for laser-based additive manufacturing. J Manuf Syst, 2019, 51: 29-41.

[19.] Karthikeyan R, Senthil Kumar V, Punitha A et al (2020) An integrated ANN-GA approach to maximise the material removal rate and to minimize the surface roughness of wire cut EDM on titanium alloy. Adv Mater Process Technol 1–11

[20.] Jones B, Nachtsheim CJ. A class of three-level designs for definitive screening in the presence of second-order effects. J Qual Technol, 2011, 43(1): 1-15.

[21.] Jones B, Nachtsheim CJ. Definitive screening designs with added two-level categorical factors. J Qual Technol, 2013, 45(2): 121-129.

[22.] Jones B, Nachtsheim CJ. Effective design-based model selection for definitive screening designs. Technometrics, 2016, 59(3): 319-329.

[23.] Towell GG, Shavlik JW. Knowledge-based artificial neural networks. Artif intell, 1994, 70(1): 119-165.

[24.] Fushiki T. Estimation of prediction error by using K-fold cross-validation. Stat Comput, 2011, 21(2): 137-146.