Using Bayesian Regularized Artificial Neural Networks to Predict the Tensile Strength of Additively Manufactured Polylactic Acid Parts
Source abstract
Abstract
Additive manufacturing has transformed the production process by enabling the construction of components in a layer-by-layer approach. This study integrates Artificial Neural Networks to explore the nuanced relationship between process parameters and mechanical performance in Fused Filament Fabrication. Using a fractional Taguchi design, seven key process parameters are systematically varied to provide a robust dataset for model training. The resulting model confirms its accuracy in predicting tensile strength. In particular, the mean squared error is 0.002, and the mean absolute error is 0.024. These results significantly advance the understanding of 3D manufactured parts, shedding light on the intricate dynamics between process nuances and mechanical outcomes. Furthermore, they underscore the transformative role of machine learning in precision-driven quality prediction and optimization in additive manufacturing.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Additive Manufacturing and 3D Printing Technologies · Manufacturing Process and Optimization · Industrial Vision Systems and Defect Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Civil and Mechanical Engineering, University of Cassino and Southern Lazio, via G. di Biasio 43, 03043 Cassino, Italy
Faculty of Engineering, University of Applied Sciences Ansbach, Residenzstr. 8, 91522 Ansbach, Germany
References (51)
Show source-provided references
1. Multi Objective Optimization of Fused Deposition Modeling Process Parameters with Desirability Function10.1016/j.procir.2021.03.117 ↗
2. An Overall Performance Index to Quantify Dimensional Accuracy and Mechanical Strength of Parts Manufactured through VAT Photopolymerization in Biodegradable and Non-Biodegradable Resin10.1007/s00170-023-12285-1 ↗
3. Additive Manufacturing—General Principles—Fundamentals and Vocabulary (Standard No. ISO/ASTM 52900:2021(En)). Available online: https://www.iso.org/obp/ui/#iso:std:iso-astm:52900:ed-2:v1:en:sec:A.
4. Gibson, I., Rosen, D.W., and Stucker, B. (2015). Additive Manufacturing Technologies, Springer. [3rd ed.].10.1007/978-1-4939-2113-3 ↗
5. Geometrical Deviations of Green Parts Due to Additive Manufacturing: A Synthetic Geometrical Performance Index10.1016/j.procir.2022.10.036 ↗
6. The Use of Machine Learning in Process–Structure–Property Modeling for Material Extrusion Additive Manufacturing: A State-of-the-Art Review10.1007/s40430-023-04637-5 ↗
7. Fused Deposition Modeling Process Parameters Optimization and Effect on Mechanical Properties and Part Quality: Review and Reflection on Present Research10.1016/j.matpr.2019.11.296 ↗
8. Effect of Process Parameters on Tensile Strength of FDM Printed PLA Part10.1108/RPJ-06-2017-0134 ↗
9. Effect of Process Parameters on Mechanical Strength of Fabricated Parts Using the Fused Deposition Modelling Method10.7736/KSPE.2019.36.8.705 ↗
10. Printing Parameter Optimization of PLA Material Concerning Geometrical Accuracy and Tensile Properties Relative to FDM Process Productivity10.1007/s12206-023-0113-6 ↗
11. The Influence of Forced-Air Cooling on a 3D Printed PLA Part Manufactured by Fused Filament Fabrication
12. Experimental Investigations of Process Parameters on Mechanical Properties for PLA during Processing in FDM
13. Enemuoh, E.U., Duginski, S., Feyen, C., and Menta, V.G.K. (2021). Effect of Process Parameters on Energy Consumption, Physical, and Mechanical Properties of Fused Deposition Modeling. Polymers, 13.10.3390/polym13152406 ↗
14. Caminero, M.A., Chacón, J.M., Plaza, E.G., Núñez, P.J., Reverte, J.M., and Bécar, J.P. (2019). Additive Manufacturing of PLA-Based Composites Using Fused Filament Fabrication: Effect of Graphene Nanoplatelet Reinforcement on Mechanical Properties, Dimensional Accuracy and Texture. Polymers, 11.10.3390/polym11050799 ↗
15. Investigation on Influence of Infill Pattern and Layer Thickness on Mechanical Strength of PLA Material in 3D Printing Technology10.26666/rmp.jesr.2019.2.5 ↗
16. Investigation on Tensile Strength and Failure Modes of FDM Printed Part Using In-House Fabricated PLA Filament
17. Deep Learning in Neural Networks: An Overview10.1016/j.neunet.2014.09.003 ↗
18. Alqahtani, N., Alam, S., Aqeel, I., Shuaib, M., Khormi, I., Khan, S.B., and Malibari, A. (2023). Deep Belief Networks (DBN) with IoT-Based Alzheimer’s Disease Detection and Classification. Appl. Sci., 13.10.3390/app13137833 ↗
19. A Study on Different Deep Learning Algorithms Used in Deep Neural Nets: MLP SOM and DBN10.1007/s11277-022-10079-4 ↗
20. An Efficient Starling Murmuration-Based Secure Web Service Model for Smart City Application Using DBN10.1007/s10462-023-10689-9 ↗
21. Guo, D., Song, Z., Liu, N., Xu, T., Wang, X., Zhang, Y., Su, W., and Cheng, Y. (2024). Performance Study of Hard Rock Cantilever Roadheader Based on PCA and DBN. Rock Mech.10.1007/s00603-023-03698-1 ↗
22. CN-BSRIQA: Cascaded Network—Blind Super-Resolution Image Quality Assessment10.1016/j.aej.2024.02.007 ↗
23. Bayesian Approach for Neural Networks—Review and Case Studies10.1016/S0893-6080(00)00098-8 ↗
24. Recent Developments of Bayesian Model Class Selection and Applications in Civil Engineering10.1016/j.strusafe.2010.03.011 ↗
25. Data, Privacy, and the Greater Good10.1126/science.aac4520 ↗
26. Burden, F.R., and Winkler, D.A. (2008). Methods in Molecular Biology, Elsevier.
27. Bayesian Personalized Treatment Selection Strategies That Integrate Predictive with Prognostic Determinants10.1002/bimj.201700323 ↗
28. Foresight Formulation in Innovative Production, Automation and Control Systems10.1108/14636680710821089 ↗
29. Razvi, S.A., Feng, S.C., Narayanan, A., Lee, Y.-T.T., and Witherell, P. (2019, January 25–28). A Review of Machine Learning Applications in Additive Manufacturing. Proceedings of the International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, Washington, DC, USA.10.1115/DETC2019-98415 ↗
30. Machine Learning-Based Mechanical Behavior Optimization of 3D Print Constructs Manufactured via the FFF Process10.1007/s11665-021-06535-0 ↗
31. Single and Multi-Objective Optimization of Processing Parameters for Fused Deposition Modeling in 3D Printing Technology10.15282/ijame.17.1.2020.03.0558 ↗
32. Jatti, V.S., Sapre, M.S., Jatti, A.V., Khedkar, N.K., and Jatti, V.S. (2022). Mechanical Properties of 3D-Printed Components Using Fused Deposition Modeling: Optimization Using the Desirability Approach and Machine Learning Regressor. Appl. Syst. Innov., 5.10.3390/asi5060112 ↗
33. Manoharan, K., Chockalingam, K., and Sasisekharan, R. (2020). AIP Conference Proceedings, AIP Publishing.
34. Dimensional errors in longitudinal turning based on the unified generalize mechanics of cutting approach. Part II: Machining process analysis and dimensional error estimate10.1016/S0890-6955(02)00118-9 ↗
35. Dey, A., and Yodo, N. (2019). A Systematic Survey of FDM Process Parameter Optimization and Their Influence on Part Characteristics. J. Manuf. Mater. Process., 3.10.3390/jmmp3030064 ↗
36. Assembly design in aeronautic field: From assembly jigs to tolerance analysis10.1177/0954405416635033 ↗
37. (2024, January 31). Ultimaker S3 Printer. Available online: https://ultimaker.com/it/3d-printers/ultimaker-s3.
38. (2024, January 31). BASF Ultrafuse PLA 750 gr. Crea3D®. Available online: https://www.crea3d.com/en/basf/486-314-basf-ultrafuse-pla-750-gr.html.
39. Standard Test Method for Tensile Properties of Plastic. An American National Standard (Standard No. ASTM D 638-22). Available online: https://www.astm.org/d0638-22.html.
40. (2024, January 10). Catalogue of Taguchi Designs—Minitab. Available online: https://support.minitab.com/en-us/minitab/21/help-and-how-to/statistical-modeling/doe/supporting-topics/taguchi-designs/catalogue-of-taguchi-designs/.
41. Effects of Build Orientations on Tensile Properties of PLA Material Processed by FDM10.4028/www.scientific.net/AMR.1044-1045.31 ↗
42. Standard Terminology Relating to Plastics (Standard No. ASTM D 883-22). Available online: https://www.astm.org/d0883-22.html.
43. (2024, January 31). MATLAB. Available online: https://www.mathworks.com/products/matlab.html.
44. Neal, R.M. (1996). Bayesian Learning for Neural Networks, Springer. [1st ed.].10.1007/978-1-4612-0745-0 ↗
45. Efficient Leave-One-out Cross-Validation for Bayesian Non-Factorized Normal and Student-t Models
46. The Coefficient of Determination R-Squared Is More Informative than SMAPE, MAE, MAPE, MSE and RMSE in Regression Analysis Evaluation
47. Will, J., and Most, T. (2009, January 18–20). Metamodell of Optimized Prognosis (MoP)—An Automatic Approach for User Friendly Parameter Optimization. Proceedings of the ANSYS Conference & 27th CADFEM Users Meeting, Leipzig, Germany.
48. Bayesian Interpolation10.1162/neco.1992.4.3.415 ↗
49. Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep Learning10.1007/s10710-017-9314-z ↗
50. An Accurate Comparison of Methods for Quantifying Variable Importance in Artificial Neural Networks Using Simulated Data10.1016/j.ecolmodel.2004.03.013 ↗
51. Illuminating the “Black Box”: A Randomization Approach for Understanding Variable Contributions in Artificial Neural Networks10.1016/S0304-3800(02)00064-9 ↗