Fused filament fabrication manufactured biological scaffolds: An investigation of mechanical properties by using the Taguchi method and machine learning techniques
Source abstract
Abstract
Tissue engineering scaffolds are three-dimensional, biocompatible, biodegradable, and porous structures designed to support cell attachment, proliferation, and differentiation, leading to new tissue formation. Designing optimal scaffolds is complex, requiring the optimisation of various physical, chemical, and biological properties, which are cell- or tissue-dependent. For hard tissue applications such as bone, compressive strength is a critical property and can be adjusted by modifying printing conditions. The mechanical properties of scaffolds produced using different microstructural polymers (semi-crystalline and amorphous) depend on parameters that significantly impact filament extrusion and the crystallisation process. This study investigates the effect of key process parameters (printing temperature, printing speed, and flow) on scaffold mechanical properties using the Taguchi method. Three biocompatible polymers with different microstructures—polycaprolactone, polylactic acid, and polyethylene terephthalate glycol—were examined. Results show a high correlation between process parameters and compressive strength using the Taguchi method, but prediction accuracy remained low. Therefore, four machine learning algorithms—Random Forest (RF), Support Vector Regression (SVR), K-Nearest Neighbour (K-NN), and Gradient Boosting Regression (GBR)—were applied to enhance predictive performance. Notably, the RF and GBR algorithms achieved approximately 99% prediction accuracy when evaluated on the test dataset. • Taguchi optimisation enhanced the compressive strength of MEX bone scaffolds from diverse polymers. • Process parameters critically influenced both mechanical strength and dimensional accuracy. • Conventional regression models could not capture complex parameter interactions. • Machine learning models accurately predicted scaffold strength for multiple materials with greater than 99% accuracy.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Additive Manufacturing and 3D Printing Technologies · Innovations in Concrete and Construction Materials
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (82)
Show source-provided references
1. 2023
2. Prediction intervals for gradient boosting regression
3. 2023
4. Support vector regression tutorial for machine learning
5. Employing the Taguchi method in optimizing the scaffold production process for artificial bone grafts10.1016/j.jmatprotec.2008.04.001 ↗
6. Taguchi Metodu ve Gri İlişkisel Analizi Kullanılarak 1,2316 Paslanmaz Çeliğin (R65) Mikro-Elektro Erozyon Delme Kabiliyetinin Değerlendirilmesi10.29130/dubited.833720 ↗
7. Fundamentals of design of experiments
8. Teaching the Taguchi method to industrial engineers10.1108/00438020110391873 ↗
9. Quality performance evaluation of thin walled PLA 3D printed parts using the taguchi method and grey relational analysis
10. Design of experiment analysis on tensile properties of PLA samples produced by fused filament fabrication10.1007/s00170-021-08216-7 ↗
11. Development of petroleum-derived polymeric additive to enhance the bituminous properties with the use of a machine-learning model10.1016/j.scenv.2024.100186 ↗
12. Mechanical characterization of bone: state of the art in experimental approaches—what types of experiments do people do and how does one interpret the results?10.1007/s11914-018-0454-8 ↗
13. On the effect of design and fabrication parameters on mechanical performance of 3D printed PLA scaffolds10.1016/j.bprint.2020.e00096 ↗
14. Design and printing parameters effect on PLA fused filament fabrication scaffolds
15. Biomanufacturing for tissue engineering: present and future trends10.1080/17452750903476288 ↗
16. Additive manufacturing materials, methods and applications: a review10.1016/j.matpr.2021.04.379 ↗
17. Comparison of boosting and genetic programming techniques for prediction of tensile strain capacity of Engineered Cementitious Composites (ECC)
18. Biopolymers for tissue engineering applications: a review10.1016/j.matpr.2020.09.628 ↗
19. Random forests10.1023/A:1010933404324 ↗
20. Introduction to analysis of variance10.1002/cem.3018 ↗
21. Investigating the effects of extrusion temperatures and material extrusion rates on FFF-printed thermoplastics10.1007/s00170-021-07850-5 ↗
22. Machine learning-based mechanical behavior optimization of 3D print constructs manufactured via the FFF process10.1007/s11665-021-06535-0 ↗
23. Impact of the fused deposition (FDM) printing process on polylactic acid (PLA) chemistry and structure10.3390/app7060579 ↗
24. Bioprinting 101: design, fabrication, and evaluation of cell-laden 3D bioprinted scaffolds10.1089/ten.tea.2019.0298 ↗
25. Ensemble learning
26. Experiment-based process modeling and optimization for high-quality and resource-efficient FFF 3D printing
27. 2009 · 275
28. Monitoring and control of biological additive manufacturing using machine learning10.1007/s10845-023-02092-6 ↗
29. Additive manufacturing technology and its implementation in construction as an eco-innovative solution10.1016/j.autcon.2018.05.005 ↗
30. Application of Taguchi method in the optimization of end milling parameters10.1016/S0924-0136(03)00865-3 ↗
31. Review of additive manufactured tissue engineering scaffolds: relationship between geometry and performance10.1186/s41038-018-0121-4 ↗
32. Fatigue performance of fused filament fabrication PLA specimens10.1016/j.matdes.2017.11.072 ↗
33. Effect of process variables on performances measured in filament and pellet based extrusion process10.1016/j.matpr.2021.05.508 ↗
34. Extreme fine-tuning and explainable AI model for non-destructive prediction of concrete compressive strength, the case of ConcreteXAI dataset10.1016/j.advengsoft.2024.103630 ↗
35. Energy consumption of common desktop additive manufacturing technologies
36. Investigation of polycaprolactone for bone tissue engineering scaffolds: in vitro degradation and biological studies10.1016/j.matdes.2022.110582 ↗
37. Effect of printing parameters on the thermal and mechanical properties of 3D-Printed PLA and PETG, using fused deposition modeling10.3390/polym13111758 ↗
38. Topography‐Supported nanoarchitectonics of hybrid scaffold for systematically modulated bone regeneration and remodeling
39. 3D printing of bone‐mimetic scaffold composed of Gelatin/β‐Tri‐Calcium phosphate for bone tissue engineering10.1002/mabi.202000256 ↗
40. An improved K-nearest-neighbor algorithm for text categorization10.1016/j.eswa.2011.08.040 ↗
41. Machine learning-based prediction for compressive and flexural strengths of steel fiber-reinforced concrete10.1016/j.conbuildmat.2020.121117 ↗
42. Data-driven moment-carrying capacity prediction of hybrid beams consisting of UHPC-NSC using machine learning-based models10.1016/j.istruc.2023.105733 ↗
43. Prediction of compressive strength of fly ash-based geopolymer concrete using supervised machine learning methods10.1007/s13369-023-08283-w ↗
44. Characterization of 3D-printed PLA parts with different raster orientations and printing speeds10.1038/s41598-022-05005-4 ↗
45. 3D‐Printed functional hydrogel by DNA‐Induced biomineralization for accelerated diabetic wound healing
46. The role of additive manufacturing for biomedical applications: a critical review10.1016/j.jmapro.2021.02.022 ↗
47. Evaluation of mechanical properties of 3D printed PETG and Polyamide (6) polymers
48. Mechanical characterization of FDM parts through instrumented flat indentation10.1007/s00170-023-10992-3 ↗
49. Scaffolds for bone-tissue engineering10.1016/j.matt.2022.06.003 ↗
50. Adaptive 3D printing for in situ adjustment of mechanical properties10.1002/aisy.202200229 ↗
51. 3D-printed versatile biliary stents with nanoengineered surface for anti-hyperplasia and antibiofilm formation
52. Effect of porosity and crystallinity on 3D printed PLA properties10.3390/polym11091487 ↗
53. Extrusion bioprinting of shear-thinning Gelatin Methacryloyl bioinks10.1002/adhm.201601451 ↗
54. A quantitative description for designing the extrudability of shear‐thinning physical hydrogels10.1002/mabi.202000295 ↗
55. Tensile strength of partially filled FFF printed parts: experimental results10.1108/RPJ-08-2015-0115 ↗
56. Chapter 11 - impact analysis of COVID-19 news headlines on global economy
57. Minitab LLC. "Analysis of variance table for Fit Regression Model." Copyright © 2023 Minitab, LLC. https://support.minitab.com/en-us/minitab/21/help-and-how-to/statistical-modeling/regression/how-to/fit-regression-model/interpret-the-results/all-statistics-and-graphs/analysis-of-variance-table/#p-value-regression (accessed 19.03.2024.
58. The roles and applications of additive manufacturing in the aerospace and automobile sector10.1016/j.matpr.2021.04.596 ↗
59. Ideal dataset splitting ratios in machine learning algorithms: general concerns for data scientists and data analysts
60. Application of gradient boosting regression model for the evaluation of feature selection techniques in improving reservoir characterisation predictions10.1016/j.petrol.2021.109244 ↗
61. Additive manufacturing in construction: a review on processes, applications, and digital planning methods
62. Feature selection based on artificial bee colony and gradient boosting decision tree10.1016/j.asoc.2018.10.036 ↗
63. Improvement of tensile and flexural properties of 3D printed PEEK through the increase of interfacial adhesion10.1016/j.jmapro.2023.03.024 ↗
64. Alginate and its application to tissue engineering10.1007/s42452-020-04096-w ↗
65. Modular strategies to build cell-free and cell-laden scaffolds towards bioengineered tissues and organs10.3390/jcm8111816 ↗
66. A beginner's guide to random Forest hyperparameter tuning
67. Numerical study of the impact of shear thinning behaviour on the strand deposition flow in the extrusion-based additive manufacturing
68. Resistance of PETG materials on thermocycling and brushing10.3390/dj11050135 ↗
69. Optimisation of FDM process parameters by Taguchi method for imparting customised properties to components10.1080/17452759.2018.1440722 ↗
70. Theory of support vector machines
71. Machine learning driven bond performance prediction between FRP bars and coral aggregate concrete10.1016/j.conbuildmat.2024.137684 ↗
72. Poly(ethylene terephthalate) copolymers that contain 5-tert-butylisophthalic acid and 1-3/1-4-cyclohexanedimethanol: synthesis, characterization, and properties10.1002/app.25592 ↗
73. Investigations of influence of infill pattern on tensile strength of 3D-printed poly lactic acid and Polyethylene Terephthalate Glycol material using Design of Experiments10.1016/j.matpr.2023.03.406 ↗
74. Additive manufacturing of biopolymers for tissue engineering and regenerative medicine: an overview, potential applications, advancements, and trends10.1155/2021/4907027 ↗
75. Machine learning model for predicting the hardness of additively manufactured acrylonitrile butadiene styrene
76. Engineering the biological performance of hierarchical nanostructured poly(ε-carpolactone) scaffolds for bone tissue engineering10.1016/j.cirp.2020.04.044 ↗
77. Using the Taguchi method for optimization of the powder metallurgy forming process for industry 3.510.1016/j.cie.2020.106635 ↗
78. Support Vector Machine Regression for project control forecasting10.1016/j.autcon.2014.07.014 ↗
79. Challenges with the development of biomaterials for sustainable tissue engineering10.3389/fbioe.2019.00127 ↗
80. A new part consolidation method to embrace the design freedom of additive manufacturing10.1016/j.jmapro.2015.06.024 ↗
81. Bone tissue engineering with porous hydroxyapatite ceramics10.1007/s10047-005-0292-1 ↗
82. An investigation of energy consumption in fused deposition modelling using ESP32 IoT monitoring System10.1016/j.procir.2023.02.045 ↗