Predicción mediante redes neuronales de los parámetros de diseño y de proceso para la fabricación por estereolitografía enmascarada (MSLA) de scaffolds sometidos a cargas de compresión

dc.contributor.advisorNarváez Tovar, Carlos Albertospa
dc.contributor.authorNajar Gomez, Brayan Sebastianspa
dc.contributor.researchgroupInnovación en Procesos de Manufactura E Ingeniería de Materiales (Ipmim)spa
dc.date.accessioned2025-04-01T19:15:58Z
dc.date.available2025-04-01T19:15:58Z
dc.date.issued2024-10-22
dc.descriptionilustraciones, diagramas, fotografíasspa
dc.description.abstractEn el presente trabajo se tiene por objetivo predecir mediante redes neuronales los parámetros de diseño y de proceso para la fabricación por estereolitografía enmascarada de scaffolds sometidos a cargas de compresión. Para ello se trabajó sobre una base de datos construida a partir de un diseño experimental Taguchi L9. Los parámetros por predecir corresponden a la compensación de la superficie media (O), el tamaño de la celda unitaria (CS) y el espesor de capa (LT). Las variables de entrada corresponden al esfuerzo de fluencia al 0.1% (Sy), así como el módulo elástico (E). Se planteo un modelo de regresión para los parámetros de O y CS, y un modelo de clasificación para LT. Para la definición de las arquitecturas de redes neuronales se recurrió a tres algoritmos de ajuste de hiperparámetros, los cuales corresponden a: GridSearch, RandomSearch y CoarseToFineSearch. El modelo de regresión seleccionado presenta tres (3) capas ocultas, con 8, 18 y 14 neuronas respectivamente, logrando un error medio absoluto (MAE) de 0.011 para el parámetro O, y de 0.144 para CS. En cuanto al modelo de clasificación la arquitectura consta de tres (3) capas ocultas, con 20, 20 y 16 neuronas respectivamente. La exactitud del modelo es de 77.8 %, sin embargo, hay presencia de sobreajuste. Durante la validación, se observó que el modelo mantiene la relación lineal entre E y Sy, con errores absolutos entre 0.176 MPa y 2.393 MPa para Sy y 5.07 MPa y 44.081 MPa para E. (Texto tomado de la fuente).spa
dc.description.abstractThis work aims to predict, through neural networks, the design and process parameters for the fabrication of scaffolds subjected to compression loads using masked stereolithography. A database was built based on a Taguchi L9 experimental design. The parameters to be predicted are the mean surface compensation (O), unit cell size (CS), and layer thickness (LT). The input variables are the 0.1% yield strength (Sy) and the elastic modulus (E). A regression model was developed for the O and CS parameters, and a classification model was developed for LT. Three hyperparameter tuning algorithms were used to define the neural network architectures: GridSearch, RandomSearch, and CoarseToFineSearch. The selected regression model consists of three hidden layers with 8, 18, and 14 neurons, achieving a mean absolute error (MAE) of 0.011 for the O parameter and 0.144 for CS. The classification model's architecture consists of three hidden layers with 20, 20, and 16 neurons, respectively, achieving an accuracy of 77.8%, although overfitting was present. During validation, it was observed that the model maintains the linear relationship between E and Sy, with absolute errors ranging from 0.176 MPa to 2.393 MPa for Sy and from 5.07 MPa to 44.081 MPa for E.eng
dc.description.degreelevelMaestríaspa
dc.description.degreenameMagíster en Ingeniería Mecánicaspa
dc.description.researchareaIngeniería de materiales y procesos de manufacturaspa
dc.format.extentxvi, 95 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/87804
dc.language.isospaspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Bogotáspa
dc.publisher.departmentDepartamento de Ingeniería Mecánica y Mecatrónicaspa
dc.publisher.facultyFacultad de Ingenieríaspa
dc.publisher.placeBogotá, Colombiaspa
dc.publisher.programBogotá - Ingeniería - Maestría en Ingeniería - Ingeniería Mecánicaspa
dc.relation.indexedBiremespa
dc.relation.referencesF. Günther, M. Wagner, S. Pilz, A. Gebert, and M. Zimmermann, “Design procedure for triply periodic minimal surface based biomimetic scaffolds,” J Mech Behav Biomed Mater, vol. 126, p. 104871, Feb. 2022, doi: 10.1016/J.JMBBM.2021.104871.spa
dc.relation.referencesD. Kong et al., “Design and manufacturing of biomimetic scaffolds for bone repair inspired by bone trabeculae,” Comput Biol Med, vol. 165, p. 107369, Oct. 2023, doi: 10.1016/J.COMPBIOMED.2023.107369.spa
dc.relation.referencesL. A. Can-Herrera, A. I. Oliva, M. A. A. Dzul-Cervantes, O. F. Pacheco-Salazar, and J. M. Cervantes-Uc, “Morphological and mechanical properties of electrospun polycaprolactone scaffolds: Effect of applied voltage,” Polymers (Basel), vol. 13, no. 4, 2021, doi: 10.3390/polym13040662.spa
dc.relation.referencesK. C. Feng et al., “The influence of roughness on stem cell differentiation using 3D printed polylactic acid scaffolds,” Soft Matter, vol. 14, no. 48, 2018, doi: 10.1039/c8sm01797b.spa
dc.relation.referencesY. Yao, W. Qin, B. Xing, N. Sha, T. Jiao, and Z. Zhao, “High performance hydroxyapatite ceramics and a triply periodic minimum surface structure fabricated by digital light processing 3D printing,” Journal of Advanced Ceramics, vol. 10, no. 1, 2021, doi: 10.1007/s40145-020-0415-4.spa
dc.relation.referencesD. Dong et al., “Microstructures and mechanical properties of biphasic calcium phosphate bioceramics fabricated by SLA 3D printing,” J Manuf Process, vol. 81, 2022, doi: 10.1016/j.jmapro.2022.07.016.spa
dc.relation.referencesP. Song et al., “DLP fabricating of precision GelMA/HAp porous composite scaffold for bone tissue engineering application,” Compos B Eng, vol. 244, Sep. 2022, doi: 10.1016/j.compositesb.2022.110163.spa
dc.relation.referencesC. Schmidleithner, S. Malferrari, R. Palgrave, D. Bomze, M. Schwentenwein, and D. M. Kalaskar, “Application of high resolution DLP stereolithography for fabrication of tricalcium phosphate scaffolds for bone regeneration,” Biomedical Materials (Bristol), vol. 14, no. 4, Jun. 2019, doi: 10.1088/1748-605X/ab279d.spa
dc.relation.referencesA. Dasan et al., “Up-cycling of LCD glass by additive manufacturing of porous translucent glass scaffolds,” Materials, vol. 14, no. 17, 2021, doi: 10.3390/ma14175083.spa
dc.relation.referencesD. Mondal et al., “mSLA-based 3D printing of acrylated epoxidized soybean oil - nano-hydroxyapatite composites for bone repair,” Materials Science and Engineering C, vol. 130, 2021, doi: 10.1016/j.msec.2021.112456.spa
dc.relation.referencesJ. H. Kang et al., “Mechanical and biological evaluation of lattice structured hydroxyapatite scaffolds produced via stereolithography additive manufacturing,” Mater Des, vol. 214, p. 110372, Feb. 2022, doi: 10.1016/J.MATDES.2021.110372.spa
dc.relation.referencesC. Feng et al., “Additive manufacturing of hydroxyapatite bioceramic scaffolds: Dispersion, digital light processing, sintering, mechanical properties, and biocompatibility,” Journal of Advanced Ceramics, vol. 9, no. 3, pp. 360–373, Jun. 2020, doi: 10.1007/S40145-020-0375-8/METRICS.spa
dc.relation.referencesF. Baino et al., “Digital light processing stereolithography of hydroxyapatite scaffolds with bone-like architecture, permeability, and mechanical properties,” Journal of the American Ceramic Society, vol. 105, no. 3, 2022, doi: 10.1111/jace.17843.spa
dc.relation.referencesY. Wang, S. Chen, H. Liang, Y. Liu, J. Bai, and M. Wang, “Digital light processing (DLP) of nano biphasic calcium phosphate bioceramic for making bone tissue engineering scaffolds,” Ceram Int, vol. 48, no. 19, pp. 27681–27692, Oct. 2022, doi: 10.1016/J.CERAMINT.2022.06.067.spa
dc.relation.referencesH. Zhang, H. Zhang, Y. Xiong, L. Dong, and X. Li, “Development of hierarchical porous bioceramic scaffolds with controlled micro/nano surface topography for accelerating bone regeneration,” Materials Science and Engineering: C, vol. 130, p. 112437, Nov. 2021, doi: 10.1016/J.MSEC.2021.112437.spa
dc.relation.referencesH. K. Lim et al., “3D-printed ceramic bone scaffolds with variable pore architectures,” Int J Mol Sci, vol. 21, no. 18, 2020, doi: 10.3390/ijms21186942.spa
dc.relation.referencesP. Navarrete-Segado, M. Tourbin, C. Frances, and D. Grossin, “Masked stereolithography of hydroxyapatite bioceramic scaffolds: From powder tailoring to evaluation of 3D printed parts properties,” Open Ceramics, vol. 9, 2022, doi: 10.1016/j.oceram.2022.100235.spa
dc.relation.referencesH. Liang, Y. Wang, S. Chen, Y. Liu, Z. Liu, and J. Bai, “Nano-Hydroxyapatite Bone Scaffolds with Different Porous Structures Processed by Digital Light Processing 3D Printing,” Int J Bioprint, vol. 8, no. 1, 2022, doi: 10.18063/IJB.V8I1.502.spa
dc.relation.referencesR. Brighenti, L. Marsavina, M. P. Marghitas, M. Montanari, A. Spagnoli, and F. Tatar, “The effect of process parameters on mechanical characteristics of specimens obtained via DLP additive manufacturing technology,” Mater Today Proc, vol. 78, pp. 331–336, Jan. 2023, doi: 10.1016/J.MATPR.2023.01.092.spa
dc.relation.referencesP. Yadav, S. Dev, I. Hussain, and R. Kumar, “Evaluation of additive manufacturing process parameters for improved mechanical properties of thermoplastic parts,” Mater Today Proc, Dec. 2022, doi: 10.1016/J.MATPR.2022.12.150.spa
dc.relation.referencesS. S. Biriaie, M. Nouari, H. Ben Boubaker, and P. Laheurte, “Effect of additive manufacturing process parameters on the titanium alloy microstructure, properties and surface integrity,” Procedia CIRP, vol. 108, no. C, pp. 811–816, Jan. 2022, doi: 10.1016/J.PROCIR.2022.03.126.spa
dc.relation.referencesI. Valizadeh, T. Tayyarian, and O. Weeger, “Influence of process parameters on geometric and elasto-visco-plastic material properties in vat photopolymerization,” Addit Manuf, vol. 72, p. 103641, Jun. 2023, doi: 10.1016/J.ADDMA.2023.103641.spa
dc.relation.referencesA. W. Gebisa and H. G. Lemu, “Influence of 3D Printing FDM Process Parameters on Tensile Property of ULTEM 9085,” Procedia Manuf, vol. 30, pp. 331–338, Jan. 2019, doi: 10.1016/J.PROMFG.2019.02.047.spa
dc.relation.referencesA. M. Khorasani, I. Gibson, U. S. Awan, and A. Ghaderi, “The effect of SLM process parameters on density, hardness, tensile strength and surface quality of Ti-6Al-4V,” Addit Manuf, vol. 25, pp. 176–186, Jan. 2019, doi: 10.1016/J.ADDMA.2018.09.002.spa
dc.relation.referencesD. S. Nagaraju, R. L. Krupakaran, C. Sripadh, G. Nitin, and G. Joy Joseph Emmanuel, “Mechanical properties of 3D printed specimen using FDM (Fused deposition modelling) and SLA (Stereolithography) technologies,” Mater Today Proc, Oct. 2023, doi: 10.1016/J.MATPR.2023.09.223.spa
dc.relation.referencesQ. Alsandi et al., “Evaluation of mechanical and physical properties of light and heat polymerized udma for dlp 3d printer,” Sensors, vol. 21, no. 10, 2021, doi: 10.3390/s21103331.spa
dc.relation.referencesY. Zhao, K. Zhao, Y. Li, and F. Chen, “Mechanical characterization of biocompatible PEEK by FDM,” J Manuf Process, vol. 56, 2020, doi: 10.1016/j.jmapro.2020.04.063.spa
dc.relation.referencesD. Veeman, S. Sudharsan, G. J. Surendhar, R. Shanmugam, and L. Guo, “Machine learning model for predicting the hardness of additively manufactured acrylonitrile butadiene styrene,” Mater Today Commun, vol. 35, p. 106147, Jun. 2023, doi: 10.1016/J.MTCOMM.2023.106147.spa
dc.relation.referencesR. Joy, J. Jude Kuzhivelil, R. Kannan, S. Sivan P.P., and M. M. Mohammed, “ANN modelling of additively manufactured carbon fibre integrated ABS,” Mater Today Proc, vol. 72, pp. 3137–3143, Jan. 2023, doi: 10.1016/J.MATPR.2022.10.004.spa
dc.relation.referencesH. Hassanin, Y. Alkendi, M. Elsayed, K. Essa, and Y. Zweiri, “Controlling the Properties of Additively Manufactured Cellular Structures Using Machine Learning Approaches,” Adv Eng Mater, vol. 22, no. 3, Mar. 2020, doi: 10.1002/adem.201901338.spa
dc.relation.referencesW. Alhaddad, M. He, Y. Halabi, and K. Yahya Mohammed Almajhali, “Optimizing the material and printing parameters of the additively manufactured fiber-reinforced polymer composites using an artificial neural network model and artificial bee colony algorithm,” Structures, vol. 46, pp. 1781–1795, Dec. 2022, doi: 10.1016/j.istruc.2022.10.134.spa
dc.relation.referencesJ. Giri, P. Shahane, S. Jachak, R. Chadge, and P. Giri, “Optimization of fdm process parameters for dual extruder 3d printer using artificial neural network,” in Materials Today: Proceedings, Elsevierspa
dc.relation.referencesP. L. Narayana et al., “Optimization of process parameters for direct energy deposited Ti-6Al-4V alloy using neural networks,” International Journal of Advanced Manufacturing Technology, vol. 114, no. 11–12, pp. 3269–3283, 2021, doi: 10.1007/s00170-021-07115-1.spa
dc.relation.referencesM. S. Saad, A. Mohd Nor, I. Abd Rahim, M. A. Syahruddin, and I. Z. Mat Darus, “Optimization of FDM process parameters to minimize surface roughness with integrated artificial neural network model and symbiotic organism search,” Neural Comput Appl, 2022, doi: 10.1007/s00521-022-07370-7.spa
dc.relation.referencesM. Shirmohammadi, S. J. Goushchi, and P. M. Keshtiban, “Optimization of 3D printing process parameters to minimize surface roughness with hybrid artificial neural network model and particle swarm algorithm,” Progress in Additive Manufacturing, vol. 6, no. 2, pp. 199–215, May 2021, doi: 10.1007/s40964-021-00166-6.spa
dc.relation.referencesM. Zhao, H. Wei, Y. Mao, C. Zhang, T. Liu, and W. Liao, “Predictions of Additive Manufacturing Process Parameters and Molten Pool Dimensions with a Physics-Informed Deep Learning Model,” Engineering, vol. 23, pp. 181–195, Apr. 2023, doi: 10.1016/J.ENG.2022.09.015.spa
dc.relation.referencesC. A. Ramírez Rodríguez, “Efecto de los parámetros geométricos de la celda unitaria TPMS y los parámetros de impresión por fotopolimerización en la rugosidad superficial de scaffolds para cultivo de tejido óseo in vitro.,” Tesis de Maestría, Universidad Nacional de Colombia, Bogotá, 2024.spa
dc.relation.referencesW. R. Wagner, S. E. Sakiyama-Elbert, G. Zhang, and M. J. Yaszemski, Biomaterials Science: An Introduction to Materials in Medicine. 2020. doi: 10.1016/C2017-0-02323-6.spa
dc.relation.referencesG. Khang, Handbook of intelligent scaffolds for tissue engineering and regenerative medicine, 2nd edition. 2017. doi: 10.1201/9781315364698.spa
dc.relation.referencesZ. Liu, H. Gong, J. Gao, and L. Liu, “Topological design, mechanical responses and mass transport characteristics of high strength-high permeability TPMS-based scaffolds,” Int J Mech Sci, vol. 217, 2022, doi: 10.1016/j.ijmecsci.2021.107023.spa
dc.relation.referencesF. Lu et al., “Rational design of bioceramic scaffolds with tuning pore geometry by stereolithography: Microstructure evaluation and mechanical evolution,” J Eur Ceram Soc, vol. 41, no. 2, 2021, doi: 10.1016/j.jeurceramsoc.2020.10.002.spa
dc.relation.referencesY. Li et al., “The design of strut/TPMS-based pore geometries in bioceramic scaffolds guiding osteogenesis and angiogenesis in bone regeneration,” Mater Today Bio, vol. 20, 2023, doi: 10.1016/j.mtbio.2023.100667.spa
dc.relation.referencesI. Bouakaz, C. Drouet, D. Grossin, E. Cobraiville, and G. Nolens, “Hydroxyapatite 3D-printed scaffolds with Gyroid-Triply periodic minimal surface porous structure: Fabrication and an in vivo pilot study in sheep,” Acta Biomater, vol. 170, 2023, doi: 10.1016/j.actbio.2023.08.041.spa
dc.relation.referencesD. Khrapov et al., “Geometrical features and mechanical properties of the sheet-based gyroid scaffolds with functionally graded porosity manufactured by electron beam melting,” Mater Today Commun, vol. 35, 2023, doi: 10.1016/j.mtcomm.2023.106410.spa
dc.relation.referencesZ. L. Deng, M. Z. Pan, S. Bin Hua, J. M. Wu, X. Y. Zhang, and Y. S. Shi, “Mechanical and degradation properties of triply periodic minimal surface (TPMS) hydroxyapatite & akermanite scaffolds with functional gradient structure,” Ceram Int, vol. 49, no. 12, 2023, doi: 10.1016/j.ceramint.2023.03.213.spa
dc.relation.referencesK. Song, Z. Wang, J. Lan, and S. Ma, “Porous structure design and mechanical behavior analysis based on TPMS for customized root analogue implant,” J Mech Behav Biomed Mater, vol. 115, 2021, doi: 10.1016/j.jmbbm.2020.104222.spa
dc.relation.referencesL. J. Gibson and M. F. Ashby, Cellular solids: Structure and properties, second edition. 2014. doi: 10.1017/CBO9781139878326.spa
dc.relation.referencesT. Maconachie et al., “SLM lattice structures: Properties, performance, applications and challenges,” 2019. doi: 10.1016/j.matdes.2019.108137.spa
dc.relation.referencesS. Frey, “Laser SLA vs DLP vs Masked SLA 3D Printing Technology.” Accessed: Oct. 16, 2024. [Online]. Available: https://theorthocosmos.com/laser-sla-vs-dlp-vs-masked-sla-3d-printing-technology-compared/spa
dc.relation.referencesJ. Kelleher, B. Mac Namee, and A. D’Arcy, Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies, vol. 53, no. 9. 2020.spa
dc.relation.referencesY. Bengio, I. Goodfellow, and A. Courville, Deep learning, vol. 1. MIT press Cambridge, MA, USA, 2017.spa
dc.relation.referencesC. C. Aggarwal and others, Neural networks and deep learning, vol. 10, no. 978. Springer, 2018.spa
dc.relation.referencesC. M. Bishop and N. M. Nasrabadi, Pattern recognition and machine learning, vol. 4, no. 4. Springer, 2006.spa
dc.relation.referencesS. Haykin, Neural networks and learning machines, 3/E. Pearson Education India, 2009.spa
dc.relation.referencesS. Samarasinghe, Neural networks for applied sciences and engineering: from fundamentals to complex pattern recognition. Auerbach publications, 2016.spa
dc.relation.referencesB. Pandey, “How Do Neural Networks Make Decisions? A Look at Activation Functions.” Accessed: Oct. 13, 2024. [Online]. Available: https://www.goglides.dev/bkpandey/how-do-neural-networks-make-decisions-a-look-at-activation-functions-141espa
dc.relation.referencesN. K. Sivakumar et al., “Predictive modeling of compressive strength for additively manufactured PEEK spinal fusion cages using machine learning techniques,” Mater Today Commun, vol. 38, 2024, doi: 10.1016/j.mtcomm.2024.108307.spa
dc.relation.referencesZ. Li, Z. Zhang, J. Shi, and D. Wu, “Prediction of surface roughness in extrusion-based additive manufacturing with machine learning,” Robot Comput Integr Manuf, vol. 57, 2019, doi: 10.1016/j.rcim.2019.01.004.spa
dc.relation.referencesI. Baturynska and K. Martinsen, “Prediction of geometry deviations in additive manufactured parts: comparison of linear regression with machine learning algorithms,” J Intell Manuf, vol. 32, no. 1, 2021, doi: 10.1007/s10845-020-01567-0.spa
dc.relation.referencesZ. Zhan and H. Li, “Machine learning based fatigue life prediction with effects of additive manufacturing process parameters for printed SS 316L,” Int J Fatigue, vol. 142, 2021, doi: 10.1016/j.ijfatigue.2020.105941.spa
dc.relation.referencesD. Soler, M. Telleria, M. B. García-Blanco, E. Espinosa, M. Cuesta, and P. J. Arrazola, “Prediction of Surface Roughness of SLM Built Parts after Finishing Processes Using an Artificial Neural Network,” Journal of Manufacturing and Materials Processing, vol. 6, no. 4, 2022, doi: 10.3390/jmmp6040082.spa
dc.relation.referencesA. S. Mohammed, M. Almutahhar, K. Sattar, A. Alhajeri, A. Nazir, and U. Ali, “Deep learning based porosity prediction for additively manufactured laser powder-bed fusion parts,” Journal of Materials Research and Technology, vol. 27, pp. 7330–7335, Nov. 2023, doi: 10.1016/J.JMRT.2023.11.130.spa
dc.relation.referencesN. Phadke, R. Raj, A. Kumar Srivastava, S. Dwivedi, and A. Rai Dixit, “Modeling and parametric optimization of laser powder bed fusion 3D printing technique using artificial neural network for enhancing dimensional accuracy,” Mater Today Proc, vol. 56, 2022, doi: 10.1016/j.matpr.2022.02.523.spa
dc.relation.referencesZ. Li et al., “Design of nonlinear gradient sheet-based TPMS-lattice using artificial neural networks,” Journal of Materials Research and Technology, vol. 33, pp. 223–234, Nov. 2024, doi: 10.1016/J.JMRT.2024.09.051.spa
dc.relation.referencesJ. Peloquin, A. Kirillova, C. Rudin, L. C. Brinson, and K. Gall, “Prediction of tensile performance for 3D printed photopolymer gyroid lattices using structural porosity, base material properties, and machine learning,” Mater Des, vol. 232, 2023, doi: 10.1016/j.matdes.2023.112126.spa
dc.relation.referencesK. Sandeep Varma, K. Lal Meena, and R. B. R. Chekuri, “Optimizing mechanical properties of 3D-printed aramid fiber-reinforced polyethylene terephthalate glycol composite: A systematic approach using BPNN and ANOVA,” Engineering Science and Technology, an International Journal, vol. 56, p. 101785, Aug. 2024, doi: 10.1016/J.JESTCH.2024.101785.spa
dc.relation.referencesN. Vidakis, M. Petousis, N. Mountakis, E. Maravelakis, S. Zaoutsos, and J. D. Kechagias, “Mechanical response assessment of antibacterial PA12/TiO2 3D printed parts: parameters optimization through artificial neural networks modeling,” International Journal of Advanced Manufacturing Technology, vol. 121, no. 1–2, 2022, doi: 10.1007/s00170-022-09376-w.spa
dc.relation.referencesR. Teharia, R. M. Singari, and H. Kumar, “Optimization of process variables for additive manufactured PLA based tensile specimen using taguchi design and artificial neural network (ANN) technique,” Mater Today Proc, vol. 56, 2022, doi: 10.1016/j.matpr.2021.10.376.spa
dc.relation.referencesW. Alhaddad, M. He, Y. Halabi, and K. Yahya Mohammed Almajhali, “Optimizing the material and printing parameters of the additively manufactured fiber-reinforced polymer composites using an artificial neural network model and artificial bee colony algorithm,” Structures, vol. 46, pp. 1781–1795, Dec. 2022, doi: 10.1016/J.ISTRUC.2022.10.134.spa
dc.relation.referencesMinitab, “Gráficas de residuos para Ajustar modelo lineal general.” Accessed: Oct. 16, 2024. [Online]. Available: https://support.minitab.com/es-mx/minitab/help-and-how-to/statistical-modeling/anova/how-to/fit-general-linear-model/interpret-the-results/all-statistics-and-graphs/residual-plots/spa
dc.relation.referencesE. Hazir, K. H. Koc, and S. Hiziroglu, “Optimization Of Sanding Parameters Using Response Surface Methodology,” Maderas: Ciencia y Tecnologia, vol. 19, no. 4, 2017, doi: 10.4067/S0718-221X2017005000101.spa
dc.relation.referencesA. Agresti and C. Franklin, “The art and science of learning from data,” 3rd ed., Pearson, 2007, ch. 15, pp. 733–742.spa
dc.relation.referencesS. Okoye Kingsley and Hosseini, “Mann–Whitney U Test and Kruskal–Wallis H Test Statistics in R,” in R Programming: Statistical Data Analysis in Research, Singapore: Springer Nature Singapore, 2024, pp. 225–246. doi: 10.1007/978-981-97-3385-9_11.spa
dc.relation.referencesL. F. B. Souza et al., “Evaluating mechanical and surface properties of zirconia-containing composites: 3D printing, subtractive, and layering techniques,” J Mech Behav Biomed Mater, vol. 157, p. 106608, Sep. 2024, doi: 10.1016/J.JMBBM.2024.106608.spa
dc.relation.referencesA. Rabinowitz, P. M. DeSantis, C. Basgul, H. Spece, and S. M. Kurtz, “Taguchi optimization of 3D printed short carbon fiber polyetherketoneketone (CFR PEKK),” J Mech Behav Biomed Mater, vol. 145, 2023, doi: 10.1016/j.jmbbm.2023.105981.spa
dc.relation.referencesS. Sidney, “Nonparametric statistics for the behavioral sciences,” no. 3, McGraw-Hill, 1957, ch. 8, pp. 184–194.spa
dc.relation.referencesLearn Statistics Easily, “Kruskal-Wallis Test: Mastering Non-Parametric Analysis for Multiple Groups.” Accessed: Oct. 19, 2024. [Online]. Available: https://statisticseasily.com/kruskal-wallis-test/spa
dc.relation.referencesSPSS Tutorials, “Kruskal-Wallis Test – Simple Tutorial.” Accessed: Oct. 19, 2024. [Online]. Available: https://www.spss-tutorials.com/kruskal-wallis-test/#ref4spa
dc.relation.referencesN. YÜKSEL, O. EREN, H. R. BÖRKLÜ, and H. K. SEZER, “Mechanical properties of additively manufactured lattice structures designed by deep learning,” Thin-Walled Structures, vol. 196, 2024, doi: 10.1016/j.tws.2023.111475.spa
dc.relation.referencesW. Liang, M. Lou, Y. Wang, C. Zhang, S. Chen, and C. Cui, “A fatigue crack growth prediction method on small datasets based on optimized deep neural network and Delaunay data augmentation,” Theoretical and Applied Fracture Mechanics, vol. 129, 2024, doi: 10.1016/j.tafmec.2023.104218.spa
dc.relation.referencesE. M. Dogo, O. J. Afolabi, N. I. Nwulu, B. Twala, and C. O. Aigbavboa, “A Comparative Analysis of Gradient Descent-Based Optimization Algorithms on Convolutional Neural Networks,” in Proceedings of the International Conference on Computational Techniques, Electronics and Mechanical Systems, CTEMS 2018, 2018. doi: 10.1109/CTEMS.2018.8769211.spa
dc.relation.referencesS. Bera and V. K. Shrivastava, “Analysis of various optimizers on deep convolutional neural network model in the application of hyperspectral remote sensing image classification,” Int J Remote Sens, vol. 41, no. 7, 2020, doi: 10.1080/01431161.2019.1694725.spa
dc.relation.referencesN. S. Huda, M. S. Mubarok, and Adiwijaya, “A multi-label classification on topics of quranic verses (english translation) using backpropagation neural network with stochastic gradient descent and adam optimizer,” in 2019 7th International Conference on Information and Communication Technology, ICoICT 2019, 2019. doi: 10.1109/ICoICT.2019.8835362.spa
dc.relation.referencesP. Poudel, S. H. Bae, and B. Jang, “Comparison of Different Deep Learning Optimizers for Modeling Photovoltaic Power,” J. Chosun Natural Sci, vol. 11, no. 4, 2018.spa
dc.relation.referencesB. Ding, H. Qian, and J. Zhou, “Activation functions and their characteristics in deep neural networks,” in Proceedings of the 30th Chinese Control and Decision Conference, CCDC 2018, 2018. doi: 10.1109/CCDC.2018.8407425.spa
dc.relation.referencesT. Szandała, “Review and Comparison of Commonly Used Activation Functions for Deep Neural Networks,” in Bio-inspired Neurocomputing, A. K. Bhoi, P. K. Mallick, C.-M. Liu, and V. E. Balas, Eds., Singapore: Springer Singapore, 2021, pp. 203–224. doi: 10.1007/978-981-15-5495-7_11.spa
dc.relation.referencesLouis. Owen, “Hyperparameter Tuning with Python,” Packt, 2022, ch. 12, pp. 233–243.spa
dc.relation.referencesH. Follet et al., “Effects of preexisting microdamage, collagen cross-links, degree of mineralization, age, and architecture on compressive mechanical properties of elderly human vertebral trabecular bone,” Journal of Orthopaedic Research, vol. 29, no. 4, 2011, doi: 10.1002/jor.21275.spa
dc.relation.referencesP. Augat, T. Link, T. F. Lang, J. C. Lin, S. Majumdar, and H. K. Genant, “Anisotropy of the elastic modulus of trabecular bone specimens from different anatomical locations,” Med Eng Phys, vol. 20, no. 2, 1998, doi: 10.1016/S1350-4533(98)00001-0.spa
dc.relation.referencesJ. Black and G. Hastings, Handbook of Biomaterial Properties, 1st ed. London: Chapman & Hall, 1998. doi: 10.1007/978-1-4615-5801-9.spa
dc.relation.referencesC. E. Misch, Z. Qu, and M. W. Bidez, “Mechanical properties of trabecular bone in the human mandible: Implications for dental implant treatment planning and surgical placement,” Journal of Oral and Maxillofacial Surgery, vol. 57, no. 6, 1999, doi: 10.1016/S0278-2391(99)90437-8.spa
dc.relation.referencesM. Araya, J. Murillo, R. Vindas, and T. Guillén, “Compressive behavior of SLA open-cell lattices: A comparison between triply periodic minimal surface gyroid and stochastic structures for artificial bone,” Materialia (Oxf), vol. 38, p. 102233, Dec. 2024, doi: 10.1016/J.MTLA.2024.102233.spa
dc.relation.referencesE. Mancini, M. Utzeri, E. Farotti, A. Lattanzi, and M. Sasso, “DLP printed 3D gyroid structure: Mechanical response at meso and macro scale,” Mechanics of Materials, vol. 192, 2024, doi: 10.1016/j.mechmat.2024.104970.spa
dc.relation.referencesI. Cazin, M. O. Gleirscher, M. Fleisch, M. Berer, M. Sangermano, and S. Schlögl, “Spatially controlling the mechanical properties of 3D printed objects by dual-wavelength vat photopolymerization,” Addit Manuf, vol. 57, 2022, doi: 10.1016/j.addma.2022.102977.spa
dc.relation.referencesJ. Huang, P. Fu, W. Li, L. Xiao, J. Chen, and X. Nie, “Influence of crosslinking density on the mechanical and thermal properties of plant oil-based epoxy resin,” RSC Adv, vol. 12, no. 36, 2022, doi: 10.1039/d2ra04206a.spa
dc.relation.referencesD. Miedzińska, R. Gieleta, and E. Małek, “Experimental study of strength properties of SLA resins under low and high strain rates,” Mechanics of Materials, vol. 141, 2020, doi: 10.1016/j.mechmat.2019.103245.spa
dc.relation.referencesS. Park, A. M. Smallwood, and C. Y. Ryu, “Mechanical and thermal properties of 3d-printed thermosets by stereolithography,” Journal of Photopolymer Science and Technology, vol. 32, no. 2, 2019, doi: 10.2494/photopolymer.32.227.spa
dc.relation.referencesR. Liu, L. Ma, H. Liu, B. Xu, C. Feng, and R. He, “Effects of pore size on the mechanical and biological properties of stereolithographic 3D printed HAp bioceramic scaffold,” Ceram Int, vol. 47, no. 20, 2021, doi: 10.1016/j.ceramint.2021.07.053.spa
dc.relation.referencesN. Butler, Y. Zhao, S. Lu, and S. Yin, “Effects of light exposure intensity and time on printing quality and compressive strength of β-TCP scaffolds fabricated with digital light processing,” J Eur Ceram Soc, vol. 44, no. 4, 2024, doi: 10.1016/j.jeurceramsoc.2023.11.046.spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseAtribución-NoComercial-CompartirIgual 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/spa
dc.subject.ddc620 - Ingeniería y operaciones afines::629 - Otras ramas de la ingenieríaspa
dc.subject.ddc600 - Tecnología (Ciencias aplicadas)::607 - Educación, investigación, temas relacionadosspa
dc.subject.decsAndamios del Tejidospa
dc.subject.decsTissue Scaffoldseng
dc.subject.decsRedes Neuronales Celulares Computacionalesspa
dc.subject.decsCellular Neural Networks, Computereng
dc.subject.proposalManufactura aditivaspa
dc.subject.proposalEstereolitografía enmascaradaspa
dc.subject.proposalRedes neuronales artificialesspa
dc.subject.proposalScaffoldeng
dc.subject.proposalPropiedades mecánicasspa
dc.subject.proposalResistencia a compresiónspa
dc.subject.proposalAdditive manufacturingeng
dc.subject.proposalMasked stereolithographyeng
dc.subject.proposalArtificial neural networkseng
dc.subject.proposalMechanical propertieseng
dc.subject.proposalCompression strengtheng
dc.subject.wikidataestereolitografíaspa
dc.subject.wikidatastereolithographyeng
dc.titlePredicción mediante redes neuronales de los parámetros de diseño y de proceso para la fabricación por estereolitografía enmascarada (MSLA) de scaffolds sometidos a cargas de compresiónspa
dc.title.translatedDesign and manufacturing parameters prediction by neural networks for the fabrication by MSLA of scaffolds subjected to compression loadeng
dc.typeTrabajo de grado - Maestríaspa
dc.type.coarhttp://purl.org/coar/resource_type/c_bdccspa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/masterThesisspa
dc.type.redcolhttp://purl.org/redcol/resource_type/TMspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
dcterms.audience.professionaldevelopmentEstudiantesspa
dcterms.audience.professionaldevelopmentInvestigadoresspa
dcterms.audience.professionaldevelopmentMaestrosspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
1023980137.2024.pdf
Tamaño:
6.28 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Maestría en Ingeniería - Ingeniería Mecánica

Bloque de licencias

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
license.txt
Tamaño:
5.74 KB
Formato:
Item-specific license agreed upon to submission
Descripción: