Keywords
Computational materials science
Biomedical materials
Titanium alloys
How to Cite
Abstract
Titanium alloys are widely preferred in the healthcare sector as biocompatible materials due to their superior properties such as low density and exceptional mechanical strength. Their low density provides lightweight solutions, and their density is closer to that of human bone compared to other metallic alloys with similar strength. This similarity facilitates a balanced load distribution between the bone and the implant, enhancing biomechanical compatibility. This study investigates the effects of alloying elements on the density of titanium-based biomedical materials using a computational materials science approach. A total of 72 different compositions of Ti-Al-V alloys were modeled using JMatPro software, and their densities were simulated at room temperature (25°C). The simulation produced a comprehensive dataset, which was utilized to train an explainable artificial intelligence (XAI) model. Advanced interpretability techniques, including SHAP (SHapley Additive exPlanations), LIME (Local Interpretable Model-agnostic Explanations), and Partial Dependence Plots (PDP), were employed to elucidate the influence of each alloying element on the density. The dataset was analyzed using an XAI-based regression model implemented with the Artificial Neural Network (ANN) algorithm. The interpretability graphs provided insights into the individual contributions of the alloying elements, revealing their positive or negative effects on the density. The findings offer a deeper understanding of the role of alloying elements in optimizing the performance of titanium-based biomedical materials, particularly in achieving lightweight designs. This study highlights the potential of integrating computational material modeling with explainable AI to advance the design and development of high-performance lightweight materials for biomedical applications.
References
Alipour, H., M. Asgari Bajgirani, and M. Sahihi, 2022 Investigation of Mechanical, Thermal, Electrical, and Hydrogen Diffusion Properties in Ternary V-Ti-X Alloys: A Density Functional Theory Study. Journal of Physical Chemistry C 126: 1672–1687.
Alqattan, M., L. Peters, Y. Alshammari, F. Yang, and L. Bolzoni, 2020 Antibacterial Ti-Mn-Cu alloys for biomedical applications. Regenerative Biomaterials 8: rbaa050.
Bodunrin, M. O., L. H. Chown, J. W. van der Merwe, and K. K. Alaneme, 2020 On the substitution of vanadium with iron in Ti–6Al–4V: Thermo-Calc simulation and processing map considerations for design of low-cost alloys. Materials Science and Engineering: A 791: 139622.
Brusewitz Lindahl, B., X. L. Liu, Z.-K. Liu, and M. Selleby, 2015 A thermodynamic re-assessment of Al-V toward an assessment of the ternary Al-Ti-V system. Calphad 51: 75–88.
Barbinta, A., K. Earar, C. Crimu, L. Dr˘agan, and C. Munteanu, 2013 In Vitro Evaluation of the Cytotoxicity of Some New Titanium Alloys. Key Engineering Materials 587: 303–308.
Ferdib-Al-Islam, A. Saha, E. J. Bristy, M. Rahatul Islam, R. Afzal, et al., 2023 LIME-based Explainable AI Models for Predicting Disease from Patient’s Symptoms. In 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), pp. 1–6.
Friedman, J. H., 2001 Greedy function approximation: a gradient boosting machine. Annals of Statistics pp. 1189–1232.
Goodfellow, I., Y. Bengio, and A. Courville, 2016 Deep Learning. Adaptive Computation and Machine Learning series, MIT Press.
Hagan, M. T., H. B. Demuth, M. H. Beale, and O. De Jesús, 2014 Neural Network Design. Martin Hagan.
Hayyawi, A. R., H. Al-Ethari, and A. H. Haleem, 2022 Development of β-Ti Alloys for Biomedical Applications – A Review. 2022 13th International Conference on Mechanical and Aerospace Engineering (ICMAE) pp. 1–6.
Ikedaa, M., M. Ueda, and M. Ninomi, 2020 Recent Studies and Developments in Titanium Biomaterials. MATECWeb of Conferences 321: 2004.
Ivanov, E., E. del Rio, I. Kapchemnko, M. Nyström, and J. Kotila, 2018 Development of Bio-Compatible Beta Ti Alloy Powders for Additive Manufacturing for Application in Patient-Specific Orthopedic Implants. Key Engineering Materials 770: 9–17.
Kartamyshev, A., A. Lipnitskii, A. O. Boev, I. Nelasov, V. Maksimenko, et al., 2020 Angular dependent interatomic potential for Ti-V system for molecular dynamics simulations. Modelling and Simulation in Materials Science and Engineering.
Li, K., G. Fan, G. Fan, W. Zheng, J. Wang, et al., 2024 Thermodynamic modeling of the ti–al–v system over the entire composition and a wide temperature range. Calphad: Computer Coupling of Phase Diagrams and Thermochemistry 85: 102683.
Li, Y. H., X. J. Liang, and T. Fan, 2011 Research development of biomedical titanium alloy. Applied Mechanics and Materials 55: 2009–2012.
Luan, J. H., Z. B. Jiao, W. H. Liu, Z. P. Lu, W. X. Zhao, et al., 2017 Compositional and microstructural optimization and mechanical-property enhancement of cast Ti alloys based on Ti-6Al-4V alloy. Materials Science and Engineering: A 704: 91–101.
Lundberg, S. M. and S.-I. Lee, 2017 A Unified Approach to Interpreting Model Predictions. In Neural Information Processing Systems.
Madalina Simona, B., C.-A. Tugui, M. Perju, M. Benchea, C. Spataru, et al., 2019 Biocompatible Titanium Alloys used in Medical Applications. Revista de Chimie 70: 1302–1306.
Maitra, V., C. Arrasmith, and J. Shi, 2024 Introducing explainable artificial intelligence to property prediction in metal additive manufacturing. Manufacturing Letters 41: 1125–1135.
Manojlovic, V. and G. Markovic, 2023 Titanium Alloys Database for Medical Applications. Metallurgical and Materials Data 1: 1–6.
Niinomi, M., 2008 Biologically and Mechanically Biocompatible Titanium Alloys. Materials Transactions - Mater Trans 49: 2170–2178.
Niinomi, M., Y. Liu, M. Nakai, H. Liu, and H. Li, 2016 Biomedical titanium alloys with Young’s moduli close to that of cortical bone. Regenerative Biomaterials 3: 173–185.
Phume, L., S. L. Pityana, C. Meacock, and A. P. I. Popoola, 2012 Laser coating of hafnium on Ti6Al4 for biomedical applications.
Ribeiro, M. T., S. Singh, and C. Guestrin, 2016 "Why Should I Trust You?": Explaining the Predictions of Any Classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, pp. 1135–1144, New York, NY, USA, Association for Computing Machinery.
Scavuzzo, C. M., J. M. Scavuzzo, M. N. Campero, M. Anegagrie, A. A. Aramendia, et al., 2022 Feature importance: Opening a soil-transmitted helminth machine learning model via SHAP. Infectious Disease Modelling 7: 262–276.
Sun, R. and G. Mi, 2023 Influence of Alloying Elements Content on High Temperature Properties of Ti-V-Cr and Ti-Al-V Series Titanium Alloys: A JMatPro Program Calculation Study. Journal of Physics: Conference Series 2639: 12019.
Togacar, M., Z. Cömert, and B. Ergen, 2021 Enhancing of dataset using DeepDream, fuzzy color image enhancement and hypercolumn techniques to detection of the Alzheimer’s disease stages by deep learning model. Neural Computing and Applications 33: 9877–9889.
Togacar, M., B. Ergen, and V. Tümen, 2022 Use of dominant activations obtained by processing OCT images with the CNNs and slime mold method in retinal disease detection. Biocybernetics and Biomedical Engineering 42: 646–666.
Valipoorsalimi, P., 2023 Machine Learning Assisted Investigation of High-Strength Biocompatible and Biodegradable Magnesium Alloy. Ph.D. thesis, McGill University (Canada), Canada – Quebec, CA.
Wan, Y., Y. Zeng, X. Qian, Q. Yang, K. Sun, et al., 2020 First-principles calculations of structural, elastic and electronic properties of second phases and solid solutions in Ti–Al–V alloys. Physica B: Condensed Matter 591: 412241.
Zhou, Y.-L., M. Niinomi, T. Akahori, M. Nakai, and H. Fukui, 2007 Comparison of Various Properties between Titanium-Tantalum Alloy and Pure Titanium for Biomedical Applications. Materials Transactions 48: 380–384.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.