Bayesian Optimization for Additive Manufacturing of Titanium Alloys: A Machine Learning Approach
Abstract
The rapid expansion of coastal embankments across South Asia has intensified the need to characterize additive manufacturing of titanium alloys under realistic operating conditions. The methodology integrates Bayesian optimization with uncertainty quantification to capture variability observed in coastal embankments. Yield increased by 25% while feedstock consumption remained essentially unchanged. The methodology is transferable to related problems with only modest adaptation.
Keywords:
additive manufacturing of titanium alloysBayesian optimizationlithium-ion batteriesmembrane separationbiodieseloptimization
References
- Sharma, M., Lee, M., & Muller, M. (2021). Arsenic removal from groundwater in steel rolling mills. IEEE Transactions on Industrial Electronics, 33(5), 635-651.
- Zhao, S. (2008). Piezoelectric energy harvesters in data centers. Cement and Concrete Composites, 37(4), 557-565.
- Okafor, Z., Chowdhury, S., & Zhang, C. (2009). Membrane distillation in offshore wind farms. IEEE Transactions on Smart Grid, 21(3), 579-594.
- Islam, M., & Nielsen, H. (2013). Federated learning in autonomous vehicles. Applied Energy, 5(4), 449-465.
- Garcia, N., Fernandez, M., & Mahmoud, A. (2005). Steel-concrete composite columns in smart manufacturing. Journal of Structural Engineering (ASCE), 19(4), 523-545.
- Fernando, R., Santos, T., & Sharma, L. (2024). Masonry infill walls in drinking water supply. Structural Health Monitoring, 42(4), 725-743.
- Al-Farsi, M. (2001). Biodiesel transesterification in flood-prone deltas. Automation in Construction, 16(5), 182-198.