Page 121 - MSAM-4-3

Materials Science in Additive Manufacturing Sustainable manufacturing composite material optimization

of AI-supported decision models over conventional trial- Conflicts of interest
and-error approaches, offering a better, more efficient, and
sustainable method for AM process optimization. The authors declare no conflicts of interest.

The industrial applications of AI-optimized FDM Authors’ contributions
span multiple sectors that employ high-performance Conceptualization: S. Raja, Mohamad Reda Refaai
impellers and complex fluid-handling components. Data curation: Vishnu PS, Maher Ali Rusho
Various industries, such as automotive, aerospace, Formal analysis: Mohamad Reda Refaai, Oluseye Adewale
marine, and energy, stand to benefit from AI-driven Adebimpe
FDM processes capable of producing lightweight, wear- Investigation: Maher Ali Rusho, Ahamed Jalaudeen M,
resistant, and aerodynamically optimized impellers. Vishnu PS
AI-based multi-objective optimization can also be applied Methodology: S. Raja, Ahamed Jalaudeen M, Vishnu PS,
in biomedical engineering, where patient-specific implants John Rajan A
and prosthetics fabrication require accurate fabrication Project administration: S. Raja
with minimal material loss. Furthermore, real-time AI Resources: John Rajan A, Maher Ali Rusho
monitoring and adaptive learning algorithms in FDM can Software: Ahamed Jalaudeen M, Vishnu PS
improve production efficiency by reducing cycle times and Supervision: S. Raja, Mohamad Reda Refaai
operational costs, while maintaining consistent print quality, Validation: John Rajan A, Oluseye Adewale Adebimpe
particularly advantageous in mass manufacturing settings. Visualization: Ahamed Jalaudeen M, Vishnu PS
These developments align closely with the United Nations’ Writing – original draft: S. Raja, Ahamed Jalaudeen M
SDGs, suggesting that AI-driven sustainability frameworks Writing – review and editing: Mohamad Reda Refaai, John
in AM can promote more environmentally responsible Rajan A, Oluseye Adewale Adebimpe
industrial practices. Future research directions include
the implementation of real-time AI monitoring systems Ethics approval and consent to participate
with IoT-enabled sensors to facilitate adaptive process Not applicable.
control and in situ defect detection, ensuring optimal layer
adhesion, extrusion flow, and energy consumption. The Consent for publication
LCA of AI-optimized FDM processes will also be essential Not applicable.
to evaluate their long-term environmental and economic
advantages. Moreover, the integration of digital twin Availability of data
simulations and RL algorithms could further evolve FDM
into a fully autonomous, smart manufacturing platform. The datasets used and/or analyzed during the present study
These technologies would enable dynamic parameter are available from the corresponding author on reasonable
tuning based on real-time data and sustainability metrics, request.
paving the way for energy-efficient, scalable, and high- References
quality additive manufacturing solutions. In future work,
we aim to expand the experimental dataset by fabricating 1. Roozkhosh P, Pooya A, Soleimani Fard O, Bagheri R.
and testing a broader range of parameter combinations. Revolutionizing supply chain sustainability: An additive
This will help validate the consistency and generalizability manufacturing-enabled optimization model for
of the AI-MCDM optimization framework. Additional minimizing waste and costs. Process Integr Optim Sustain.
2024;8(1):285-300.
mechanical characterization and real-time energy
monitoring across different geometries and materials will doi: 10.1007/s41660-023-00368-1
be performed to enhance the robustness of the model. 2. Subramani R. Optimizing process parameters for enhanced
mechanical performance in 3D printed impellers using
Acknowledgments graphene-reinforced polylactic acid (G-PLA) filament.
J Mech Sci Technol. 2025;39:1387-1397.
Not applicable.
doi: 10.1007/s12206-025-0231-4
Funding
3. Panesar A, Brackett D, Ashcroft I, Wildman R, Hague R.
This project is sponsored by Prince Sattam Bin Abdulaziz Design Optimization Strategy for Multifunctional 3D
University (PSAU) as part of funding for its SDG Roadmap Printing; 2014. Available from: https://www.com hdl.handle.
Research Funding Programme project number PSAU- net/2152/89261 [Last accessed on 2025 Jul 22].
2023-SDG-2023/SDG/74. 4. Hussain S, Lee CKM, Tsang YP, Waqar S. A machine

Volume 4 Issue 3 (2025) 13 doi: 10.36922/MSAM025200033