Page 109 - MSAM-4-3

Materials Science in

Additive Manufacturing

ORIGINAL RESEARCH ARTICLE
Sustainable manufacturing of

FDM-manufactured composite impellers using
hybrid machine learning and simulation-based

optimization

Subramani Raja 1 , Ahamed Jalaludeen Mohammad Iliyas 1 ,
Paneer Selvam Vishnu 1 , Amaladas John Rajan 2 , Maher Ali Rusho 3 ,
Mohamad Reda Refaai * , and Oluseye Adewale Adebimpe 5
4
1 Center for Advanced Multidisciplinary Research and Innovation, Chennai Institute of Technology,
Chennai, Tamil Nadu, India
2 Department of Mechanical Engineering, School of Mechanical Engineering, Vellore Institute of
Technology, Chennai, Tamil Nadu, India
3 Research and Development Unit, Mr.R BUSINESS CORPORATION, Karur, Tamil Nadu, India
4 Department of Mechanical Engineering, College of Engineering, Prince Sattam bin Abdulaziz
University, Al-Kharj 11942, Saudi Arabia
5 Department of Industrial and Production Engineering, Faculty of Technology, University of Ibadan,
Ibadan, Oyo, Nigeria

Abstract
*Corresponding author:
Mohamad Reda Refaai Conventional optimization of fused deposition modeling (FDM) often relies on trial-and-
(m.rifaee@psau.edu.sa) error or heuristic approaches, which lack scalability and precision, especially for complex
Citation: Raja S, Mohammad geometries such as impellers. While prior studies have integrated artificial intelligence
Iliyas AJ, Vishnu PS, et al. (AI) or multi-criteria decision-making (MCDM) techniques for process optimization,
Sustainable manufacturing of their combined application remains limited, particularly in scenarios that prioritize
FDM-manufactured composite
impellers using hybrid machine energy-efficient and sustainable manufacturing. This study introduces a novel hybrid
learning and simulation-based AI-MCDM framework for the multi-objective optimization of FDM-printed composite
optimization. Mater Sci Add Manuf. impellers, integrating mechanical performance, energy consumption, and material
2025;4(3):025200033.
doi: 10.36922/MSAM025200033 utilization within a unified decision-making model. A key feature of the approach is the
real-time tracking of energy usage, enabling dynamic evaluation of process efficiency.
Received: May 14, 2025
Experimental validation demonstrates a 7% enhancement in tensile strength, a 25%
Revised: June 24, 2025 reduction in energy consumption, and a 30% decrease in material wastage compared to
Accepted: July 4, 2025 baseline configurations. These results underscore the potential of AI-driven simulation
and optimization frameworks to support sustainable additive manufacturing, with
Published online: July 28, 2025
significant implications for aerospace, biomedical, and energy sector applications.
Copyright: © 2025 Author(s).
This is an Open-Access article
distributed under the terms of the Keywords: Fused deposition modeling; Rapid prototyping; Machine learning; Multi-
Creative Commons Attribution criteria decision-making; Sustainable manufacturing; Optimization algorithms;
License, permitting distribution,
and reproduction in any medium, Mechanical characterization; SDG Goals
provided the original work is
properly cited.
Publisher’s Note: AccScience
Publishing remains neutral with 1. Introduction
regard to jurisdictional claims in
published maps and institutional Fused deposition modeling (FDM) is the most commonly used additive manufacturing
affiliations. (AM) technology, due to its ease of operation, affordability, capability to produce

Volume 4 Issue 3 (2025) 1 doi: 10.36922/MSAM025200033