Machine learning-driven sustainable optimization of rapid prototyping via FDM: Enhancing mechanical strength, energy efficiency, and SDG contributions of thermoplastic composites

Fused Deposition Modeling (FDM)-based rapid prototyping is a key technology in sustainable manufacturing, offering cost-effective solutions aligned with the United Nations Sustainable Development Goals (SDGs 1–6) by promoting affordable production, resource efficiency, and environmental sustainability. However, optimizing mechanical performance and energy efficiency in bio-based thermoplastic composites remains a challenge. This study explores PLA–walnut wood fiber composites, leveraging machine learning (ML) to optimize tensile, compression, and flexural properties while minimizing energy consumption. A dataset incorporating nozzle temperature, layer height, infill density, and print speed was trained using ML, achieving prediction accuracy above 95%. State-of-the-art studies highlight bio-based composite advantages, yet ML-driven multi-objective optimization for mechanical strength and sustainability remains unexplored. Experimental results indicate that an optimal nozzle temperature of 200–210°C, an infill density of 60–80%, and a layer height of 0.2 mm led to a 15% increase in tensile strength (38 MPa), a 12% improvement in flexural strength (62 MPa), and a 10% enhancement in compression strength (49 MPa). SEM analysis confirms improved fiber-matrix adhesion, enhancing structural integrity. Additionally, energy consumption was reduced by 18%, supporting cost-effective and low-carbon production. These findings contribute to poverty reduction (SDG 1), agricultural waste valorization (SDG 2), biocompatible materials for healthcare (SDG 3), STEM education accessibility (SDG 4), gender inclusivity in engineering (SDG 5), and clean water protection through reduced plastic waste (SDG 6). This study underscores the potential of ML-driven sustainable rapid prototyping to advance material efficiency, waste reduction, and resource-conscious manufacturing.