Fused deposition modeling (FDM) is a widely used additive manufacturing (AM) method that offers great flexibility in fabricating complex geometries without requiring expensive equipment. However, compared to other manufacturing methods, FDM-produced parts generally exhibit lower strength and fatigue life. To overcome this limitation, researchers have explored the use of fibers and reinforcements to enhance the mechanical properties of FDM parts. Nevertheless, the performance of FDM-produced parts can be significantly affected by various manufacturing parameters, including infill density, which is a key factor in balancing time and cost. In this study, the tensile strength and fatigue life of carbon fiber-reinforced polylactic acid (PLA) composites produced by FDM were investigated by varying the infill density (50 and 75%) and raster angle (0°, 45°, and 90°). The effects of 100% filling density, raster width, and nozzle diameter on mechanical properties were also examined. The experimental results demonstrated that increasing the infill density and decreasing the raster angle can enhance the tensile strength, although the fatigue behavior was found to be more complex and dependent on the infill density. The optimal parameters for producing FDM parts with improved mechanical properties were identified based on the analysis of the tensile strength and fatigue life data. This research has yielded significant findings concerning the diverse fatigue behavior associated with the raster angle at different infill densities. Specifically, noteworthy observations reveal that a raster angle of 45 degrees at 50% infill density, and a raster angle of 0 degrees at 75% infill density, exhibited the most prolonged fatigue life. This outcome can be ascribed to the specific loading conditions and the inherent strength of the sediment layer at the critical point of stress concentration.

The integration of additive manufacturing (AM) and green composites has wide potential for designing sustainable and eco-friendly structures. Green composites, made of natural fibers and bio-matrix matrices, balance mechanical performance against environmental responsibility. However, their structural reliability is based on fracture toughness, a field poorly developed for AM-manufactured materials. Fused Deposition Modeling (FDM), an extrusion-based AM process, enables the manufacture of low-cost fiber-reinforced thermoplastics with intricate geometries. This study investigates the essential work of fracture in a green wood-reinforced PLA composite fabricated by FDM. In this study, double-edge notch tension (DENT) specimens were evaluated under tension, and in addition to determining the specific work of fracture, the unnecessary work and the material ductility level were also evaluated. The DENTs were printed with three build orientations, 100% infill density, and a steel nozzle to evaluate process-induced anisotropy and inherent fracture resistance. Specific fracture work ranged from 11.62 to 76.06 kJ/m², with a maximum value in on-edge orientations. Ductility level ranged from 0.11 to 0.32, indicating medium deformability before failure. Morphology of the fracture surface was examined by Field Emission Scanning Electron Microscopy (FE-SEM) to understand failure mechanisms, where microstructural features controlling crack growth were seen. This integrated experimental research, using commercial filaments, highlights the importance of build direction to anisotropic fracture behavior and warrants the use of sustainable composites in engineering systems demanding mechanical performance and environmental sustainability.

The convergence of additive manufacturing (AM) and artificial intelligence (AI) is poised to redefine the landscape of modern production; however, the literature remains fragmented across isolated applications, lacking a unified perspective on the engineering impact and practical deployment of these technologies. This review provides a comprehensive and critical synthesis of the state of the art in AI-enhanced AM, systematically covering supervised, unsupervised, and reinforcement learning paradigms, alongside deep-learning-based computer vision, natural language processing, and robotics. In contrast to prior works that focus on singular aspects, this paper consolidates progress across four core engineering domains: (i) lightweight and manufacturable design, (ii) real-time in situ defect detection and process analysis, (iii) energy-efficient process optimization, and (iv) cost-effective build-time estimation with intelligent support minimization. Beyond cataloging these advances, this review identifies key quantitative benchmarks and recurring technical challenges, including data scarcity, poor model generalizability, and the critical gap between offline prediction and real-time closed-loop control. To transcend these isolated successes and enable industrial adoption, we propose a novel, unified closed-loop AI-AM framework that tightly integrates generative design, process planning, in situ production monitoring, and continuous model updating into a cohesive digital thread. Furthermore, a domain-stratified SWOT analysis is compiled, offering a strategic evaluation of strengths, weaknesses, opportunities, and threats across the four application pillars. By bridging the gap between laboratory prototypes and production-ready autonomous systems, this review serves as a definitive reference for researchers and practitioners aiming to navigate, deploy, and advance the rapidly evolving field of AI in additive manufacturing.