Integrating Machine Learning (ML) with optimization algorithms in 3D printing, also known as Additive Manufacturing (AM), has revolutionized the creation and production of complex structures. This integration has significantly boosted material efficiency, print quality, and optimization of the entire process. This paper delves into details on improving 3D printing design and production workflows using advanced ML techniques such as neural networks, Reinforcement Learning (RL), and optimization techniques, such as topology optimization and genetic algorithms. The proposed framework offers a 15-25% reduction in print time and material consumption and a 10-20% improvement in predictive accuracy over existing methods. Additionally, the results of the multiobjective optimization reveal an aligned improvement in cost-effectiveness, structural strength, and mechanical performance. Stress-strain analysis showed that optimized designs can achieve up to a 12% increase in yield strength, while defect rates decrease by up to 30% by applying dynamic RL for parameter adjustments. The results validate the effectiveness of these hybrid models, emphasizing their potential to boost reliability, efficiency, and scalability in additive manufacturing processes.

The aerospace industry faces challenges in managing inventory effectively due to long product life cycles and unpredictable demand. Additive Manufacturing (AM) is a promising technology that enables the on-demand production of spare parts, potentially reducing inventory costs and improving supply chain efficiency. This paper proposes a novel conceptual framework for employing AM in the aerospace spare parts industry to isolate demand volatility. A conceptual approach is employed in this study, which involves a comprehensive literature review to identify the factors to consider when employing AM for spare parts and the methods for demand volatility isolation, followed by a structured framework development that outlines the decision-making steps for AM utilization based on the identified factors. The framework outlines a structured approach for using AM to produce spare parts and isolate demand volatility, which can help mitigate the impact of demand uncertainty on inventory management. The proposed approach provides a basis for future research and has the potential to transform how spare parts are produced and managed in the aerospace industry. Overall, this paper contributes to the emerging literature on AM in the aerospace industry by presenting a novel approach to improving inventory management and addressing demand uncertainty.

This study reports the fabrication and characterization of copper–silicon carbide (Cu–SiC) metal matrix composites produced using powder metallurgy (PM) combined with thermo-compression processing (TCP), a dual route that remains limited in Cu–SiC research. Micro-sized SiC particles (1–25 wt.%) were incorporated into Cu, compacted, sintered, and subsequently subjected to sequential forging and annealing. Unlike conventional PM-only processing, TCP significantly reduced porosity, promoted more uniform reinforcement dispersion, and relieved residual stresses, creating a strong synergy between densification and microstructural refinement. SEM, EDS, XRD, and Raman analyses confirmed phase stability, homogeneous reinforcement distribution, and the absence of deleterious interfacial phases. The integrated PM + TCP route achieved an ultimate tensile strength of ~209 MPa, hardness of ~65 HRB, and toughness of ~35 MJ/m³ at approximately 3 wt.% SiC. The superior performance at this composition resulted not from the lowest porosity but from the combined effects of uniform particle dispersion, improved particle–matrix bonding, and deformation-driven refinement. These findings establish TCP as an effective post-sintering strategy that overcomes intrinsic porosity and interfacial limitations in Cu–SiC composites. Overall, powder metallurgy combined with the thermo-compression processing is identified as a promising processing pathway for developing high-strength, thermally stable Cu–SiC materials for structural and thermal management applications.

Advanced 3D Printing (A3P) revolutionizes manufacturing with precision, speed, and innovation, unlocking limitless design possibilities and superior material performance for next-generation industrial and creative applications. A3P epitomizes a paradigm shift in manufacturing, seamlessly merging additive fabrication with advanced 3D printing to construct intricate geometries unattainable through conventional methods. However, inherent challenges persist, including structural deformations in Stereolithography (SLA) and nozzle occlusions in Fused Deposition Modeling (FDM), necessitating intelligent intervention. This study introduces LoRe-GRNN, a groundbreaking Deep Learning (DL) framework for real-time anomaly detection and stress distribution prediction. Leveraging a novel fusion of Longformer-Reformer (LoRe) architectures with Gated Recurrent Neural Networks (GRNN), the system optimizes feature extraction and predictive accuracy. A meticulously curated 3D model repository, synergized with Finite Element (FE) simulations, enhances SLA stress predictions, while an integrated multisensory module ensures FDM process monitoring. The hybrid approach demonstrates unparalleled precision, achieving 99.23% anomaly detection accuracy, significantly mitigating computational overhead compared to traditional FE simulations. This transformative framework enhances the resilience of additive manufacturing, heralding an era of intelligent, high-fidelity, and resource-efficient 3D printing systems.

This study reports the fabrication of copper-based metal matrix composites reinforced with a combination of micro- and nano-sized titanium carbide (TiC) particles using the powder metallurgy route. The micro-TiC content was maintained at 5 wt.%, while the nano-TiC addition was systematically varied between 1 and 3 wt.% in increments of 1 wt.%. The consolidation of the blends was achieved by uniaxial compaction at 500 MPa, followed by sintering in a nitrogen atmosphere at 750–900 °C for 2 h. Tribological assessment under dry sliding conditions was performed using a pin-on-disk apparatus. Structural and microstructural examinations using X-ray diffraction (XRD), scanning electron microscopy (SEM), and energy-dispersive spectroscopy (EDS) confirmed a uniform incorporation of the reinforcements within the Cu matrix. The incorporation of nano-TiC up to 2 wt.% significantly enhanced density, hardness, and wear resistance, after which a marginal decline was observed. SEM analysis of worn surfaces revealed that adhesive wear, abrasion, and delamination were the primary wear mechanisms. To better understand the relationship between processing conditions and material responses, response surface methodology (RSM) was employed. The developed models for density, hardness, and wear loss showed good agreement with the experimental results, with confirmatory tests yielding errors of 1.59%, 2.06%, and 2%, respectively, thereby validating the approach’s reliability.

This work presents a compact multilayer solar absorber based on a spiral multi‐ring resonator integrated with MXene for broadband energy harvesting. The proposed metal–dielectric–MXene–metal configuration consists of a patterned Fe resonator placed over a SiO ₂ spacer and MXene layer, backed by a metallic ground plane to suppress transmission. The structure achieves near‐perfect absorption, reaching 99.9% peak and maintaining absorption above 0.85 across 0.3 to 3.3 µm. Parametric analysis reveals that MXene enhances absorption through strong electromagnetic coupling and intrinsic losses, while SiO ₂ thickness governs spectral tuning. The design maintains stable absorption up to 60° incidence for both TE and TM modes, with superior TM performance. Broadband behavior arises from impedance matching, plasmonic resonances, and dielectric interference. Strong field confinement in the spiral resonator enhances absorption around 1.8–2.0 µm. Machine learning models predict absorption effectively, with AdaBoost achieving the highest accuracy (R ² ≈ 0.943), demonstrating scalability and application potential.