Laser Powder Bed Fusion (LPBF) has emerged as a leading additive manufacturing (AM) process for producing complex metal components. Despite its advantages, the inherent LPBF process complexity leads to challenges in achieving consistent quality and repeatability. To address these concerns, recent research efforts have focused on sensor fusion techniques for process monitoring, and on developing more elaborate control strategies. Sensor fusion combines information from multiple in situ sensors to provide more comprehensive insights into process characteristics such as melt pool behavior, spatter formation, and layer integrity. By leveraging multimodal data sources, sensor fusion enhances the detection and diagnosis of process anomalies in real-time. Closed-loop control systems may utilize this fused information to adjust key process parameters–such as laser power, focal depth, and scanning speed–to mitigate defect formation during the build process. This review focuses on the current state-of-the-art in sensor fusion monitoring and control strategies for LPBF. In terms of sensor fusion, recent advances extend beyond CNN-based approaches to include graph-based, attention, and transformer architectures. Among these, feature-level integration has shown the best balance between accuracy and computational cost. However, the limited volume of available experimental data, class-imbalance issues and lack of standardization still hinder further progress. In terms of control, a trend away from purely physics-based towards Machine Learning (ML)-assisted and hybrid strategies can be observed. These strategies show promise for more adaptive and effective quality enhancement. The biggest challenge is the broader validation on more complex part geometries and under realistic conditions using commercial LPBF systems.

Additive manufacturing (AM) technologies enable the production of customized and personalized medical devices that facilitate users’ comfort and rehabilitation requirements according to their individual conditions. The concept of a tailor-made orthopedic device addresses the accelerated recovery and comfort of the patient through the utilization of personalized rehabilitation equipment. Direct modeling, with an increasing number of approaches and prototypes, has provided many successful results until now. The modeling procedure for 3D-printed orthoses has emerged as the execution of steady and continuous tasks with several design selection criteria, such as cutting, thickening the surface, and engraving the shell of the orthosis. This publication takes into consideration the aforementioned criteria and proposes the creation of a holistic methodology and automated computational design process for the customization of orthotic assistive devices, considering aspects such as material properties, manufacturing limitations, recycling, and patients’ requirements. This proposal leads to the designing and manufacturing of a wrist orthopedic device based on reverse engineering, Design for AM (DfAM), and Design for Recycling (DfR) principles. The proposed methodology can be adjusted for different limbs. A dual-material approach was attained utilizing rigid, mechanically enhanced feedstock material and soft elastic material with reduced skin irritation risks to achieve both mechanical requirements and adequate cushioning for user comfort during rehabilitation. Recyclable thermoplastic matrices were selected, which also allow for the option to create washable devices for product life extension. Then, 3D scanning procedures were implemented to acquire the initial anatomic measurements for the design of the WHO and ensure and assess the dimensional accuracy of the final product. Physical mechanical testing was implemented to evaluate the WHO’s mechanical behavior and verify its functionality during basic wrist movements. The extracted dimensional data for the two main orthosis components that indicated approximately 50% and 25% of the tolerance values, respectively, were within the range (−0.1 mm, 0.1 mm).

Process reliability and quality output are critical indicators for the upscaling potential of a fabrication process on an industrial level. Fused filament fabrication (FFF) is a versatile additive manufacturing (AM) technology that provides viable and cost-effective solutions for prototyping applications and low-volume manufacturing of high-performance functional parts, yet is defect-prone due to the inherent aspect of parametrization. A systematic yet parametric workflow for quality inspection is therefore required. The work presented describes a versatile and reliable framework for automatic defect detection during the FFF process, enabled by artificial intelligence-based computer vision. Specifically, state-of-the-art deep learning models are developed for in-line inspection of individual thermoplastic strands’ surface morphology and weld quality, thus defining acceptable limits for FFF process parameter values. We examine the capabilities of an NVIDIA Jetson Nano, a low-power, high-performance computer with an integrated graphical processing unit (GPU). The developed deep learning models used in this analysis use a pre-trained model combined with manual configurations in order to efficiently identify the thermoplastic strands’ surface morphology. The proposed methodology aims to facilitate process parameter selection and the early identification of critical defects, toward an overall improvement in process reliability with reduced operator intervention.

Fused filament fabrication (FFF) is a popular additive manufacturing (AM) method for creating thermoplastic parts with intricate geometrical designs. Pure thermoplastic materials utilized in FFF, whose polymeric matrix is reinforced with other materials, such as carbon fibers (CFs), introduce products with advanced mechanical properties. However, since not all of these materials are biodegradable, the need for recycling and reuse immediately emerges to address the significant problem of how to dispose of their waste. The proposed study evaluates the printability, surface morphology and in vitro toxicity of two thermoplastic-based composite materials commonly used in wearable device manufacturing to provide enhanced properties and functionalities, making them suitable for various applications in the field of wearable devices. Tritan Copolyester TX1501 with 7.3% chopped CFs (cCFs) and Polyamide 12 (PA12) with 8.6%cCFs and 7.5% iron Magnetic Nanoparticles (MNPs)—Fe₄O₃ were used in the discrete ascending cycles of recycling, focusing on the surface quality performance optimization of the printed parts. Through stereoscopy evaluation, under-extrusion, and over-extrusion defects, as well as non-uniform material flow, are assessed in order to first investigate the influence of various process parameters’ application on the printing quality of each material and, second, to analyze the optimal value fluctuation of the printing parameters throughout the recycling cycles of the materials. The results indicate that after applying certain adjustments to the main printing parameter values, the examined recycled reinforced materials are still effectively 3D printed even after multiple cycles of recycling. A morphology examination using scanning electron microscope (SEM) revealed surface alterations, while a cytotoxicity assessment revealed the adverse effects of both materials in the form of cell viability and the release of proinflammatory cytokines in the cell culture medium.