Abderrachid Hamrani

Avec l'avancé des méthodes numériques, de nouvelles méthodes dites « sans maillage » sont apparues pour remédier à certaines limitations de la méthode des éléments finis. Ces méthodes ont la particularité de n’employer aucun maillage prédéfini : elles utilisent un ensemble de nœuds dispersés dans le domaine considéré et sur ses frontières. L’objectif de cette étude est de montrer l’intérêt de l’application des méthodes sans maillage basées sur les fonctions de base radiale pour la simulation des procédés de mise en forme en général et de poinçonnage rapide en particulier. Une attention particulière sera portée sur la méthode RPIM qui offre l’avantage de proposer une interpolation nodale. La démarche proposée dans ce document consiste: à rappeler succinctement les principes essentiels des méthodes sans maillage en précisant leurs avantages par rapport aux méthodes classiques, à présenter et à mettre en œuvre la technique numérique de la méthode sans maillage RPIM avec un calibrage des paramètres caractéristiques, et enfin, à traiter des exemples numériques de procédés de mise en forme avec amorçage et propagation de fissure qui confirmeront ces avantages.

Wire-directed energy deposition (W-DED) produces steep thermal gradients and rapid heating-cooling cycles due to the moving heat source, where modest variations in process parameters significantly alter heat input per unit length and therefore the full thermal history. This sensitivity makes process tuning by trial-and-error or repeated FE sweeps expensive, motivating inverse analysis. This work proposes an inverse thermal process design framework that couples single-track experiments, a calibrated finite element (FE) thermal model, and a parametric physics-informed neural network (PINN) surrogate. By using experimentally calibrated heat-loss physics to define the training constraints, the PINN learns a parameterized thermal response from physics alone (no temperature data in the PINN loss), enabling inverse design without repeated FE runs. Thermocouple measurements are used to calibrate the convection film coefficient and emissivity in the FE model, and those parameters are used to train a parametric PINN over continuous ranges of arc power (1.5–3.0 kW) and travel speed (0.005–0.015 m/s) without using temperature data in the loss function. The trained PINN model was validated against the calibrated FE model at 3 probe locations with different power and travel speed combinations. Across these benchmark conditions, the mean absolute errors are between 6.5–17.4 °C, with cooling-tail errors ranging from 1.8–12.1 °C. The trained surrogate is then embedded in a sampling-based inverse optimization loop to identify power-speed combinations that achieve prescribed interlayer temperatures at a fixed dwell time. For target interlayer temperatures of 100, 130, and 160 °C with a 10 s dwell time, the optimized solutions remain within 3.3–5.6 °C of the target according to the PINN, while FE verification is within 4.0–6.6 °C. The results demonstrate that a physics-only parametric PINN surrogate enables inverse thermal process design without repeated FE runs while establishing a single-track baseline for extension to multi-track and multi-layer builds.

Catalytic pyrolysis (CP) of biomass is a promising method for producing sustainable hydrogen because lignocellulosic biomass is widely available, renewable, and approximately carbon-neutral. CP of biomass is influenced by complex, interdependent process parameters, making optimization challenging and time-consuming using traditional methods. This study investigated a two-stage machine learning (ML) framework fortified with Bayesian optimization to enhance hydrogen production from CP. The ML models were used to classify and predict hydrogen yield using a dataset of 306 points with 14 input features. The classification stage identified conditions favorable for good hydrogen yield, while the regression model (second stage) quantitatively predicted hydrogen yield. The random forest classifier and regressor demonstrated superior capabilities, achieving R² scores of 1.0 and 0.8, respectively. The model demonstrated strong agreement with experimental data and effectively captured the key factors driving hydrogen production. Shapley Additive exPlanation (SHAP) identified temperature and catalyst properties (nickel loading) as the most influential parameters. The inverse analysis framework validated the model’s ability to determine optimal conditions for predicting targeted hydrogen yields by comparing it to experimental data reported in the literature. This AI-driven approach provides a scalable and data-efficient tool for optimizing processes in sustainable hydrogen production.

The swift integration of AI, robotics, and advanced sensing technologies has revolutionized agriculture into a data-centric, autonomous, and sustainable sector. This systematic study examines the interplay between artificial intelligence and agricultural robotics in intelligent farming systems. Artificial intelligence, machine learning, computer vision, swarm robotics, and generative AI are analyzed for crop monitoring, precision irrigation, autonomous harvesting, and post-harvest processing. Employing PRISMA to categorize more than 10,000 high-impact publications from Scopus, WoS, and IEEE. Drones and vision-based models predominate the industry, while IoT integration, digital twins, and generative AI are on the rise. Insufficient field validation rates, inadequate crop and regional representation, and the implementation of explainable AI continue to pose significant challenges. Inadequate model generalization, energy limitations, and infrastructural restrictions impede scalability. We identify solutions in federated learning, swarm robotics, and climate-smart agricultural artificial intelligence. This paper presents a framework for inclusive, resilient, and feasible AI-robotic agricultural systems.

Producing high-quality segmentation masks for medical images is a fundamental challenge in biomedical image analysis. Recent research has investigated the use of supervised learning with large volumes of labeled data to improve segmentation across medical imaging modalities and unsupervised learning with unlabeled data to segment without detailed annotations. However, a significant hurdle remains in constructing a model that can segment diverse medical images in a zero-shot manner without any annotations. In this work, we introduce the attention diffusion zero-shot unsupervised system (ADZUS), a new method that uses self-attention diffusion models to segment biomedical images without needing any prior labels. This method combines self-attention mechanisms to enable context-aware and detail-sensitive segmentations, with the strengths of the pre-trained diffusion model. The experimental results show that ADZUS outperformed state-of-the-art models on various medical imaging datasets, such as skin lesions, chest X-ray infections, and white blood cell segmentations. The model demonstrated significant improvements by achieving Dice scores ranging from 88.7% to 92.9% and IoU scores from 66.3% to 93.3%. The success of the ADZUS model in zero-shot settings could lower the costs of labeling data and help it adapt to new medical imaging tasks, improving the diagnostic capabilities of AI-based medical imaging technologies.

The swift integration of AI, robotics, and advanced sensing technologies has revolutionized agriculture into a data-centric, autonomous, and sustainable sector. This systematic study examines the interplay between artificial intelligence and agricultural robotics in intelligent farming systems. Artificial intelligence, machine learning, computer vision, swarm robotics, and generative AI are analyzed for crop monitoring, precision irrigation, autonomous harvesting, and post-harvest processing. Employing PRISMA to categorize more than 10,000 high-impact publications from Scopus, WoS, and IEEE. Drones and vision-based models predominate the industry, while IoT integration, digital twins, and generative AI are on the rise. Insufficient field validation rates, inadequate crop and regional representation, and the implementation of explainable AI continue to pose significant challenges. Inadequate model generalization, energy limitations, and infrastructural restrictions impede scalability. We identify solutions in federated learning, swarm robotics, and climate-smart agricultural artificial intelligence. This paper presents a framework for inclusive, resilient, and feasible AI-robotic agricultural systems.

Precise thermal management remains a critical challenge in Wire Arc-Direct Energy Deposition (W-DED) processes due to significant temperature fluctuations that can adversely impact part quality, dimensional accuracy, and process reliability. To address these issues, this study introduces a novel Hybrid Interlayer Hysteresis Controller (HIHC) designed specifically for W-DED, which integrates real-time thermal feedback and adaptive dwell time control. The system implements a dual-mode cooling strategy based on a temperature threshold, utilizing optical character recognition-based temperature monitoring and a rolling buffer system for stability. Experimental validation demonstrated improvements in thermal management, with the dynamic control system maintaining an average temperature undershoot of 1.38% while achieving 96.29% optimal temperature window compliance. Surface quality analysis revealed an 8.67% improvement in front face smoothness and a 5.15% enhancement in top surface quality. The dynamic control system also exhibited superior dimensional accuracy, producing thin walls with widths of 61.98 mm versus 66.43 mm in fixed dwell time samples, relative to the intended 60 mm specification. This study advances the field of additive manufacturing by establishing a robust framework for precise thermal management in W-DED processes, contributing to enhanced part quality, reduced post-processing requirements, and improved process reliability. Despite these advances, limitations include the system’s dependence on external optical monitoring hardware, potential scalability constraints for complex geometries, and limited testing across diverse material systems. Future work should focus on integrating multi-axis thermal sensors, extending the framework to multi-material deposition scenarios and implementing machine learning algorithms for predictive thermal modeling.

Diabetic foot ulcers (DFUs) pose a significant challenge in healthcare, requiring precise and efficient wound assessment to enhance patient outcomes. This study introduces the Attention Diffusion Zero-shot Unsupervised System (ADZUS), a novel text-guided diffusion model that performs wound segmentation without relying on labeled training data. Unlike conventional deep learning models, which require extensive annotation, ADZUS leverages zero-shot learning to dynamically adapt segmentation based on descriptive prompts, offering enhanced flexibility and adaptability in clinical applications. Experimental evaluations demonstrate that ADZUS surpasses traditional and state-of-the-art segmentation models, achieving an IoU of 86.68\% and the highest precision of 94.69\% on the chronic wound dataset, outperforming supervised approaches such as FUSegNet. Further validation on a custom-curated DFU dataset reinforces its robustness, with ADZUS achieving a median DSC of 75\%, significantly surpassing FUSegNet's 45\%. The model's text-guided segmentation capability enables real-time customization of segmentation outputs, allowing targeted analysis of wound characteristics based on clinical descriptions. Despite its competitive performance, the computational cost of diffusion-based inference and the need for potential fine-tuning remain areas for future improvement. ADZUS represents a transformative step in wound segmentation, providing a scalable, efficient, and adaptable AI-driven solution for medical imaging.

Producing high-quality segmentation masks for medical images is a fundamental challenge in biomedical image analysis. Recent research has explored large-scale supervised training to enable segmentation across various medical imaging modalities and unsupervised training to facilitate segmentation without dense annotations. However, constructing a model capable of segmenting diverse medical images in a zero-shot manner without any annotations remains a significant hurdle. This paper introduces the Attention Diffusion Zero-shot Unsupervised System (ADZUS), a novel approach that leverages self-attention diffusion models for zero-shot biomedical image segmentation. ADZUS harnesses the intrinsic capabilities of pre-trained diffusion models, utilizing their generative and discriminative potentials to segment medical images without requiring annotated training data or prior domain-specific knowledge. The ADZUS architecture is detailed, with its integration of self-attention mechanisms that facilitate context-aware and detail-sensitive segmentations being highlighted. Experimental results across various medical imaging datasets, including skin lesion segmentation, chest X-ray infection segmentation, and white blood cell segmentation, reveal that ADZUS achieves state-of-the-art performance. Notably, ADZUS reached Dice scores ranging from 88.7\% to 92.9\% and IoU scores from 66.3\% to 93.3\% across different segmentation tasks, demonstrating significant improvements in handling novel, unseen medical imagery. It is noteworthy that while ADZUS demonstrates high effectiveness, it demands substantial computational resources and extended processing times. The model's efficacy in zero-shot settings underscores its potential to reduce reliance on costly annotations and seamlessly adapt to new medical imaging tasks, thereby expanding the diagnostic capabilities of AI-driven medical imaging technologies.