Search Results (632)

In this work, Laser Powder Bed Fusion (LPBF), an additive manufacturing (AM) process, was optimised to produce pure magnesium components. The focus of the presented work is on the prediction of the relative product density using the machine learning model XGBoost to improve the production process and thus the usability of the material for practical use. Experimental tests with different parameters, laser power, scanning speed and layer thickness, and fixed parameters, track overlapping and hatching distance, were analysed and resulted in relative material densities between 89.29% and 99.975%. The XGBoost model showed high predictive power, achieving an R² test result of 0.835, a mean absolute error (MAE) of 0.728 and a root mean square error (RMSE) of 0.982. Feature importance analysis showed that the interaction of laser power and scanning speed had the largest influence on the predictions at 35.9%, followed by laser power × layer thickness at 29.0%. The individual contributions were laser power (11.8%), scanning speed (10.7%), scanning speed × layer thickness (9.0%) and layer thickness (3.6%). These results provide a data-based method for LPBF parameter settings that improve manufacturing efficiency and component performance in the aerospace, automotive and biomedical industries and identify optimal parameter regions for a high density, serving as a pre-optimisation stage. Full article

This study systematically investigates the homogenization-induced Laves phase dissolution kinetics and recrystallization mechanisms in laser powder bed fusion (L-PBF) processed IN718 superalloy. The as-built material exhibits a characteristic fine dendritic microstructure with interdendritic Laves phase segregation and high dislocation density, featuring directional sub-grain boundaries aligned with the build direction. Laves phase dissolution demonstrates dual-stage kinetics: initial rapid dissolution (0–15 min) governed by bulk atomic diffusion, followed by interface reaction-controlled deceleration (15–60 min) after 1 h at 1150 °C. Complete dissolution of the Laves phase is achieved after 3.7 h at 1150 °C. Recrystallization initiates preferentially at serrated grain boundaries through boundary bulging mechanisms, driven by localized orientation gradients and stored energy differentials. Grain growth kinetics obey a fourth-power time dependence, confirming Ostwald ripening-controlled boundary migration via grain boundary diffusion. Such a study is expected to be helpful in understanding the microstructural development of L-PBF-built IN718 under heat treatments. Full article

Background: Overcrowded emergency departments (EDs) create significant challenges for patient management and hospital efficiency. In response, Amiens Picardy University Hospital (APUH) developed the “Prediction of the Patient Pathway in the Emergency Department” (3P-U) model to enhance patient flow management. Objectives: To develop and clinically validate an explainable artificial intelligence (XAI) model for hospital admission predictions, using structured triage data, and demonstrate its real-world applicability in the ED setting. Methods: Our retrospective, single-center study involved 351,019 patients consulting in APUH’s EDs between 2015 and 2018. Various models (including a cross-validation artificial neural network (ANN), a k-nearest neighbors (KNN) model, a logistic regression (LR) model, and a random forest (RF) model) were trained and assessed for performance with regard to the area under the receiver operating characteristic curve (AUROC). The best model was validated internally with a test set, and the F1 score was used to determine the best threshold for recall, precision, and accuracy. XAI techniques, such as Shapley additive explanations (SHAP) and partial dependence plots (PDP) were employed, and the clinical explanations were evaluated by emergency physicians. Results: The ANN gave the best performance during the training stage, with an AUROC of 83.1% (SD: 0.2%) for the test set; it surpassed the RF (AUROC: 71.6%, SD: 0.1%), KNN (AUROC: 67.2%, SD: 0.2%), and LR (AUROC: 71.5%, SD: 0.2%) models. In an internal validation, the ANN’s AUROC was 83.2%. The best F1 score (0.67) determined that 0.35 was the optimal threshold; the corresponding recall, precision, and accuracy were 75.7%, 59.7%, and 75.3%, respectively. The SHAP and PDP XAI techniques (as assessed by emergency physicians) highlighted patient age, heart rate, and presentation with multiple injuries as the features that most specifically influenced the admission from the ED to a hospital ward. These insights are being used in bed allocation and patient prioritization, directly improving ED operations. Conclusions: The 3P-U model demonstrates practical utility by reducing ED crowding and enhancing decision-making processes at APUH. Its transparency and physician validation foster trust, facilitating its adoption in clinical practice and offering a replicable framework for other hospitals to optimize patient flow. Full article

Laser beam powder bed fusion of metals (PBF-LB/M, or simply L-PBF) has emerged as one of the most competitive additive manufacturing technologies for producing complex metallic components with high precision, design freedom, and minimal material waste. Among the various categories of additive manufacturing processes, L-PBF stands out, paving the way for the execution of part designs with geometries previously considered unfeasible. Despite offering several advantages, parts with overhang features require the use of support structures to provide dimensional stability of the part. Support structures achieve this by resisting residual stresses generated during processing and assisting heat dissipation. Although the scientific community acknowledges the role of support structures in the success of L-PBF manufacturing, they have remained relatively underexplored in the literature. In this context, the present work investigated the impact of laser power and scanning speed on the dimensioning, integrity and tensile strength of single-walled block type support structures manufactured in AISI 316L stainless steel. The method proposed in this work is divided in two stages: processing parameter exploration, and mechanical characterization. The results indicated that support structures become more robust and resistant as laser power increases, and the opposite effect is observed with an increment in scanning speed. In addition, defects were detected at the interfaces between the bulk and support regions, which were crucial for the failure of the tensile test specimens. For a layer thickness corresponding to 0.060 mm, it was verified that the combination of laser power and scanning speed of 150 W and 500 mm/s resulted in the highest tensile resistance while respecting the dimensional deviation requirement. Full article

Red sandstones of the Cambrian age are globally distributed and represent an important sedimentation phase during this critical time interval. Their sedimentology and geochemistry can provide key information about the sedimentation style, paleoclimatic conditions, and weathering trends during the Cambrian. In the Salt Range of Pakistan, the Khewra Sandstone constitutes the Lower Cambrian strata and consists of red–maroon sandstones with minor siltstone and shale in the basal part. Cross-bedding, graded bedding, ripple marks, parallel laminations, load casts, ball and pillows, desiccation cracks, and bioturbation are the common sedimentary features of the formation. The sandstones are fine to medium to coarse-grained with subangular to subrounded morphology and display an overall coarsening upward trend. Petrographic analysis indicates that the sandstones are sub-arkose and sub-lithic arenites, and dolomite and calcite are common cementing materials. X-ray Diffraction (XRD) analysis indicates that the main minerals in the formation are quartz, feldspars, kaolinite, illite, mica, hematite, dolomite, and calcite. Geochemical analysis indicates that SiO₂ is the major component at a range of 53.3 to 88% (averaging 70.4%), Al₂O₃ ranges from 3.1 to 19.2% (averaging 9.2%), CaO ranges from 0.4 to 25.3% (averaging 7.4%), K₂O ranges from 1.2 to 7.4% (averaging 4.8%), MgO ranges from 0.2 to 7.4% (averaging 3.5%), and Na₂O ranges from 0.1 to 0.9% (averaging 0.4%), respectively. The results of the combined proxies indicate that the sedimentation occurred in fluvial–deltaic settings under overall arid to semi-arid paleoclimatic conditions with poor to moderate chemical weathering. The Khewra Sandstone represents the red Cambrian sandstones on the NW Indian Plate margin of Gondwana and can be correlated with contemporaneous red sandstones in the USA, Europe, Africa, Iran, and Turkey (Türkiye). Full article

Additive manufacturing (AM), particularly laser powder bed fusion (L-PBF), provides unmatched design flexibility for creating intricate steel structures with minimal post-processing. However, adopting L-PBF for high-performance applications is difficult due to the challenge of predicting microstructure evolution. This is because the process is sensitive to many parameters and has a complex thermal history. Thin-walled geometries present an added challenge because their dimensions often approach the scale of individual grains. Thus, microstructure becomes a critical factor in the overall integrity of the component. This study focuses on applying cellular automata (CA) modeling to establish robust and efficient process–structure relationships in L-PBF of 316L stainless steel. The CA framework simulates solidification-driven grain evolution and texture development across various processing conditions. Model predictions are evaluated against experimental electron backscatter diffraction (EBSD) data, with additional quantitative comparisons based on texture and morphology metrics. The results demonstrate that CA simulations calibrated with relevant process parameters can effectively reproduce key microstructural features, including grain size distributions, aspect ratios, and texture components, observed in thin-walled L-PBF structures. This work highlights the strengths and limitations of CA-based modeling and supports its role in reliably designing and optimizing complex L-PBF components. Full article

Identifying correspondences of road segments in different road networks, namely road-network matching, is an essential task for road network-centric data processing such as data integration of road networks and data quality assessment of crowd-sourced road networks. Traditional road-network matching usually relies on feature engineering and parameter selection of the geometry and topology of road networks for similarity measurement, resulting in poor performance when dealing with dense and irregular road network structures. Recent development of graph neural networks (GNNs) has demonstrated unsupervised modeling power on road network data, which learn the embedded vector representation of road networks through spatial feature induction and topology-based neighbor aggregation. However, weighting spatial information on the node feature alone fails to give full play to the expressive power of GNNs. To this end, this paper proposes a Spatial Pattern-aware Graph EMbedding learning method for road-network matching, named SP-GEM, which explores the idea of spatially-explicit modeling by identifying spatial patterns in neighbor aggregation. Firstly, a road graph is constructed from the road network data, and geometric, topological features are extracted as node features of the road graph. Then, four spatial patterns, including grid, high branching degree, irregular grid, and circuitous, are modelled in a sector-based road neighborhood for road embedding. Finally, the similarity of road embedding is used to find data correspondences between road networks. We conduct an algorithmic accuracy test to verify the effectiveness of SP-GEM on OSM and Tele Atlas data. The algorithmic accuracy experiments show that SP-GEM improves the matching accuracy and recall by at least 6.7% and 10.2% among the baselines, with high matching success rate (>70%), and improves the matching accuracy and recall by at least 17.7% and 17.0%, compared to the baseline GNNs, without spatially-explicit modeling. Further embedding analysis also verifies the effectiveness of the induction of spatial patterns. This study not only provides an effective and practical algorithm for road-network matching, but also serves as a test bed in exploring the role of spatially-explicit modeling in GNN-based road network modeling. The experimental performances of SP-GEM illuminate the path to develop GeoEmbedding services for geospatial applications. Full article

The paper presents the geochemical characteristics of 26 selected oil seeps, more than half of which are remnants of old oil wells. The samples were collected from three tectonic units: the Magura, Silesian, and Skole units in the Polish part of the Carpathians. The analyzed seeps are mainly located on outcrops of Inoceramian beds within the Magura nappe, the Krosno Beds and Transition Beds in the Silesian nappe, as well as the Menilite Beds of the Skole unit. The study primarily focused on genetic characteristics, which were used to correlate the seeps with the oils from the deposits of these tectonic units and to assess the degree of secondary alterations. All hydrocarbon seeps were analyzed in terms of their location on surface cross-sections, and attempts were made to assign them features based on the classification proposed in 1952, which takes into account the tectonic characteristics of the regions where the seeps were identified. In the general genetic characterization, these seeps did not show significant differences, suggesting a similar source of supply as the crude oils. Among the analyzed seeps, three genetic groups were distinguished. For correlation purposes, information from published materials on crude oils and their genetic characteristics was used. Of the five classification types described in the literature, only two could be assigned to those occurring in the Carpathians. Considering the tectonic structure and the location of the seeps (based on surface cross-sections), it has been determined that most of the analyzed seeps are the result of migration along faults connecting source rocks or, less frequently, deformed deep accumulations with the surface. Full article

In this study, we delve into the intricate microstructural features of Ti-6Al-4V alloy additively manufactured and heat-treated at 800 °C for 4 h. Our in-depth analysis will enable us to gain a better understanding of the β-Ti precipitation process, its dependence on temperature, and its ultimate effect on the overall mechanical properties. As well as α-Ti martensite grains and β-Ti particles interspersed in the α-Ti grain boundaries, there is a third microstructural feature, overlooked by many researchers. This feature is observed as nano-sized particles homogeneously embedded inside the α-Ti laths. Using high-resolution transmission electron microscopy, we reveal that these nano-sized features do not constitute a different phase. Instead, they define isolated regions of α-Ti in its relaxed form, surrounded by the heavily strained form of the α-Ti phase. This phenomenon is a result of the “incomplete” precipitation of the β-Ti phase following the heat treatment stage. The straining of the α-Ti phase appears as a shift in the equilibrium atomic position. Full article

To explore the effects of different plant combinations in ecological floating beds on water quality purification and phytoplankton community structure in shallow eutrophic lakes, we conducted a survey of phytoplankton communities within ecological floating beds featuring distinct plant combinations in Meiliang Bay, Lake Taihu, during June and August 2021. The study focuses on two combinations: EA (Canna indica + Acorus calamus + Phragmites australis) and ES (Canna indica + Oenanthe javanica + Sagittaria sagittifolia). Results indicated that ecological floating beds significantly improved water quality, with the strongest restoration effects observed in the EA area. Specifically, turbidity was reduced by 47–89%, while chlorophyll a (Chl-a) concentration inhibition rates reached 82% in June and 54% in August. The comprehensive trophic state index (TLI) remained stable at levels indicating slight eutrophication (≤58.6). Phytoplankton community structure shifted from dominance by eutrophic functional groups (primarily FG M) toward greater diversity. In the EA area, the number of dominant functional groups increased from five (control) to six, and the abundance of the key cyanobacteria group (FG M) declined from 18.29% (control) to 7.86%. Redundancy analysis (RDA) revealed temporal changes in driving factors: nutrients were primary in June (explanation rate: 64.7%), while physical factors dominated in August (explanation rate: 51.2%). This study demonstrates that installing ecological floating beds with diverse plant combinations in shallow eutrophic lakes can effectively alter phytoplankton community structure and enhance in situ water restoration. Among the tested combinations, EA (Canna indica + Acorus calamus + Phragmites australis) exhibited the optimal restoration effect. These findings provide a scientific basis for water environment protection and aquatic biological resource restoration in shallow eutrophic lakes. Full article

In recent decades, climate change has led to more frequent episodes of extreme rainfall, increasing the risk of river flooding. Streams and rivers characterized by short flow times are subject to rapid and impressive floods; for this reason, the modeling of their beds is of fundamental importance for the execution of hydraulic calculations capable of predicting the flow rates and identifying the points where floods may occur. In the context of studies conducted on three watercourses in Calabria (Italy), different survey and restitution techniques were used (aerial LiDAR, terrestrial laser scanner, GNSS, photogrammetry). By integrating these methodologies, multi-resolution models were generated, featuring a horizontal accuracy of ±16 cm and a vertical accuracy of ±15 cm. These models form the basis for the hydraulic calculations performed. The results demonstrate the feasibility of producing accurate models that are compatible with the memory and processing capabilities of modern computers. Furthermore, the technique set up and implemented for the refined representation of both the models and the effects predicted by hydraulic calculations in the event of exceptional rainfall (such as flow, speed, flooded areas, and critical points along riverbanks) serves as a valuable tool for improving hydrogeological planning, designing appropriate defense works, and preparing evacuation plans in case of emergency, all with the goal of mitigating hydrogeological risk. Full article

Laser powder-bed fusion (L-PBF) additive manufacturing has been widely explored for fabricating intricate metallic parts such as lattice structures with thin struts. However, L-PBF-fabricated small parts (e.g., thin struts) exhibit different morphological and mechanical characteristics compared to bulk-sized parts due to distinct scan lengths, affecting the melt pool behavior between transient and quasi-steady states. This study investigates the keyhole porosity in Ti6Al4V thin struts fabricated by L-PBF, incorporating a range of strut sizes, along with various levels of linear energy densities. Micro-scaled computed tomography and image analysis were employed for porosity measurements and evaluations. Generally, keyhole porosity lessens with decreasing energy density, though with varying patterns across a higher energy density range. Keyhole porosity in struts predictably becomes severe at high laser powers and/or low scan speeds. However, a major finding reveals that the porosity is reduced with decreasing strut size (if less than 1.25 mm diameter), plausibly because the keyhole formed has not reached a stable state to produce pores in a permanent way. This implies that a higher linear energy density, greater than commonly formulated in making bulk components, could be utilized in making small-scale features to ensure not only full melting but also minimum keyhole porosity. Full article

Additive manufacturing is one of the foundational pillars of Industry 4.0, which is rooted in the integration of intelligent digital technologies, manufacturing, and industrial processes. Machine learning techniques are resources used to support Design for Additive Manufacturing, particularly in design phases and process analysis. Neural Networks are suited to manage complex and non-linear datasets. The article proposes a methodology for the time and cost assessment of the Laser-Powder Bed Fusion 3D printing process using a Neural Network-based approach. The methodology analyzes the main geometrical features of STL files to train Neural Network Machine Learning models. The methodology has been tested on a preliminary dataset that includes a set of parametric CAD models and their corresponding Additive Manufacturing simulations. The trained models achieve an R² value greater than 0.97. A web-service platform has been implemented to provide a valuable tool for users, transforming a research-grade model into a production-grade online endpoint. Full article

The poor surface quality of the metal parts produced by laser powder bed fusion limits their application in load-bearing components, as it promotes crack initiation under cyclic loadings. Consequently, improving part quality relies on time-consuming surface finishing. This work explores a dual-laser powder bed fusion strategy to simultaneously improve the productivity, surface quality, and fatigue life of parts with inclined up-facing surfaces made from a novel tool steel. This is achieved by combining building using a high layer thickness of 120 μm with in situ quality enhancement through powder removal and laser remelting. A bending fatigue campaign was conducted to assess the performance of such treated samples produced with different layer thicknesses (60 μm, hull-bulk 60/120 μm, 120 μm) compared to as-built and machined reference samples. Remelting consistently enhanced the fatigue life compared to the as-built reference samples by up to a factor of 36. The improvement was attributed to the reduced surface roughness, the reduced critical stress concentration factors, and the gradually changing surface features with increased lateral dimensions. This led to a beneficial load distribution and fewer potential crack initiation points. Finally, the remelting samples produced with a layer thickness of 120 μm enhanced the fatigue life by a factor of four and reduced the production time by 30% compared to the standard approach using a layer thickness of 60 μm. Full article

Sleep position recognition plays a crucial role in diagnosing and managing various health conditions, such as sleep apnea, pressure ulcers, and musculoskeletal disorders. Accurate monitoring of body posture during sleep can provide valuable insights for clinicians and support the development of intelligent healthcare systems. This research presents a comparative analysis of sleep position recognition using two distinct approaches: image-based deep learning and accelerometer-based classification. There are five classes: prone, supine, right side, left side, and wake up. For the image-based method, the Visual Geometry Group 16 (VGG16) convolutional neural network was fine-tuned with data augmentation strategies including rotation, reflection, scaling, and translation to enhance model generalization. The image-based model achieved an overall accuracy of 93.49%, with perfect precision and recall for “right side” and “wakeup” positions, but slightly lower performance for “left side” and “supine” classes. In contrast, the accelerometer-based method employed a feedforward neural network trained on features extracted from segmented accelerometer data, such as signal sum, standard deviation, maximum, and spike count. This method yielded superior performance, reaching an accuracy exceeding 99.8% across most sleep positions. The “wake up” position was particularly easy to detect due to the absence of body movements such as heartbeat or respiration when the person is no longer in bed. The results demonstrate that while image-based models are effective, accelerometer-based classification offers higher precision and robustness, particularly in real-time and privacy-sensitive scenarios. Further comparisons of the system characteristics, data size, and training time are also carried out to offer crucial insights for selecting the appropriate technology in clinical, in-home, or embedded healthcare monitoring applications. Full article