Search Results (3,467)

The integration of machine learning (ML) into industrial automation is fundamentally reshaping how manufacturing systems are monitored, inspected, and optimized. By applying machine learning to real-time sensor data and operational histories, advanced models enable proactive fault prediction, intelligent inspection, and dynamic process control—directly enhancing system reliability, product quality, and efficiency. This review explores the transformative role of ML across three key domains: Predictive Maintenance (PdM), Quality Control (QC), and Process Optimization (PO). It also analyzes how Digital Twin (DT) and Edge AI technologies are expanding the practical impact of ML in these areas. Our analysis reveals a marked rise in deep learning, especially convolutional and recurrent architectures, with a growing shift toward real-time, edge-based deployment. The paper also catalogs the datasets used, the tools and sensors employed for data collection, and the industrial software platforms supporting ML deployment in practice. This review not only maps the current research terrain but also highlights emerging opportunities in self-learning systems, federated architectures, explainable AI, and themes such as self-adaptive control, collaborative intelligence, and autonomous defect diagnosis—indicating that ML is poised to become deeply embedded across the full spectrum of industrial operations in the coming years. Full article

South Dongting Lake is an essential aquatic ecosystem that receives substantial water inflows from the Xiangjiang and Zishui Rivers. However, it is significantly impacted by human activities, including mining, smelting, and farming. These activities have led to serious contamination of the lake’s sediments with heavy metals (HMs). This study investigated the distribution, mobility, and influencing factors of HMs at the sediment–water interface. To this end, sediment samples were analyzed from three key regions (Xiangjiang River estuary, Zishui River estuary, and northeastern South Dongting Lake) using traditional sampling methods and Diffusive Gradients in Thin Films (DGT) technology. Analysis of fifteen HMs (Pb, Bi, Ni, As, Se, Cd, Sb, Mn, Zn, V, Cr, Cu, Tl, Co, and Fe) revealed significant spatial heterogeneity. The results showed that Cr, Cu, Pb, Bi, Ni, As, Se, Cd, Sb, Mn, Zn, and Fe exhibited high variability (CV > 0.20), whereas V, Tl, and Co demonstrated stable concentrations (CV < 0.20). Concentrations were found to exceed background values of the upper continental crust of eastern China (UCC), Yangtze River sediments (YZ), and Dongting Lake sediments (DT), particularly at the Xiangjiang estuary (XE) and in the northeastern regions. Speciation analysis revealed that V, Cr, Cu, Ni, and As were predominantly found in the residual fraction (F4), while Pb and Co were concentrated in the oxidizable fraction (F3), Mn and Zn appeared primarily in the exchangeable fractions (F1 and F2), and Cd was notably dominant in the exchangeable fraction (F1), suggesting a high potential for mobility. Additionally, DGT results confirmed a significant potential for the release of Pb, Zn, and Cd. Contamination assessment using the Pollution Load Index (PLI) and Geoaccumulation Index (Igeo) identified Pb, Bi, Ni, As, Se, Cd, and Sb as major pollutants. Among these, Bi and Cd were found to pose the highest risks. Furthermore, the Risk Assessment Code (RAC) and the Potential Ecological Risk Index (PERI) highlighted Cd as the primary ecological risk contributor, especially in the XE. The study identified sediment grain size, pH, electrical conductivity, and nutrient levels as the primary influencing factors. The PMF modeling revealed HM sources as mixed smelting/natural inputs, agricultural activities, natural weathering, and mining/smelting operations, suggesting that remediation should prioritize Cd control in the XE with emphasis on external inputs. Full article

Background: A dilated main pancreatic duct (MPD) ≥ 5 mm can be observed in main-duct IPMNs (MD-IPMN) and chronic pancreatitis (CP); however, distinguishing between the two differently treated diseases can be difficult. Cell-free (cf) DNA in MPD fluid obtained by EUS-guided FNA might help to distinguish MD-IPMN from CP. Methods: All patients with a dilated MPD ≥ 5 mm on EUS during the period of 1 June 2017 to 30 April 2024 were prospectively analysed in this single-centre study, with EUS-guided MPD fluid aspiration performed for suspected MD-IPMN or CP in patients who were suitable for surgery. Twenty-two known gastrointestinal cancer genes, including GNAS and KRAS, were analysed by deep targeted (dt) NGS. The results were correlated with resected tissue, biopsy, and long-term follow-up. Results: A total of 164 patients with a dilated MPD were identified, of which 30 (18.3%) underwent EUS-guided FNA, with 1 patient having a minor complication (3.3%). Twenty-two patients (mean MPD diameter of 12.4 (7–31) mm) with a definitive, mostly surgically confirmed diagnosis were included in the analysis. Only a fish-mouth papilla, which was present in 3 of 12 (25%) MD-IPMNs, could reliably differentiate between the two diseases, with history, symptoms, diffuse or segmental MPD dilation, presence of calcifications on imaging, cytology, and CEA in the ductal fluid failing to achieve differentiation. However, GNAS mutations were found exclusively in 11 of the 12 (91.6%) patients with MD-IPMN (p < 0.01), whereas KRAS mutations were identified in both diseases. Conclusions: GNAS testing by dtNGS in aspirated fluid from dilated MPD obtained by EUS-guided FNA may help differentiate MD-IPMN from CP for surgical resection. Full article

The rapid growth of electric vehicles (EVs) and new energy systems has put lithium-ion batteries at the center of the clean energy change. Nevertheless, to achieve the best battery performance, safety, and sustainability in many changing circumstances, major innovations are needed in Battery Management Systems (BMS). This review paper explores how artificial intelligence (AI) and digital twin (DT) technologies can be integrated to enable the intelligent BMS of the future. It investigates how powerful data approaches such as deep learning, ensembles, and models that rely on physics improve the accuracy of predicting state of charge (SOC), state of health (SOH), and remaining useful life (RUL). Additionally, the paper reviews progress in AI features for cooling, fast charging, fault detection, and intelligible AI models. Working together, cloud and edge computing technology with DTs means better diagnostics, predictive support, and improved management for any use of EVs, stored energy, and recycling. The review underlines recent successes in AI-driven material research, renewable battery production, and plans for used systems, along with new problems in cybersecurity, combining data and mass rollout. We spotlight important research themes, existing problems, and future drawbacks following careful analysis of different up-to-date approaches and systems. Uniting physical modeling with AI-based analytics on cloud-edge-DT platforms supports the development of tough, intelligent, and ecologically responsible batteries that line up with future mobility and wider use of renewable energy. Full article

A Digital Twin (DT) is not just a collection of static digital models at the component level of a physical system, but a dynamic entity that evolves in parallel with the physical system it mirrors. This evolution starts with physics-based or data-driven physics models representing the physical system and advances to Authoritative Virtualization or DT through continuous data assimilation, and ongoing Digital Engineering (DE) Test and Evaluation (T&E) processes. This paper presents a generalizable mathematical framework for the DE Test and Evaluation Process that incorporates data assimilation, uncertainty quantification, propagation, and DT calibration, applicable to diverse physical–digital systems. This framework will enable the DT to perform operations, control, decision-making, and predictions at scale. The framework will be implemented for two cases: (i) the DT of the CubeSat to analyze the CubeSat’s structural deformation during its deployment in space and (ii) the DT of the CROME engine. The DT of the CubeSat will be capable of predicting and monitoring structural health during its space operations. The DT of the CROME engine will be able to predict the thrust at various conditions. Full article

Zinc (Zn) deficiency poses a major global health challenge, and wheat grains generally contain low Zn concentrations. In this study, the wheat cultivar ‘Zhongmai 175’ was identified as zinc-efficient. Hydroponic experiments demonstrated that Zn deficiency induced the secretion of oxalic acid and malic acid in root exudates and significantly increased total root length in ‘Zhongmai 175’. To elucidate the underlying regulatory mechanisms, transcriptome profiling via RNA sequencing was conducted under Zn-deficient conditions. A total of 2287 and 1935 differentially expressed genes (DEGs) were identified in roots and shoots, respectively. Gene Ontology enrichment analysis revealed that these DEGs were primarily associated with Zn ion transport, homeostasis, transmembrane transport, and hormone signaling. Key DEGs belonged to gene families including VIT, NAS, DMAS, ZIP, tDT, HMA, and NAAT. KEGG pathway analysis indicated that phenylpropanoid biosynthesis, particularly lignin synthesis genes, was significantly downregulated in Zn-deficient roots. In shoots, cysteine and methionine metabolism, along with plant hormone signal transduction, were the most enriched pathways. Notably, most DEGs in shoots were associated with the biosynthesis of phytosiderophores (MAs, NA) and ethylene. Overall, genes involved in Zn ion transport, phytosiderophore biosynthesis, dicarboxylate transport, and ethylene biosynthesis appear to play central roles in wheat’s adaptive response to Zn deficiency. These findings provide a valuable foundation for understanding the molecular basis of Zn efficiency in wheat and for breeding Zn-enriched varieties. Full article

As the global emphasis on sustainable development intensifies, the integration of digital technologies (DTs) into efforts to address the Sustainable Development Goals (SDGs) has gained increasing attention. However, existing research on the link between the SDGs and DTs remains fragmented and lacks a comprehensive perspective on their interconnections. We aimed to address this gap by conducting a large-scale bibliometric analysis based on Elsevier’s SDG research mapping technique. Drawing on approximately 1.17 million publications related to both the 17 SDGs and 11 representative DTs, we explored research trends in the SDG–DT association, identified DTs that are most frequently tied to specific SDGs, and uncovered emerging areas of research within this interdisciplinary domain. Our results highlight the rapid expansion in the volume and variety of SDG–DT studies. Our findings shed light on the widespread relevance of artificial intelligence and robotics, the goal-specific applications of technologies such as 3D printing, cloud computing, drones, and extended reality, as well as the growing visibility of emerging technologies such as digital twins and blockchain. These findings offer valuable insights for researchers, policymakers, and industry leaders aiming to strategically harness DTs to support sustainable development and accelerate progress toward achieving the SDGs. Full article

Microfluidic platforms offer a powerful approach for ultimately replicating vascularization in vitro, enabling precise microscale control and manipulation of physical parameters. Despite these advances, the real-time ability to monitor and quantify mechanical forces—particularly pressure—within microfluidic environments remains constrained by limitations in cost and compatibility across diverse device architectures. Our work presents an advanced experimental module for quantifying pressure within a vascularizing microfluidic platform. Equipped with an integrated Arduino microcontroller and image monitoring, the system facilitates real-time remote monitoring to access temporal pressure and flow dynamics within the device. This setup provides actionable insights into the hemodynamic parameters driving vascularization in vitro. In-line pressure sensors, interfaced through I2C communication, are employed to precisely record inlet and outlet pressures during critical stages of microvasculature tubulogenesis. Flow measurements are obtained by analyzing changes in reservoir volume over time (dV/dt), correlated with the change in pressure over time (dP/dt). This quantitative assessment of various pressure conditions in a microfluidic platform offers insights into their impact on microvasculature perfusion kinetics. Data acquisition can help inform and finetune functional vessel network formation and potentially enhance the durability, stability, and reproducibility of engineered in vitro platforms for organoid vascularization in regenerative medicine. Full article

Background: This study aimed to assess the impact of methacrylate-functionalized polyhedral oligomeric silsesquioxanes dispersed in nanosilica (MA/Ns-POSS) on the mechanical properties of light-curable dental resins and composites. The primary goal was to evaluate how different concentrations of MA/Ns-POSS (0.5–20 wt.%) affect the hardness, flexural strength, modulus, diametral tensile strength, polymerization shrinkage stress, and degree of conversion of these materials. Methods: A mixture of Bis-GMA, UDMA, TEGDMA, HEMA, and camphorquinone, with a tertiary amine as the photoinitiator, was used to create resin and composite samples, incorporating 45 wt.% silanized silica for the composites. Hardness (Vickers method, HV), flexural strength (FS), and flexural modulus (E_f) were assessed using three-point bending tests, while diametral tensile strength (DTS) polymerization shrinkage stresses (PSS), and degree of conversion (DC) analysis were analyzed for the composites. Results: The results showed that resins with 10 wt.% MA/Ns-POSS exhibited the highest E_f and FS values. Composite hardness peaked at 20 wt.% MA/Ns-POSS, while DTS increased up to 2.5 wt.% MA/Ns-POSS but declined at higher concentrations. PSS values decreased with increasing MA/Ns-POSS concentration, with the lowest values recorded at 15–20 wt.%. DC analysis also showed substantial improvement for 15–20 wt.% Conclusion: Incorporating MA/Ns-POSS improves the mechanical properties of both resins and composites, with 20 wt.% showing the best results. Further studies are needed to explore the influence of higher additive concentrations. Full article

Oil and gas development is characterized by high technical complexity, strong interdisciplinarity, long investment cycles, and significant uncertainty. To meet the need for quick evaluation of overseas oilfield projects with limited data and experience, this study develops an analogy indicator system and tests multiple machine-learning algorithms on two analogy tasks to identify the optimal method. Using an initial set of basic indicators and a database of 1436 oilfield samples, a combined subjective–objective weighting strategy that integrates statistical methods with expert judgment is used to select, classify, and assign weights to the indicators. This process results in 26 key indicators for practical analogy analysis. Single-indicator and whole-asset analogy experiments are then performed with five standard machine-learning algorithms—support vector machine (SVM), random forest (RF), backpropagation neural network (BP), k-nearest neighbor (KNN), and decision tree (DT). Results show that SVM achieves classification accuracies of 86% and 95% in medium-high permeability sandstone oilfields, respectively, greatly surpassing other methods. These results demonstrate the effectiveness of the proposed indicator system and methodology, providing efficient and objective technical support for evaluating and making decisions on overseas oilfield development projects. Full article

The growing scale of big data and artificial intelligence (AI)-based models has heightened the urgency of developing real-time digital twins (DTs), particularly those capable of simulating personalized behavior in dynamic environments. In this study, we examine the personalization of AI-based digital twins (DTs), with a focus on overcoming computational latencies that hinder real-time responses—especially in complex, large-scale systems and networks. We use bibliometric analysis to map current trends, prevailing themes, and technical challenges in this field. The key findings highlight the growing emphasis on scalable model architectures, multimodal data integration, and the use of high-performance computing platforms. While existing research has focused on model decomposition, structural optimization, and algorithmic integration, there remains a need for fast DT platforms that support diverse user requirements. This review synthesizes these insights to outline new directions for accelerating adaptation and enhancing personalization. By providing a structured overview of the current research landscape, this study contributes to a better understanding of how AI and edge computing can drive the development of the next generation of real-time personalized DTs. Full article

Helical milling presents a promising alternative to conventional drilling for hole production, offering superior surface quality and improved production efficiency. While this technique has been extensively applied in the aerospace industry, its potential for machining common engineering materials, such as AISI 1045 steel, remains underexplored in the literature. This study addresses this gap by systematically evaluating the influence of key process parameters—cutting speed (V_c), axial depth of cut (a_p), and tool diameter (D_t)—on hole quality attributes, including surface roughness, burr formation, and nominal diameter accuracy. A full factorial experimental design (2³) was employed, coupled with analysis of variance (ANOVA), to quantify the effects and interactions of these parameters. The results reveal that, with a higher V_c, it is possible to reduce surface roughness (R_a) by 30% to 40%, while an increased a_p leads to a 50% increase in R_a. Additionally, D_t emerged as the most critical factor for nominal diameter accuracy, reducing geometrical errors by 1% with a larger D_t. Burr formation was predominantly observed at the lower end of the hole, highlighting challenges specific to this technique. These findings provide valuable insights into optimizing helical milling for low-carbon steels, offering a foundation for broader industrial adoption and further research. Full article

The integration of digital twins (DTs) with intelligent traffic systems (ITSs) holds strong potential for improving real-time management in smart cities. However, securing digital twins remains a significant challenge due to the dynamic and adversarial nature of cyber–physical environments. In this work, we propose TwinFedPot, an innovative digital twin-based security architecture that combines honeypot-driven data collection with Zero-Shot Learning (ZSL) for robust and adaptive cyber threat detection without requiring prior sampling. The framework leverages Inverse Federated Distillation (IFD) to train the DT server, where edge-deployed honeypots generate semantic predictions of anomalous behavior and upload soft logits instead of raw data. Unlike conventional federated approaches, TwinFedPot reverses the typical knowledge flow by distilling collective intelligence from the honeypots into a central teacher model hosted on the DT. This inversion allows the system to learn generalized attack patterns using only limited data, while preserving privacy and enhancing robustness. Experimental results demonstrate significant improvements in accuracy and F1-score, establishing TwinFedPot as a scalable and effective defense solution for smart traffic infrastructures. Full article

The increasing utilization of hard-to-cut materials in high-performance sectors such as aerospace and defense has pushed manufacturing systems to be flexible in processing large workpieces with a wide range of materials while also delivering high precision. Recent studies have highlighted the potential of integrating industrial robots (IRs) with electric discharge machining (EDM) to create a non-contact, low-force manufacturing platform, particularly suited for the accurate machining of hard-to-cut materials into complex and large-scale monolithic components. In response to this potential, a novel robotic EDM system has been developed. However, the manual programming and control of such a convoluted system present a significant challenge, often leading to inefficiencies and increased error rates, creating a scenario where the EDM process becomes unfeasible. To enhance the industrial applicability of this robotic EDM technology, this study focuses on a novel methodology to develop and validate a digital twin (DT) of the physical robotic EDM system. The digital twin functions as a virtual experimental environment for tool motion, effectively addressing the challenges posed by collisions and kinematic singularities inherent in the physical system, yet with proven 20-micron EDM gap accuracy. Furthermore, it facilitates a CNC-like, user-friendly offline programming framework for robotic EDM cutting path generation. Full article

The aim was to explore using machine learning (including cluster mapping and k-means methods) to classify types of mead based on sensory analysis and aromatic compounds. Machine learning is a modern tool that helps with detailed analysis, especially because verifying aromatic compounds is challenging. In the first stage, a cluster map analysis was conducted, allowing for the exploratory identification of the most characteristic features of mead. Based on this, k-means clustering was performed to evaluate how well the identified sensory features align with logically consistent groups of observations. In the next stage, experiments were carried out to classify the type of mead using algorithms such as Random Forest (RF), adaptive boosting (AdaBoost), Bootstrap aggregation (Bagging), K-Nearest Neighbors (KNN), and Decision Tree (DT). The analysis revealed that the RF and KNN algorithms were the most effective in classifying mead based on sensory characteristics, achieving the highest accuracy. In contrast, the AdaBoost algorithm consistently produced the lowest accuracy results. However, the Decision Tree algorithm achieved the highest accuracy value (0.909), demonstrating its potential for precise classification based on aroma characteristics. The error matrix analysis also indicated that acacia mead was easier for the algorithms to identify than tilia or buckwheat mead. The results show the potential of combining an exploratory approach (cluster map with the k-means method) with machine learning. It is also important to focus on selecting and optimizing classification models used in practice because, as the results so far indicate, choosing the right algorithm greatly affects the success of mead identification. Full article