Search Results (45)

To address cooperative path planning for multiple UAVs in complex environments, this paper proposes an improved multi-agent deep deterministic policy gradient algorithm, named Prioritized Experience Multi-Agent Deep Deterministic Policy Gradient (PE-MADDPG). An urban low-altitude inspection environment is first constructed within a reinforcement-learning framework, in which dynamic constraints, safety-separation requirements, and formation-cooperation objectives are incorporated into a partially observable Markov decision process. To improve training effectiveness, prioritized experience replay is introduced to increase the utilization of informative samples, an adaptive exploration-noise strategy is designed to regulate exploration intensity, and a multi-head attention mechanism is embedded in the Critic network to enhance the representation of inter-agent interactions. Simulation results in a three-dimensional urban inspection scenario show that PE-MADDPG outperforms the selected benchmark methods in task completion rate, formation maintenance, flight efficiency, and energy consumption. These results provide an effective solution for urban low-altitude inspection tasks. Full article

This paper considers the problem of controlling the motion of an autonomous underwater vehicle (AUV) following a leader in a leader–follower scheme based on visual information about the leader’s position. It is assumed that the leader is equipped with a system of light markers with known geometry, and the follower determines its relative position based on data from an onboard camera without using a hydroacoustic communication channel or direct exchange of navigation information. To synthesize the control law, a reinforcement learning method based on the Proximal Policy Optimization algorithm is used. Policy learning is performed in a simulation environment, taking into account the dynamic model of the agent in the horizontal plane and observation noise. A structure of state space, actions, and reward function is proposed, aimed at minimizing the error in relative position and orientation. Additionally, Bayesian optimization of the weight coefficients of the reward function is performed. Bayesian optimization of the reward function weights reduces the RMS tracking error from 0.24 m to 0.09 m and demonstrates that heading regulation has a significantly stronger impact on stability than position penalties. The results of modeling, testing in the Webots environment, and experiments on MiddleAUV class devices confirm the feasibility and scalability of the approach. It is shown that a single trained policy ensures stable formation maintenance when the number of follower agents and initial conditions change without additional retraining. Full article

This paper proposes a new Unified Namespace (UNS)-based architecture to improve predictive and prescriptive maintenance of industrial equipment and overcome challenges such as incomplete data, poor interoperability, and disconnected IT/OT environments. The framework combines interoperable data formats in real-time sensor data, predictive modeling, prescriptive analytics, and simulations of digital twins, using UNS as a centralized, protocol-agnostic data layer that is scalable and complies with Industry 4.0 and Pharma 4.0 standards. The suggested methodology increases data accessibility, reduces integration complexity, and allows low-latency analytics and automated decision-making. Machine learning predictive models achieved more than 94% accuracy in predicting equipment failures. Prescriptive analytics provides maintenance recommendations to reduce downtime and risks. The feedback loops of digital twins can enhance the accuracy of predictions and allow decision optimization through what-if analysis. A test-bench deployment showed a higher performance compared to traditional point-to-point integration, with lower latency (approximately 18 ms vs. approximately 31 ms), decreasing packet loss (0.40% vs. 3.11%), and higher model accuracy (94.20% vs. 87.51%). The structure avoided more than 4000 simulated breakdowns in the test-bench environment, indicating dependability. The study connects the theoretical applications of the UNS with the actual maintenance processes and provides a sound approach to the industrial analytics and optimization of the equipment. Full article

Mortise and tenon joints are a core technique in ancient Chinese architecture and an important form of extant intangible cultural heritage (ICH). However, despite growing digital adoption for ICH preservation, limited empirical evidence exists on how virtual reality (VR) serious games affect user attitudes and ICH transmission, particularly in complex manual construction such as mortise and tenon joints. This study develops and evaluates a VR gamified learning system based on the six-column Luban lock to examine its role in preserving and transmitting applied ICH. Two studies were conducted: Study 1 focused on the design of the VR system, and Study 2 involved an empirical evaluation, recruiting 14 college students for structured interviews and 305 participants for a questionnaire, analyzed using reliability and validity tests and a four-quadrant model. The analysis revealed that the questionnaire showed excellent internal consistency (Cronbach’s alpha = 0.98) and good construct validity (KMO = 0.97). Most indicators for subject selection, game design, and VR format were in the “advantage” and “maintenance” zones of the four-quadrant model. This supports the hypothesis that these design factors are positively associated with user attitudes and the perceived effectiveness of ICH protection. These results suggest that VR-gamified learning offers a scalable template for digitally protecting and disseminating ICH skills. Full article

Accurate detection of road surface defects and their integration into geospatial representations are key requirements for scalable UAV-based inspection and maintenance systems.This work presents a lightweight processing pipeline that converts image-based pavement defect segmentations into compact geospatial vector representations suitable for integration with GIS-driven inspection workflows. In addition, we introduce and publicly release a UAV-based road defect dataset with pixel-level annotations, specifically designed for crack-like pavement damage. A deep convolutional neural network is trained to perform semantic segmentation of pavement defects using images derived from the publicly available RDD2022 dataset. Segmentation performance is evaluated across a range of probability thresholds using standard pixel-wise metrics, and a validation-selected operating point is used to generate binary defect masks. These masks are subsequently processed to identify individual defect instances and extract vector polygons that preserve the underlying geometry of crack-like structures. For illustrative geospatial integration, predicted defects are projected into geographic coordinates and exported in standard GIS formats. By transforming dense segmentation outputs into compact georeferenced polygons, the proposed framework bridges deep learning-based perception and GIS-based infrastructure assessment, enabling instance-level geometric analysis and providing a practical representation for UAV-based road inspection scenarios. Full article

Urban street greening structure plays a crucial role in promoting environmental justice and enhancing residents’ daily well-being, yet existing studies have primarily focused on vegetation quantity while neglecting how perception and governance interact to shape fairness. This study develops an integrated analytical framework that combines deep learning, machine learning, and spatial analysis to examine the impact of perceptual experience and socio-economic indicators on the equity of greening structure distribution in urban streets, and to reveal the underlying mechanisms driving this equity. Using DeepLabV3+ semantic segmentation, perception indices derived from street-view imagery, and population-weighted Gini coefficients, the study quantifies both the structural and perceptual dimensions of greening equity. XGBoost regression, SHAP interpretation, and Partial Dependence Plot analysis were applied to reveal the influence mechanism of the “Matthew effect” of perception and the Site governance responsiveness on the fairness of the green structure. The results identify two key findings: (1) perception has a positive driving effect and a negative vicious cycle effect on the formation of fairness, where positive perceptions such as beauty and safety gradually enhance fairness, while negative perceptions such as depression and boredom rapidly intensify inequality; (2) Site management with environmental sensitivity and dynamic mutual feedback to a certain extent determines whether the fairness of urban green structure can persist under pressure, as diverse Tree–Bush–Grass configurations reflect coordinated management and lead to more balanced outcomes. Policy strategies should therefore emphasize perceptual monitoring, flexible maintenance systems, and transparent public participation to achieve resilient and equitable urban street greening structures. Full article

(1) Background: Mental health disparities persist across culturally diverse populations despite robust cognitive–behavioral therapy (CBT) efficacy evidence. Cultural neuroscience suggests that neurobiological processes underlying therapeutic mechanisms may exhibit culturally variable patterns, yet integration of neuroscientific frameworks into culturally adapted interventions remains limited. (2) Methods: Following PRISMA 2020 guidelines, we systematically searched PubMed/MEDLINE, PsycINFO, Scopus, and Web of Science (January 2014–December 2024) for peer-reviewed studies examining CBT interventions targeting depression, anxiety, PTSD, or psychological distress in culturally diverse populations. Ninety-four studies were synthesized using narrative methods; methodological heterogeneity precluded meta-analytic pooling. (3) Results: Culturally adapted CBT interventions consistently demonstrated superior outcomes compared to standard protocols across diverse populations. Group formats showed exceptional retention in collectivistic cultures, while hybrid technology-enhanced models achieved strong completion rates across contexts. Cultural adaptation enhanced engagement (e.g., 84% vs. 52% retention in refugee populations) and maintenance of treatment gains. Individual studies reported effect sizes ranging from d = 0.29 to d = 2.4; substantial within-group variability was observed, and identified patterns likely reflect learned cultural adaptations rather than inherent biological differences. Direct neuroimaging evidence within included studies remained limited (13.8%). (4) Conclusions: The evidence supports culturally adapted interventions as essential for equitable mental health outcomes. Cultural experiences may influence therapeutic processes, suggesting potential benefit from considering culturally variable processing patterns alongside universal mechanisms. However, conclusions regarding specific neural pathways remain preliminary, and individual assessment remains paramount, with cultural background representing one factor among many in treatment planning. Full article

This article presents the development of a device for collecting data from acceleration sensors. The developed device uses a 32-bit ESP32 microcontroller, which offers good computational capabilities and rich communication peripherals. The current work examines the structure of the developed system, as well as its operational algorithm. The text presents the main components of the device and the method used for data acquisition. Vibration data was collected using a digital accelerometer. The configuration and parameterization of the device were carried out via a JSON file, which controlled the number of measurements and the rate at which they were performed. The acquired data can be easily filtered and processed using mathematical software, allowing it to be presented in a format suitable for further use in machine learning algorithms and artificial neural networks. The developed solution represents a low-cost alternative to similar vibration data acquisition systems, enabling condition monitoring of various machine components and predictive maintenance at a low hardware cost. Full article

Condition assessment of power equipment is crucial for optimizing maintenance strategies. However, knowledge-driven approaches rely heavily on manual alignment between equipment failure characteristics and guideline information, while data-driven methods predominantly depend on on-site experiments to detect abnormal conditions. Both face challenges in terms of inefficiency and timeliness limitations. With the growing integration of information systems, a significant portion of condition assessment-related information is represented in textual formats, such as system alerts and experimental records. Although Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) show promise in processing such text-based information, their practical application is constrained by LLMs’ hallucinations and RAG’s coarse-grained retrieval mechanisms, which struggle with semantically similar but contextually distinct guideline items. To address these issues, this paper proposes an enhanced RAG framework that integrates hierarchical and global retrieval mechanisms (IHGR-RAG). The framework comprehensively incorporates three optimization strategies: a query rewriting mechanism based on few-shot learning prompt engineering, an integrated approach combining hierarchical and global retrieval mechanisms, and a zero-shot chain-of-thought generation optimization pipeline. Additionally, a Task-Specific Quantitative Evaluation Benchmark is developed to rigorously evaluate model performance. Experimental results indicate that IHGR-RAG achieves accuracy improvements of $4.14\%$ and $5.12\%$ in the task of matching the solely correct guideline item, compared to conventional RAG and standalone hierarchical methods, respectively. Ablation studies confirm the effectiveness of each module. This work advances dynamic health monitoring for power equipment by balancing interpretability, accuracy, and domain adaptability, providing a cost-effective optimization pathway for scenarios with limited annotated data. Full article

Non-destructive evaluation of reinforced concrete structures is essential for effective maintenance and safety assessments. This study explores the combined use of active microwave thermography and deep learning to detect and localize steel reinforcement within concrete elements. Numerical simulations were developed to model the thermal response of reinforced concrete subjected to microwave excitation, generating synthetic thermal images representing the surface temperature patterns of reinforced concrete, influenced by subsurface steel reinforcement. These images served as training data for a deep neural network designed to identify and localize rebar positions based on thermal patterns. The model was trained exclusively on simulation data and subsequently validated using experimental measurements obtained from large-format concrete slabs incorporating a structured layout of embedded steel reinforcement bars. Surface temperature distributions obtained through infrared imaging were compared with model predictions to evaluate detection accuracy. The results demonstrate that the proposed method can successfully identify the presence and approximate location of internal reinforcement without damaging the concrete surface. This approach introduces a new pathway for contactless, automated inspection using a combination of physical modeling and data-driven analysis. While the current work focuses on rebar detection and localization, the methodology lays the foundation for broader applications in non-destructive testing of concrete infrastructure. Full article

Exploring the action mechanisms and enhancement pathways of the resilience of agricultural product green supply chains is conducive to strengthening the system’s risk resistance capacity and providing decision support for achieving the “dual carbon” goals. Based on theories such as dynamic capability theory and complex adaptive systems, this paper constructs a resilience framework covering the three stages of “steady-state maintenance–dynamic adjustment–continuous evolution” from both single and multiple perspectives. Combined with 768 units of multi-agent questionnaire data, it adopts Structural Equation Modeling (SEM) and fuzzy-set Qualitative Comparative Analysis (fsQCA) to analyze the influencing factors of resilience and reveal the nonlinear mechanisms of resilience formation. Secondly, by integrating configurational analysis with machine learning, it innovatively constructs a resilience level prediction model based on fsQCA-XGBoost. The research findings are as follows: (1) fsQCA identifies a total of four high-resilience pathways, verifying the core proposition of “multiple conjunctural causality” in complex adaptive system theory; (2) compared with single algorithms such as Random Forest, Decision Tree, AdaBoost, ExtraTrees, and XGBoost, the fsQCA-XGBoost prediction method proposed in this paper achieves an optimization of 66% and over 150% in recall rate and positive sample identification, respectively. It reduces false negative risk omission by 50% and improves the ability to capture high-risk samples by three times, which verifies the feasibility and applicability of the fsQCA-XGBoost prediction method in the field of resilience prediction for agricultural product green supply chains. This research provides a risk prevention and control paradigm with both theoretical explanatory power and practical operability for agricultural product green supply chains, and promotes collaborative realization of the “carbon reduction–supply stability–efficiency improvement” goals, transforming them from policy vision to operational reality. Full article

This study aims to provide a comprehensive overview of the application of artificial intelligence (AI) methods to solve real-world problems in the oil and gas sector. The methodology involved a two-step process for analyzing AI applications. In the first step, an initial exploration of scientific articles in the Scopus database was conducted using keywords related to AI and computational intelligence, resulting in a total of 11,296 articles. The bibliometric analysis conducted using VOS Viewer version 1.6.15 software revealed an average annual growth of approximately 15% in the number of publications related to AI in the sector between 2015 and 2024, indicating the growing importance of this technology. In the second step, the research focused on the OnePetro database, widely used by the oil industry, selecting articles with terms associated with production and drilling, such as “production system”, “hydrate formation”, “machine learning”, “real-time”, and “neural network”. The results highlight the transformative impact of AI on production operations, with key applications including optimizing operations through real-time data analysis, predictive maintenance to anticipate failures, advanced reservoir management through improved modeling, image and video analysis for continuous equipment monitoring, and enhanced safety through immediate risk detection. The bibliometric analysis identified a significant concentration of publications at Society of Petroleum Engineers (SPE) events, which accounted for approximately 40% of the selected articles. Overall, the integration of AI into production operations has driven significant improvements in efficiency and safety, and its continued evolution is expected to advance industry practices further and address emerging challenges. Full article

Manufacturing enterprises implementing Industry 4.0 technologies face significant challenges in integrating heterogeneous maintenance data sources and deploying AI solutions effectively. While various AI methods exist for predictive maintenance, the fundamental challenge lies in creating a cohesive architecture that enables seamless data flow and AI deployment. This paper presents a standardized architecture framework with initial implementation steps at Toyota Motor Manufacturing France. The proposed architecture introduces a four-layer approach: (1) a unified data acquisition layer integrating IoT sensors, CMMS, and legacy systems through standardized interfaces (OPC UA/MQTT), (2) a data quality and standardization layer ensuring consistent formats and automated validation, (3) a modular AI deployment layer supporting anomaly detection (Wavelet-based analysis and Deep Learning) and remaining useful life prediction (LSTM networks), and (4) a maintenance workflow integration layer with bi-directional feedback. Key innovations include a unified maintenance data model, configurable data quality pipelines, and human-in-the-loop decision support. A conceptual validation suggests this architecture can improve integration efficiency and reduce equipment downtime. This research contributes to smart maintenance by providing a scalable architecture that balances interoperability, data quality, and practical deployment in brownfield environments. Full article

The analysis and accurate identification of DC-side grounding faults in grid-connected photovoltaic (PV) inverters is a critical step in enhancing operation and maintenance capabilities and ensuring the safe operation of PV grid-connected systems. However, the characteristics of DC-side grounding faults remain unclear, and effective methods for identifying such faults are lacking. To address the need for leakage characteristic analysis and fault identification of DC-side grounding faults in grid-connected PV inverters, this paper first establishes an equivalent analysis model for DC-side grounding faults in three-phase grid-connected inverters. The formation mechanism and frequency-domain characteristics of residual current under DC-side fault conditions are analyzed, and the specific causes of different frequency components in the residual current are identified. Based on the leakage current mechanisms and statistical characteristics of grid-connected PV inverters, a multi-type DC-side grounding fault identification method is proposed using the light gradient-boosting machine (LGBM) algorithm. In the simulation case study, the proposed fault identification method, which combines mechanism characteristics and statistical characteristics, achieved an accuracy rate of 99%, which was significantly superior to traditional methods based solely on statistical characteristics and other machine learning algorithms. Real-time simulation verification shows that introducing mechanism-based features into grid-connected photovoltaic inverters can significantly improve the accuracy of identifying grounding faults on the DC side. Full article

Background: Understanding the metabolic adaptations of wild bighorn sheep (Ovis c. canadensis) to nutritional stress is crucial for their conservation. Methods: This study employed ¹H nuclear magnetic resonance (NMR) metabolomics to investigate the biochemical responses of these animals to varying sub-maintenance nutritional states. Serum samples from 388 wild bighorn sheep collected between 2014 and 2017 from December (early sub-maintenance) through March (severe sub-maintenance) across Wyoming and Montana were analyzed. Multivariate statistics and machine learning analyses were employed to identify characteristic metabolic patterns and metabolic interactions between early and severe sub-maintenance nutritional states. Results: Significant differences were observed in the levels of 15 of the 49 quantified metabolites, including formate, thymine, glucose, choline, and others, pointing to disruptions in one-carbon, amino acid, and central carbon metabolic pathways. These metabolites may serve as indicators of critical physiological processes such as nutritional intake, immune function, energy metabolism, and protein catabolism, which are essential for understanding how wild bighorn sheep adapt to nutritional stress. Conclusions: This study has generated valuable insights into molecular networks underlying the metabolic resilience of wild bighorn sheep, highlighting the potential for using specific biochemical markers to evaluate nutritional and energetic states in free-ranging ungulates. These insights may help wildlife managers and ecologists compare populations across different times in seasonal cycles, providing information to assess the adequacy of seasonal ranges and support conservation efforts. This research strengthens our understanding of metabolic adaptations to environmental stressors in wild ruminants, offering a foundation for improving management practices to maintain healthy bighorn sheep populations. Full article