Search Results (6,259)

The large-scale integration and grid connection of renewable energy sources and charging stations introduce a multitude of nonlinear and impact loads, resulting in more severe distortion and higher complexity of disturbance signals in power systems. As a consequence, power quality disturbances (PQDs) in active distribution networks, including overvoltage and harmonics, display greater randomness and diversity, which increases the challenge of PQD identification. To tackle this problem, this study presents a dual-channel early-fusion approach for PQD recognition based on Spatial Post-MultiScale Fusion Entropy (SMFE). SMFE is used as an entropy-based feature-construction pipeline in which a time–frequency representation is formed prior to spatial post-multiscale aggregation to produce a compact complexity map complementary to waveform morphology. Subsequently, a dual-channel model is constructed by integrating waveform-morphology input with SMFE-derived complexity features for joint learning. By leveraging the ConvNeXt architecture and a Squeeze-and-Excitation (SE) mechanism, a multimodal channel-recalibration model is implemented to emphasize informative feature responses during PQD recognition. Experimental verification with simulated signals shows that the proposed approach achieves an identification accuracy of 97.83% under an SNR of 30 dB, indicating robust performance under the tested noise settings. Full article

Accurately quantifying vertical sediment transport rates in large seaward rivers is vital for estimating basin-scale water and sediment fluxes and assessing riverbed evolution. Traditional multi-point velocity and suspended sediment concentration (SSC) measurements are costly and slow, hindering long-term online monitoring. Bidirectional flows in tidal reaches further exacerbate this challenge. We propose a physics-constrained support vector machine (SVM) inversion method to estimate vertical sediment transport rates from single-point measurements. Constrained by modified logarithmic velocity and Rouse suspended sediment concentration profiles, it quantitatively relates single-point hydraulic variables to key parameters governing vertical distributions. Lower Yangtze River tidal reach field data validate the hybrid model’s successful reconstruction of vertical distributions. It accurately captures transient sediment responses across maximum flood and ebb. Inverted transport rates match measurements closely (RMSE = 0.085, NSE = 0.969, PBIAS = 2.50%) and exhibit strong cross-site generalization. Sensitivity analysis identifies 0.4 times the water depth above the riverbed as the optimal single-point sensor position. Although currently validated only in the lower Yangtze River, this low-cost, reliable method supports local basin management, flood control, and disaster mitigation by enabling continuous sediment flux monitoring. However, applying it to other river or estuarine systems may require recalibration or retraining to adapt to different local conditions. Full article

Urban underground sewage pipelines often suffer from defects such as cracks, irregular joint misalignment, and stratified sedimentation blockages, which may lead to pipeline bursts, sewage overflow, and water pollution. Timely detection of abnormal defects in sewage pipelines is critical to ensuring public health and environmental sustainability. Vision-based sewage pipeline defect detection plays a crucial role in modern urban wastewater treatment systems. However, it still faces challenges such as limited feature extraction capabilities, insufficient multi-scale defect characterization, and poor positioning stability when dealing with low-contrast images and in environments with severe background interference. To address this issue, this study proposes an enhanced SAW-YOLOv8l model that integrates RT-DETR (real-time detection Transformer) with CNN (convolutional neural network) architecture. First, a C2f_SCA module improves the long-distance feature extraction capability and localization precision. Second, an AIFI-PRBN module enhances global feature correlation through attention-mechanism-based intra-scale feature interaction and reduces computational complexity using lightweight techniques. Finally, an adaptive dynamic weighted loss function based on Wise-IoU (weighted intersection over union) further improves training convergence and robustness by balancing the gradient distribution of samples. Experiments on a mixed dataset comprising Sewer-ML and industrial images demonstrate that the SAW-YOLOv8l model achieved mAP@0.5 of 86.2% and precision of 84.4%, which were improvements of 2.4% and 6.6% respectively over the baseline model, significantly enhancing the detection performance of abnormal defects in sewage pipelines. Full article

Accurate precipitation nowcasting plays an important role in disaster prevention and hydrometeorological applications, yet it remains highly challenging due to the complex spatiotemporal variability and multi-scale structural characteristics of precipitation systems. Existing deep learning methods are largely data-driven and often struggle to effectively exploit multi-source observations or learn physically meaningful representations. To address these limitations, this study proposes a Multi-Scale Frequency–Temporal Network (MS-FTNet) for precipitation nowcasting. The framework leverages Fourier transform-based frequency-domain modeling to achieve an interpretable multi-scale decomposition of precipitation dynamics. Specifically, low-frequency components capture large-scale stratiform patterns and their temporal evolution, while high-frequency components represent localized convective structures and abrupt variations. Building on this, a Global Feature Collaboration (GFC) module integrates global frequency-domain representations with multi-scale convolutional features, and an Adaptive Temporal Fusion (ATF) module enhances temporal dependency modeling. Experiments on the SEVIR dataset demonstrate that MS-FTNet consistently outperforms representative baseline models in terms of MSE, CSI, and LPIPS, particularly for heavy precipitation events and longer forecast lead times. Full article

With the rapid development of e-commerce and smart manufacturing, automated warehouse systems have become critical infrastructure for modern logistics. In China’s vast market, the dynamic scheduling of Rail-Guided Vehicles (RGVs) faces significant challenges due to complex task uncertainties, hierarchical supply chain structures, and real-time collision avoidance requirements. Traditional rule-based methods and static optimization models often fail to adapt to such dynamic environments. To address these issues, this paper proposes a novel hybrid deep reinforcement learning framework integrating a Dynamic Graph Neural Network (DGNN) and a Transformer model. The DGNN captures the spatiotemporal dependencies of the warehouse network topology, while the Transformer mechanism enhances long-range feature extraction for task prioritization. Furthermore, we design a centralized Deep Q-network (DQN) framework with parameterized action spaces to coordinate multiple RGVs collaboratively. While the system manages multiple physical vehicles, the learning architecture employs a single-agent global scheduler to avoid the non-stationarity issues inherent in multi-agent reinforcement learning. Experimental results based on real-world data from a large-scale electronics manufacturing warehouse demonstrate that our method reduces average task completion time by 18.5% and improves system throughput by 22.3% compared to state-of-the-art baselines. The proposed approach demonstrates potential for intelligent warehouse management in dynamic industrial scenarios. Full article

High-quality training data are essential for the performance and generalization of artificial intelligence systems, particularly in dynamic environments such as adaptive stream processing for disaster response. However, constructing large and representative datasets remains costly and time-consuming, especially in domains where real data are scarce or difficult to obtain. Large Language Models (LLMs) provide powerful capabilities for synthetic text generation, yet the quality of generated data strongly depends on the design of input prompts. Prompt engineering is therefore critical, but it remains largely manual and difficult to scale, particularly in black-box settings where model internals are inaccessible. This work introduces EVOLMD-MO, a multi-objective evolutionary framework for automated prompt learning aimed at generating high-quality synthetic text datasets using black-box LLMs. The proposed approach formulates prompt optimization as a multi-objective search problem in which candidate prompts evolve through genetic operators guided by two complementary objectives: semantic fidelity to reference data and generative diversity of the produced samples. To support scalable optimization, the framework integrates a modular multi-agent architecture that decouples prompt evolution, LLM interaction, and evaluation mechanisms. The evolutionary process is implemented using the NSGA-II algorithm, enabling the discovery of diverse Pareto-optimal prompts that balance semantic preservation and diversity. Experimental evaluation using large-scale disaster-related social media data demonstrates that the proposed approach consistently improves prompt quality across generations while maintaining a stable trade-off between fidelity and diversity. Compared with a single-objective baseline, EVOLMD-MO explores a significantly broader semantic search space and produces more diverse yet semantically coherent synthetic datasets. These results indicate that multi-objective evolutionary prompt learning constitutes a promising strategy for black-box LLM-driven data generation, with potential applicability to adaptive data analytics and real-time decision-support systems in highly dynamic environments, pending broader validation across domains and models. Full article

Parallel robots are widely applied in many fields because of their unique advantages. To ensure their operational safety and reduce maintenance costs, designing an accurate and reliable fault diagnosis method is essential. Focusing on the 2RRU-RRS parallel robot, this paper proposes an intelligent fault diagnosis method based on a multi-scale convolutional residual network integrated with an Efficient Channel Attention mechanism (MS-ECA-ResNet). Firstly, to fully retain the time-frequency features of the signals, the one-dimensional vibration signals are converted into two-dimensional images using the Continuous Wavelet Transform (CWT). Secondly, a multi-scale convolutional feature extraction structure is designed to enhance the model’s feature extraction ability at different time scales. Furthermore, the ECA mechanism is introduced into the residual network to reinforce important feature channels and suppress noise interference. Comparative experiments, noise environment experiments, and ablation experiments were conducted on a 2RRU-RRS parallel robot experimental platform with a vibration signal dataset. The results demonstrate that the proposed method achieves superior diagnostic accuracy and robustness compared to typical deep learning models, particularly in maintaining high performance under simulated noise conditions. This provides a preliminary validation of the method’s effectiveness in capturing fault-related impacts, offering a potential technical reference for the health monitoring of parallel robots in real-world scenarios. Full article

Evacuation planning is increasingly challenged by compound hazards in which interacting threats degrade infrastructure, influence human behavior, and destabilize transportation systems. Although agent-based models and dynamic traffic simulations have advanced substantially, much of the evacuation literature remains hazard-specific, case-bound, or difficult to transfer across regions. In parallel, transportation resilience research shows that multi-hazard effects are often non-additive and that cascading infrastructure failures can amplify disruption beyond directly affected areas, raising important sustainability concerns related to community safety, infrastructure continuity, social equity, and long-term planning capacity. These realities motivate the development of evacuation modeling frameworks that are modular, adaptable, and capable of representing co-evolving behavioral and network processes under compound hazard conditions. This review synthesizes advances in evacuation agent-based modeling, dynamic traffic assignment, hazard-induced network degradation, and compound disaster research to propose an adaptable compound-hazard evacuation framework integrating three interdependent layers: hazard processes, transportation network dynamics, and agent decision-making. The proposed framework is organized around four principles: (1) modular hazard representation, (2) decoupling behavioral decision logic from hazard physics, (3) dynamic network state evolution, and (4) neighborhood-scale performance metrics. To support sustainable and equitable local planning, the framework prioritizes spatially resolved outputs, including neighborhood clearance time, isolation probability, accessibility loss, and shelter demand imbalance. By emphasizing modularity, configurability, and policy-relevant metrics, this review connects methodological advances in evacuation modeling to the broader sustainability goals of resilient infrastructure systems, inclusive disaster risk reduction, and locally informed emergency planning. Full article

Citrus trees exhibit severe alternate bearing, resulting in significant annual yield fluctuations and posing substantial challenges to orchard management planning. Accurate citrus bud counting provides an effective solution by supplying essential data for tree-level and orchard-level yield prediction. However, citrus buds are extremely small (5–10 mm in diameter) and are frequently occluded by leaves during the flowering stage, which makes precise detection highly challenging in complex orchard environments. To address these challenges, this paper proposes a Contextual and Frequency-Aware Detector (CFADet) for robust citrus bud detection. Specifically, an Enhanced Feature Fusion (EFF) module is introduced in the neck to refine multi-scale feature aggregation and strengthen information flow for small targets. A Contextual Boundary Enhancement Module (CBEM) is designed to capture surrounding contextual cues and enhance boundary representation through dimensional interaction and max-pooling operations. To suppress background interference, a Frequency-Aware Module (FAM) is developed to adaptively recalibrate frequency components in the amplitude spectrum, thereby enhancing target features while reducing background noise. In addition, Spatial-to-Depth Convolution (SPDConv) is employed to reconstruct the backbone to preserve fine-grained bud features while reducing model parameters. Experimental results show that CFADet achieves 81.1% precision, 80.9% recall, 81.0% F1-score, and 87.8% mAP, with stable real-time performance on mobile devices in practical orchard scenarios. This study presents a preliminary investigation into robust citrus bud detection in real-world orchard environments and provides a promising technical foundation for intelligent orchard monitoring and early yield estimation, while further validation on larger and more diverse datasets is still required. Full article

Accurate and rapid transient voltage stability assessment is crucial for the safe and stable operation of new energy bases in desert and grassland regions. Existing deep learning methods fail to adequately capture the high-dimensional dynamic coupling features of transient voltage signals in large-scale renewable energy bases with UHVDC transmission, and suffer from poor performance under class-imbalanced sample conditions. This paper proposes a transient voltage stability assessment method utilizing continuous wavelet transform (CWT) time–frequency images and a deep residual network (ResNet-50). CWT with the Morlet wavelet basis converts voltage time-series signals into multi-scale time–frequency images to simultaneously capture temporal and frequency-domain transient features. An improved focal loss (FL) function is introduced to dynamically adjust category weights based on actual sample distribution, enhancing model robustness under extreme class imbalance. The proposed method is validated on a modified IEEE 39-bus system incorporating the Qishao UHVDC line and wind/photovoltaic integration in Northwest China, using 1490 simulation samples under diverse fault scenarios. Results demonstrate that the proposed CWT-ResNet achieves 98.88% accuracy, 94.74% precision, 100% recall, and 97.29% F1-score, outperforming SVM, 1D-CNN, and 1D-ResNet baselines. Under 5 dB noise conditions, the method maintains over 90% accuracy, demonstrating strong noise robustness. Full article

Cooperative exploration of unknown environments in multi-robot systems poses significant challenges, particularly in terms of efficiency and redundancy. Current approaches primarily rely on centralized systems for target point allocation and the construction of 2D grid maps, which often result in overlapping exploration efforts and reduced efficiency. This paper aims to enhance the cooperative behaviors of decentralized multi-robot systems, enabling effective exploration in large-scale and complex scenarios. We propose a decentralized multi-robot cooperative exploration framework that includes: (1) a trajectory-point extraction strategy for sequentially identifying key navigation points, (2) a dynamic convex polygon expansion method for delineating explored regions among robots, and (3) a novel hierarchical frontier selection mechanism to guide robots toward unexplored areas. By integrating these components, our framework enables coordinated exploration through the sharing of information about explored regions. Experimental results demonstrate that our approach reduces exploration time by 61.43% and overall travel distance by 56.14% compared to recent advancements in multi-robot exploration tasks. Full article

This study examines the impact of agribusiness corporations (large-scale agricultural enterprises) and family farms on the sustainable development of agriculture and rural areas in Ukraine, and considers implications for SDG-aligned agri-food value chains that rely on stable access to sustainably produced raw materials. The research applies a multi-criteria decision analysis framework integrating economic, environmental and social indicators at the regional level. Using min–max normalisation, scoring and ranking methods, composite indices of economic sustainability, environmental sustainability, and sustainable rural development were constructed for 20 selected Ukrainian regions, and an integral sustainability index was calculated. Spearman’s rank correlation was applied to identify relationships between sustainability indicators and the structural characteristics of agricultural production. The results reveal pronounced interregional differentiation and an overall predominance of economic over environmental sustainability. Regions with a higher share of family farming demonstrate stronger environmental sustainability and more balanced development patterns, whereas dominance of large-scale enterprises is associated with adverse environmental effects. At the same time, relationships between farm structure and sustainable rural development are weak and not statistically significant, suggesting that social sustainability outcomes depend on more complex and context-dependent mechanisms beyond production scale alone. The findings highlight structural trade-offs between economic efficiency and environmental sustainability and underline the importance of regionally differentiated policy instruments. Strengthening support for family farms is identified as a promising mechanism for improving environmental performance and enhancing upstream conditions for sustainability-oriented sourcing and agri-food value chains. Full article

Multi-agent systems (MASs), with unmanned aerial vehicles (UAVs) as a representative embodiment, have become increasingly vital in time-sensitive disaster response scenarios, where multiple agents must collaborate to execute “observe-and-intervene” emergency tasks and jointly cope with dynamic environmental uncertainties. Existing research on task allocation mostly eliminates uncertainty through deterministic models; the few studies that directly consider uncertainty focus primarily on time uncertainty, overlooking the critical importance of demand uncertainty. To this end, this study accounts for the impact of harsh environmental conditions and incident complexity factors on intervention resource demands. We establish an uncertainty set for these demands and construct a two-stage robust optimization model to solve the coupled multi-agent task allocation problem. Compared with deterministic models, this framework enhances risk resistance while simultaneously reducing the conservatism of decisions. Furthermore, to overcome the computational challenges of large-scale instances, a Learning-Enhanced Column and Constraint Generation (LE-C&CG) algorithm is proposed. Experimental results demonstrate that LE-C&CG converges over an order of magnitude faster than standard Benders and C&CG algorithms, consistently achieving a 0% optimality gap within fractions of a second, making it highly suitable for time-critical emergency applications. Full article

Accurate characterization of pavement responses under real traffic loading is essential for improving pavement design reliability. This study presents SmartPave, a full-scale embedded monitoring system for measuring multilayer pavement responses under heavy vehicle loading. The system integrates embedded multi-sensors to capture stress, strain, temperature, and moisture within pavement layers. Field experiments were conducted under static and moving loading conditions. The results show that peak vertical stresses in the granular base were approximately 1.7–2.0 times higher than those at the subgrade, indicating stress attenuation with depth, while tensile strains at the bottom of the asphalt layer ranged between 200 and 350 µε. Lower vehicle speeds increased load duration and amplified viscoelastic strain responses. These findings demonstrate the capability of the system to provide reliable field data for mechanistic analysis and model calibration. Full article

While deep learning-based visual SLAM (VSLAM) has achieved remarkable localization accuracy, its high computational cost and latency remain critical bottlenecks for real-time deployment. To address these limitations, this paper presents NeuroFusion-SLAM, a novel multi-sensor fusion framework tailored for both efficiency and robustness. By incorporating depthwise separable convolution, the framework cuts down model parameters by approximately 40% and training time by 49% while preserving localization accuracy, thus boosting real-time inference performance and computational efficiency in large-scale environments. Furthermore, a global edge optimization strategy is proposed by integrating sliding window optimization with a factor graph framework, which effectively improves the global consistency of the system. Extensive experiments on the TUM-VI and KITTI-360 datasets demonstrate that our system achieves real-time performance with an average latency of 30.4 ms per frame. It runs 3× faster than ORB-SLAM2 and 4× faster than VINS-Mono, while maintaining good localization accuracy. Full article