Search Results (5,949)

Accurate state estimation is essential for the real-time operation and control of modern distribution systems characterized by high renewable energy penetration, bidirectional power flows, and volatile loads. Conventional model-driven approaches such as the Weighted Least Squares (WLS) exhibit limited robustness under noisy and sparse measurements, while existing data-driven methods often neglect critical physical constraints inherent to power systems. To address these limitations, this paper proposes a physics-constrained Graph Attention Network (GAT) framework for distribution system state estimation (DSSE) that synergistically integrates data-driven learning with physical domain knowledge. The proposed method comprises three key components: (1) a Gaussian Mixture Model (GMM)-based data augmentation strategy that captures the stochastic characteristics of loads and distributed generation to generate synthetic samples consistent with actual operating distributions; (2) a GAT-based feature extractor with topology-aware admittance matrix embedding that effectively learns spatial dependencies and structural relationships among network nodes; and (3) a physics-constrained loss function that incorporates nodal power and voltage limit penalties to enforce operational feasibility. Comprehensive evaluations on the real-world 141-bus test system demonstrate that the proposed method achieves mean absolute error (MAE) reductions of 52.4% and 45.5% for voltage magnitude and angle estimation, respectively, compared to conventional Graph Convolutional Network (GCN)-based approaches. These results validate the superior accuracy, robustness, and adaptability of the proposed framework under challenging measurement conditions. Full article

Financial fraud, as a salient manifestation of corporate governance failure, erodes investor confidence and threatens the long-term sustainability of capital markets. This study aims to develop and validate SFG-2DCNN, a multimodal deep learning framework that adopts a configurational perspective to diagnose financial fraud under class-imbalanced conditions and support sustainable corporate governance. Conventional diagnostic approaches struggle to capture the higher-order interactions within covert fraud patterns due to scarce fraud samples and complex multimodal signals. To overcome these limitations, SFG-2DCNN adopts a systematic two-stage mechanism. First, to ensure a logically consistent data foundation, the framework builds a domain-adaptive generative model (SMOTE-FraudGAN) that enforces joint distribution alignment to fundamentally resolve the issue of economic logic coherence in synthetic samples. Subsequently, the framework pioneers a feature topology mapping strategy that spatializes extracted multimodal covert signals, including non-traditional indicators (e.g., Total Liabilities/Operating Costs) and affective dissonance in managerial narratives, into an ordered two-dimensional matrix, enabling a two-dimensional Convolutional Neural Network (2D-CNN) to efficiently identify potential governance failure patterns through deep spatial fusion. Experiments on Chinese A-share listed firms demonstrate that SFG-2DCNN achieves an F1-score of 0.917 and an AUC of 0.942, significantly outperforming baseline models. By advancing the analytical paradigm from isolated variable assessment to holistic multimodal configurational analysis, this research provides a high-fidelity tool for strengthening sustainable corporate governance and market transparency. Full article

COVID-19 screening is crucial for the early diagnosis and treatment of the disease, with lung ultrasound posing as a cost-effective alternative to other imaging techniques. Given the dependency on medical expertise and experience to accurately identify patterns in ultrasound exams, deep learning techniques have been explored for automatically classifying patients’ conditions. However, the limited availability of public medical databases remains a significant obstacle to the development of more advanced models. To address the data scarcity problem, this study proposes a method that leverages generative adversarial networks (GANs) to generate synthetic lung ultrasound images, which are subsequently used to train frame-based classification models. Two types of GANs are considered: Wasserstein GANs (WGAN) and Pix2Pix. Specific tools are used to show that the synthetic data produced present a distribution close to the original data. The classification models trained with synthetic data achieved a peak accuracy of 96.32% ± 4.17%, significantly outperforming the maximum accuracy of 82.69% ± 10.42% obtained when training only with the original data. Furthermore, the best results are comparable to, and in some cases surpass, those reported in recent related studies. Full article

Pavement condition assessment using computer vision has emerged as an efficient alternative to traditional manual surveys, which are often labor-intensive and time-consuming. Leveraging deep learning, pavement distress such as cracks can be automatically detected, segmented, and quantified from high-resolution images captured by survey vehicles. Although numerous segmentation models have been proposed to generate crack masks, they typically require extensive pixel-level annotations, leading to high labeling costs. To overcome this limitation, this study integrates the Segmentation Anything Model (SAM), which produces accurate segmentation masks from simple bounding box prompts while leveraging its zero-shot capability to generalize to unseen images with minimal retraining. However, since SAM alone is not an end-to-end solution, we incorporate YOLOv8 for automated crack detection, eliminating the need for manual box annotation. Furthermore, the framework applies local refinement techniques to enhance mask precision and employs Optical Character Recognition (OCR) to automatically extract embedded GPS coordinates for geospatial mapping. The proposed framework is empirically validated using open-source pavement images from Yamanashi, demonstrating effective automated detection, classification, quantification, and geospatial mapping of pavement cracks. The results support automated pavement distress mapping onto real-world road networks, facilitating efficient maintenance planning for road agencies. Full article

We experimentally demonstrate an 80 Gbit/s Nyquist-dense wavelength division multiplexed (Nyquist-DWDM) transmission system operating in a simulated atmospheric turbulence channel. The system utilizes eight wavelength-tunable lasers with 100 GHz spacing, modulated by cascaded Mach–Zehnder modulators, to generate phase-locked Nyquist pulse sequences with a 10 GHz repetition rate and a temporal width of 66.7 ps. Each channel is synchronously modulated with a 10 Gbit/s pseudo-random bit sequence (PRBS) and transmitted through controlled weak turbulence conditions generated by a temperature-gradient convection chamber. Experimental measurements reveal that, as the turbulence intensity increases from $C_n^2=1.01\times {10}^{-16}$ to $5.71\times {10}^{-16} {\mathrm{m}}^{-2/3}$, the signal-to-noise ratio (SNR) of the edge channel (C29) and central channel (C33) decreases by approximately 6.5 dB while maintaining stable Nyquist waveform profiles and inter-channel orthogonality. At a forward-error-correction (FEC) threshold of $3.8\times {10}^{-3}$, the minimum receiver sensitivity is −17.66 dBm, corresponding to power penalties below 5 dB relative to the back-to-back condition. The consistent SNR difference (<2 dB) between adjacent channels confirms uniform power distribution and low inter-channel crosstalk under turbulence. These findings verify that Nyquist pulse shaping substantially mitigates phase distortion and scintillation effects, demonstrating the feasibility of high-capacity DWDM free-space optical (FSO) systems with enhanced spectral efficiency and turbulence resilience. The proposed configuration provides a scalable foundation for future multi-wavelength FSO links and hybrid fiber-wireless optical networks. Full article

The progress in metal additive manufacturing (AM) technology has enabled the printing of parts with intricate geometries. Predicting and reducing geometrical deviations (i.e., the difference between the printed part and the design) in metal AM parts remains a challenge. This work explores how changes in laser speed, laser power, and hatch spacing affect geometrical deviations in parts made using laser powder bed fusion (L-PBF) and emphasizes predicting geometrical defects in AM parts. Sliced images obtained from CAD designs and printed parts are utilized to capture the effects of various L-PBF process parameters and to generate a comprehensive data set. Conditional Generative Adversarial Networks (cGANs) are trained to predict images that accurately reflect actual geometrical deviations. In this study, the influence of L-PBF process parameters on geometric deviation is quantified, and the prediction results demonstrate the effectiveness of the proposed cGAN-based method in improving the predictability of geometric deviations in parts fabricated via L-PBF. This approach is expected to facilitate early correction of geometrical deviations during the L-PBF process. Full article

With the rapid growth and increasing sophistication of malicious software (malware), traditional detection methods face significant challenges in addressing emerging threats. Machine learning-based detection approaches rely on manual feature engineering, making it difficult for them to adapt to diverse attack patterns. In contrast, while deep learning methods can automatically extract features, they remain vulnerable to data imbalance and sample scarcity, which lead to poor detection performance for minority-class samples. To address these issues, this study proposes a semantic data augmentation approach based on a Conditional Wasserstein Generative Adversarial Network with Gradient Penalty (CWGAN-GP), and designs a malware detection model that combines a Text Convolutional Neural Network (TextCNN) with a Transformer Encoder, termed Mal-CGP-TTN. The proposed model establishes a symmetry between local feature extraction and global semantic representation, where the convolutional and attention-based components complement each other to achieve balanced learning. First, the proposed method enriches the semantic diversity of the training data by generating high-quality synthetic samples. Then, it leverages multi-scale convolution and self-attention mechanisms to extract both local and global features of malicious behaviors, thereby enabling hierarchical semantic modeling and accurate classification of malicious activities. Experimental results on two public datasets demonstrate that the proposed method outperforms traditional machine learning and mainstream deep learning models in terms of accuracy, precision, and F1-score. Notably, it achieves substantial improvements in detecting minority-class samples. Full article

Timely and accurate fault diagnosis in power transmission systems is critical to ensuring grid stability, operational safety, and minimal service disruption. This study presents a unified deep learning framework that simultaneously performs fault identification, fault type classification, and fault location estimation using a multi-task learning (MTL) approach. Using the IEEE 39–Bus network, a comprehensive data set was generated under various load conditions, fault types, resistances, and location scenarios to reflect real-world variability. The proposed model integrates a shared representation layer and task-specific output heads, enhanced with an attention mechanism to dynamically prioritize salient input features. To further optimize the model architecture, Optuna was employed for hyperparameter tuning, enabling systematic exploration of design parameters such as neuron counts, dropout rates, activation functions, and learning rates. Experimental results demonstrate that the proposed Optimized Multi-Task Learning Attention Network (MTL-AttentionNet) achieves high accuracy across all three tasks, outperforming traditional models such as Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP), which require separate training for each task. The attention mechanism contributes to both interpretability and robustness, while the MTL design reduces computational redundancy. Overall, the proposed framework provides a unified and efficient solution for real-time fault diagnosis on the IEEE 39–bus transmission system, with promising implications for intelligent substation automation and smart grid resilience. Full article

The present work focuses on the inverse identification of loads acting on wing-like geometries, through strain measurements. These loads are considered quasi-static and considered acting at discrete stations across the span of the wing. A demonstrative case study is investigated, focusing on a complex composite structure, an Unmanned Aerial Vehicle (UAV) fin. To achieve this, a high-fidelity Finite Element model is developed, with “virtual” strain data generated through simulations. The technical challenge of optimal sensor placement is addressed with D-optimal designs, which promise sensor networks (sensor locations and strain components) that produce minimal uncertainty propagation from strain measurements to load estimates. These designs are obtained through the implementation of Genetic Algorithms. Different sensor networks with an increasing number of sensors are evaluated in order to identify a further reduction in epistemic uncertainty posed by the problem’s ill-conditioned nature. Full article

This article presents a methodology for real-time forecasting of a fire-extinguishing agent jet trajectory from a robotic fire monitor under wind influence, which can significantly displace the impact area position and complicate targeting. The proposed methodology is designed for controlling firefighting robots in conditions where visual monitoring of the impact area is impeded by factors such as: obscuration of the fire-extinguishing agent flow by smoke, low visibility of its fragmented particles against the background environment, and long-range jet discharge. Trajectory forecasting is implemented using a neural network model. The training and verification of this model are performed with datasets constructed from the results of numerical simulations of fire-extinguishing agent motion under wind influence, based on Computational Fluid Dynamics (CFD) methods. Experimentally obtained data are used for the validation of the trained neural network model and the selected CFD models. The paper describes the methodology for conducting full-scale tests of fire monitors; a photogrammetric algorithm for generating validation datasets from the test results; an algorithm for calculating target characteristics, which describe the jet trajectory and are consistent with experimental data, used for forming training and verification datasets based on simulation; and a procedure for selecting Computational Fluid Dynamics models and their parameters to ensure the required accuracy. The article also presents the results of an experimental evaluation of the developed methodology’s effectiveness for real-time prediction of the water jet trajectory from a fire monitor under various control and disturbance parameters. Full article

Generative adversarial networks (GANs) can rapidly predict urban environmental performance. However, most existing studies focus on a single target and lack cross-performance comparisons under unified conditions. Under unified urban-form inputs and training settings, this study employs the conditional adversarial model pix2pix to predict four targets—the Universal Thermal Climate Index (UTCI), annual global solar radiation (Rad), sunshine duration (SolarH), and near-surface wind speed (Wind)—and establishes a closed-loop evaluation framework spanning pixel, structural/region-level, cross-task synergy, complexity, and efficiency. The results show that (1) the overall ranking in accuracy and structural consistency is SolarH ≈ Rad > UTCI > Wind; (2) per-epoch times are similar, whereas convergence epochs differ markedly, indicating that total time is primarily governed by convergence difficulty; (3) structurally, Rad/SolarH perform better on hot-region overlap and edge alignment, whereas Wind exhibits larger errors at corners and canyons; (4) in terms of learnability, texture variation explains errors far better than edge count; and (5) cross-task synergy is higher in low-value regions than in high-value regions, with Wind clearly decoupled from the other targets. The distinctive contribution lies in a unified, reproducible evaluation framework, together with learnability mechanisms and applicability bounds, providing fast and reliable evidence for performance-oriented planning and design. Full article

Accurately predicting the remaining useful life (RUL) of lithium-ion batteries is critical for anticipating battery failure and enabling effective health management. However, existing RUL prediction methods often suffer from several limitations, including the need for large volumes of training data, significant differences across datasets, and insufficient accuracy in long-term forecasting, which hinder their applicability in real world scenarios. To address these challenges, this paper proposes a hybrid model that integrates transfer learning (TL) and particle filtering (PF) with the Mogrifier LSTM (MLSTM) network. Specifically, the model first employs a transfer learning-based Mogrifier LSTM (TL-MLSTM) to perform long-term prediction of battery capacity, thereby enhancing the model’s generalization ability to accommodate RUL prediction under varying operating conditions. Subsequently, the capacity predictions generated by TL-MLSTM are used as observations in the PF algorithm, which iteratively updates the battery state parameters and refines the capacity predictions, thereby further improving accuracy. The proposed model is validated using publicly available datasets comprising multiple types of batteries under various operational conditions. Experimental results demonstrate that the model achieves an average RMSE of 0.0199, MAPE of 0.5803%, MAE of 0.0167 and APE of 11 cycles across multiple test groups. Compared with standalone models or purely data-driven approaches, the proposed method exhibits significant advantages in robustness and accuracy for long-term capacity degradation prediction. Full article

Accurate prediction of air pollutant concentrations, particularly fine particulate matter (PM_2.5), is essential for controlling and preventing heavy pollution incidents by providing early warnings of harmful substances in the atmosphere. This study proposes a novel spatiotemporal model for PM_2.5 concentration prediction based on a Conditional Wasserstein Generative Adversarial Network with Gradient Penalty (CWGAN-GP). The framework incorporates three key design components: First, the generator employs an Inception-style Convolutional Long Short-Term Memory (ConvLSTM) network, integrating parallel multi-scale convolutions and hierarchical normalization. This design enhances multi-scale spatiotemporal feature extraction while effectively suppressing boundary artifacts via a map-masking layer. Second, the discriminator adopts an architecturally enhanced U-Net, incorporating spectral normalization and shallow instance normalization. Feature-guided masked skip connections are introduced, and the output is designed as a raw score map to mitigate premature saturation during training. Third, a composite loss function is utilized, combining adversarial loss, feature-matching loss, and inter-frame spatiotemporal smoothness. A sliding-window conditioning mechanism is also implemented, leveraging multi-level features from the discriminator for joint spatiotemporal optimization. Experiments conducted on multi-source gridded data from Dongguan demonstrate that the model achieves a 12 h prediction performance with a Root Mean Square Error (RMSE) of 4.61 μg/m³, a Mean Absolute Error (MAE) of 6.42 μg/m³, and a Coefficient of Determination (R²) of 0.80. The model significantly alleviates performance degradation in long-term predictions when the forecast horizon is extended from 3 to 12 h, the RMSE increases by only 1.84 μg/m³, and regional deviations remain within ±3 μg/m³. These results indicate strong capabilities in spatial topology reconstruction and robustness against concentration anomalies, highlighting the model’s potential for hyperlocal air quality early warning. It should be noted that the empirical validation is limited to the specific environmental conditions of Dongguan, and the model’s generalizability to other geographical and climatic settings requires further investigation. Full article

The design of sustainable hydrogel materials with tunable mechanical and thermal properties is essential for emerging applications in flexible and wearable electronics. In this study, hydrogels based on natural gums such as Guar, Tara, and Xanthan and their composites with Cellulose Citrate were developed through a mild physical crosslinking process, ensuring environmental compatibility and structural integrity. The effect of cellulose citrate pretreatment under different alkaline conditions (0.04%, 5%, and 10% NaOH) was systematically investigated using Fourier Transform Infrared Spectroscopy (FT-IR), Thermogravimetric Analysis (TGA), and dynamic rheology. Overall, the results show that the composites exhibit different properties of the hydrogel networks compared to the pure hydrogel gums, strongly depending on the alkaline treatment. In all composite hydrogels, a significant increase in the number of interacting rheological units occurs, though the strength of the interactions decreases in Guar and Tara composites, which exhibit partial structural destabilization. In contrast, Xanthan–Cellulose Citrate hydrogels display enhanced strong gel character, and crosslinking density. These improvements reflect stronger intermolecular associations and a more compact polymer network, due to the favorable H-bonding and ionic interactions among Xanthan, Cellulose and Citrate mediated by water and sodium ions. Overall, the results demonstrate that Xanthan–Cellulose Citrate systems represent a new class of eco-friendly, mechanically robust hydrogels with controllable viscoelastic and thermal responses, features highly relevant for the next generation of flexible, self-supporting, and responsive soft materials suitable for wearable and stretchable electronic devices. Full article

The development of electric quarry transport puts a significant strain on local power grids, leading to sharp peaks in consumption and degradation of power quality. Existing methods of peak smoothing, such as generation control, virtual power plants, or intelligent load management, have limited efficiency under the conditions of stochastic and high-power load profiles of industrial charging stations. A new strategy for direct charge and discharge management of a system for integrated battery energy storage (IBES) is based on dynamic iterative adjustment of load boundaries. The mathematical apparatus of the method includes the formalization of an optimization problem with constraints, which is solved using a nonlinear iterative filter with feedback. The key elements are adaptive algorithms that minimize the network power dispersion functionality (i.e., the variance of $P_{grid}\left(t\right)$ over the considered time interval) while respecting the constraints on the state of charge (SOC) and battery power. Numerical simulations and experimental studies demonstrate a 15 to 30% reduction in power dispersion compared to traditional constant power control methods. The results confirm the effectiveness of the proposed approach for optimizing energy consumption and increasing the stability of local power grids of quarry enterprises. Full article