Search Results (739)

Reservoir-induced landslides threaten infrastructures and downstream communities, making continuous deformation monitoring vital. Time-series InSAR, notably the SBAS algorithm, provides high-precision surface-displacement mapping but suffers from voids due to layover/shadow effects and temporal decorrelation. Existing deep-learning approaches often operate on fixed-size patches or ignore irregular spatio-temporal dependencies, limiting their ability to recover missing pixels. With this objective, a hybrid spatio-temporal Graph Attention (ST-GAT) framework was developed and trained on SBAS-InSAR values using 24 influential features. A unified spatio-temporal graph is constructed, where each node represents a pixel at a specific acquisition time. The nodes are connected via inverse distance spatial edges to their K-nearest neighbors, and they have bidirectional temporal edges to themselves in adjacent acquisitions. The two spatial GAT layers capture terrain-driven influences, while the two temporal GAT layers model annual deformation trends. A compact MLP with per-map bias converts the fused node embeddings into normalized LOS estimates. The SBAS-InSAR results reveal LOS deformation, with 48% of missing pixels and 20% located near the Dasu dam. ST D-GAT reconstructed fully continuous spatio-temporal displacement fields, filling voids at critical sites. The model was validated and achieved an overall R² (0.907), ρ (0.947), per-map R² ≥ 0.807 with RMSE ≤ 9.99, and a ROC-AUC of 0.91. It also outperformed the six compared baseline models (IDW, KNN, RF, XGBoost, MLP, simple-NN) in both RMSE and R². By combining observed LOS values with 24 covariates in the proposed model, it delivers physically consistent gap-filling and enables continuous, high-resolution landslide monitoring in radar-challenged mountainous terrain. Full article

This study presents the design, fabrication, and performance assessment of a novel, small-scale (30–70 W), hybrid ocean energy system that captures energy from wave-induced heave motion using a point-absorber buoy and from ocean currents via a vertical axis water turbine (VAWT). Key innovations include a custom designed and built dual-rotor generator that accepts independent mechanical input from both subsystems without requiring complex mechanical coupling and a bi-directional mechanical motion rectifier with an overdrive. Numerical simulations using ANSYS AQWA (2024R2) and QBLADE(2.0.4) guided the design optimization of the buoy and turbine, respectively. Wave resource assessment for the Khobar coastline, Saudi Arabia, was conducted using both historical data and field measurements. The prototype was designed and built using readily available 3D-printed components, ensuring cost-effective construction. This mechanically simple system was tested in both laboratory and outdoor conditions. Results showed reliable operation and stable power generation under simultaneous wave and current input. The performance is comparable to that of existing hybrid ocean wave–current energy converters that employ more complex flywheel or dual degree-of-freedom systems. This work provides a validated pathway for low-cost, compact, and modular hybrid ocean energy systems suited for remote coastal applications or distributed marine sensing platforms. Full article

Matrix converters (MC) offer a compact, bidirectional solution for power conversion; however, achieving precise reactive power control at the input terminals remains challenging under varying operating conditions. This paper presents an enhanced Singular Value Decomposition modulation technique (e-SVD) as a solution tailored to optimize reactive power management on the MC input side, enabling both active and reactive power control regardless of the power factor. The proposed method achieves input reactive power control based on a reactive power gain, a quantity derived from the apparent output power and defined by a mathematical expression involving electrical parameters and control variables. Experimental tests carried out on a low-power MC prototype to validate the proposal show that the measured reactive power gain closely aligns with theoretical predictions from the mathematical expressions. Overall, the proposed e-SVD modulation technique lays the foundation for more reliable reactive power regulation in applications such as microgrids and distributed generation systems, contributing to the development of smarter and more resilient energy infrastructures. Full article

The transition to electric mobility has significantly increased the demand for lithium-ion batteries, raising concerns about their end-of-life management. Therefore, this study presents the design, development and first implementation steps of a stationary energy storage system utilizing second-life electric vehicle (EV) batteries. These batteries, no longer suitable for traction applications due to a reduced state of health (SoH) below 80%, retain sufficient capacity for less demanding stationary applications. The proposed system is designed to be flexible and scalable, serving both research and commercial purposes. Key challenges include heterogeneous battery characteristics, safety considerations due to increased internal resistance and battery aging, and the need for flexible power electronics. An optimized dual active bridge (DAB) converter topology is introduced to connect several batteries in parallel and to ensure efficient bidirectional power flow over a wide voltage range. A first prototype, rated at 50 $\mathrm{k}$$\mathrm{W}$, has been built and tested in the laboratory. This study contributes to sustainable energy storage solutions by extending battery life cycles, reducing waste, and promoting economic viability for industrial partners. Full article

The interlinking converter, an important device in a hybrid AC-DC microgrid, undertakes the task of power distribution between the AC sub-microgrid and DC sub-microgrid. To address the limitations of traditional bidirectional droop control in islanding mode, particularly the lack of consideration for regulation priority between AC frequency and DC voltage, this paper proposes an adaptive bidirectional droop control strategy. By introducing an adaptive weight coefficient based on normalized AC frequency and DC voltage, the strategy prioritizes regulating larger deviations in AC frequency or DC voltage. Interlinking converter action thresholds are set to avoid unnecessary frequent starts and stops. Finally, a hybrid AC-DC microgrid system in islanding mode is established in the Matlab/Simulink R2020a simulation platform to verify the effectiveness of the proposed control strategy. Full article

To address the high false alarm rate of intrusion detection systems based on distributed acoustic sensing (DAS) for power cables in complex underground environments, an innovative GRT-Transformer multimodal deep learning model is proposed. The core of this model lies in its distinctive three-branch parallel collaborative architecture: two branches employ Gramian Angular Summation Field (GASF) and Recursive Pattern (RP) algorithms to convert one-dimensional intrusion waveforms into two-dimensional images, thereby capturing rich spatial patterns and dynamic characteristics and the third branch utilizes a Gated Recurrent Unit (GRU) algorithm to directly focus on the temporal evolution features of the waveform; additionally, a Transformer component is integrated to capture the overall trend and global dependencies of the signals. Ultimately, the terminal employs a Bidirectional Long Short-Term Memory (BiLSTM) network to perform a deep fusion of the multidimensional features extracted from the three branches, enabling a comprehensive understanding of the bidirectional temporal dependencies within the data. Experimental validation demonstrates that the GRT-Transformer achieves an average recognition accuracy of 97.3% across three typical intrusion events—illegal tapping, mechanical operations, and vehicle passage—significantly reducing false alarms, surpassing traditional methods, and exhibiting strong practical potential in complex real-world scenarios. Full article

Distributed photovoltaic storage charging piles in remote rural areas can solve the problem of charging difficulties for new energy vehicles in the countryside, but these storage charging piles contain a large number of power electronic devices, and there is a risk of resonance in the system under weak grid conditions. Firstly, the topology of a photovoltaic storage charging pile is introduced, including a bidirectional DC/DC converter, unidirectional DC/DC converter, and single-phase grid-connected inverter. Then, the maximum power tracking control strategy based on improved conductance micro-increment is derived for a photovoltaic power generation system, and a constant voltage and constant current charge–discharge control strategy is derived for energy storage equipment. Additionally, a segmented reflective charging control strategy is introduced for charging piles, and the quasi-PR controller is introduced for single-phase grid-connected inverters. In addition, an improved second-order general integrator phase-locked loop (SOGI-PLL) based on feed-forward of the grid current is derived. Finally, a simulation model is built to verify the performance of the solar–storage charging pile and lay the technical groundwork for future integrated control strategies. Full article

The address is a key element in the construction of smart cities. When receiving reports from citizens, public security officers need to quickly and accurately locate a crime scene based on the address provided by the reporter. The address from the reporter may be a standard address or it may be a point of interest, abbreviation, or common name. The difficulty in converting the address into a standard address can be solved through the analysis of address elements and address matching. We developed a bidirectional encoder representations from transformers (BERT)-based address feature resolution method and an address-matching algorithm. On this basis, a police force address-matching system for City A was designed and implemented. A Web application system was also developed based on the address database of City A. The developed address resolution and matching method with the database maintenance module successfully matched the reported address to the standard one. Full article

This paper introduces an enhanced bi-directional full-bridge resonant converter designed for Vehicle-to-Grid (V2G) systems. A key innovation lies in the incorporation of an auxiliary LC resonant circuit connected via a tertiary transformer winding. This circuit dynamically modifies the magnetizing inductance based on operating frequency, enabling soft-switching across all primary switches, specifically, Zero-Voltage Switching (ZVS) at turn-on and near Zero-Current Switching (ZCS) at turn-off across the entire load spectrum. Additionally, the converter supports both Constant Current (CC) and Constant Voltage (CV) charging modes at distinct, fixed operating frequencies, thus avoiding wide frequency variations. A 3.3 kW prototype developed for onboard electric vehicle charging applications demonstrates the effectiveness of the proposed topology. Experimental results confirm high efficiency in both charging and discharging operations, achieving up to 98.13% efficiency in charge mode and 98% in discharge mode. Full article

As electric vehicles (EVs) continue to advance toward widespread adoption, innovations in power electronics are playing a pivotal role in improving efficiency, performance, and sustainability. This review presents recent progress in bidirectional converters and regenerative braking systems (RBSs), highlighting their contributions to energy recovery, battery longevity, and vehicle-to-grid integration. Bidirectional converters support two-way energy flow, enabling efficient regenerative braking and advanced charging capabilities. The integration of wide-bandgap semiconductors, such as silicon carbide and gallium nitride, further enhances power density and thermal performance. The paper evaluates various converter topologies, including single-stage and multi-stage architectures, and assesses their suitability for high-voltage EV platforms. Intelligent control strategies, including fuzzy logic, neural networks, and sliding mode control, are discussed for optimizing braking force and maximizing energy recuperation. In addition, the paper explores the influence of regenerative braking on battery degradation and presents hybrid energy storage systems and AI-based methods as mitigation strategies. Special emphasis is placed on the integration of RBSs in advanced electric vehicle platforms, including autonomous systems. The review concludes by identifying current challenges, emerging trends, and key design considerations to inform future research and practical implementation in electric vehicle energy systems. Full article

The detection of aerial imagery captured by Unmanned Aerial Vehicles (UAVs) is widely employed across various domains, including engineering construction, traffic regulation, and precision agriculture. However, aerial images are typically characterized by numerous small targets, significant occlusion issues, and densely clustered targets, rendering traditional detection algorithms largely ineffective for such imagery. This work proposes a small target detection algorithm, SR-YOLO. It is specifically tailored to address these challenges in UAV-captured aerial images. First, the Space-to-Depth layer and Receptive Field Attention Convolution are combined, and the SR-Conv module is designed to replace the Conv module within the original backbone network. This hybrid module extracts more fine-grained information about small target features by converting image spatial information into depth information and the attention of the network to targets of different scales. Second, a small target detection layer and a bidirectional feature pyramid network mechanism are introduced to enhance the neck network, thereby strengthening the feature extraction and fusion capabilities for small targets. Finally, the model’s detection performance for small targets is improved by utilizing the Normalized Wasserstein Distance loss function to optimize the Complete Intersection over Union loss function. Empirical results demonstrate that the SR-YOLO algorithm significantly enhances the precision of small target detection in UAV aerial images. Ablation experiments and comparative experiments are conducted on the VisDrone2019 and RSOD datasets. Compared to the baseline algorithm YOLOv8s, our SR-YOLO algorithm has improved mAP@0.5 by 6.3% and 3.5% and mAP@0.5:0.95 by 3.8% and 2.3% on the datasets VisDrone2019 and RSOD, respectively. It also achieves superior detection results compared to other mainstream target detection methods. Full article

Doubly Fed Induction Generator (DFIG)-based Wind Energy Systems (WESs) have become increasingly prominent in the global energy sector, owing to their superior efficiency and operational flexibility. Nevertheless, DFIGs are notably vulnerable to fluctuations in the grid, which can result in power quality issues—including voltage swells, sags, harmonic distortion, and flicker—while also posing difficulties in complying with Fault Ride-Through (FRT) standards established by grid regulations. To address the previously mentioned challenges, this paper develops an integrated approach utilizing a Dynamic Voltage Restorer (DVR) in conjunction with a Lithium-ion storage system. The DVR is coupled in series with the WES terminal, while the storage system is coupled in parallel with the DC link of the DFIG through a DC/DC converter, enabling rapid voltage compensation and bidirectional energy exchange. Simulation results for a 2 MW WES employing DFIG modeled in MATLAB/Simulink demonstrate the efficacy of the proposed system. The approach maintains terminal voltage stability, reduces Total Harmonic Distortion (THD) to below 0.73% during voltage sags and below 0.42% during swells, and limits DC-link voltage oscillations within permissible limits. The system also successfully mitigates voltage flicker (THD reduced to 0.41%) and harmonics (THD reduced to 0.4%), ensuring compliance with IEEE Standard 519. These results highlight the proposed system’s ability to enhance both PQ and FRT capabilities, ensuring uninterrupted wind power generation under various grid disturbances. Full article

Polymers characterize a different and important class of materials through various industries, all with unique functional properties and structural attributes. Conventional models of polymer classification depend greatly on labor-intensive methods liable to human error and subjectivity. Hence, a continually growing requirement for new polymers with greater properties is a deep understanding and exploration of the chemical space. Hence, data-driven methods for polymers are developing and able to deal with unique challenges originating from the outstanding physical and chemical range of polymers at smaller and larger scales. Recently, Deep Learning (DL) models have considerably transformed material science by allowing for the automatic study and classification of composite polymers. In this paper, a novel optimization algorithm with a DL-Based Neural Networks for Data-Driven Polymer Classification (OADLNN-DDPC) model is proposed. The main intention of the OADLNN-DDPC model is to improve the classification model for data-driven polymers using state-of-the-art optimization algorithms. The data normalization stage is initially executed via Z-score normalization to convert input data into a beneficial format. In addition, the proposed OADLNN-DDPC model implements the bald eagle search (BES) model for feature selection to detect and retain the most appropriate features. For the polymer classification process, the bidirectional gated recurrent unit (BiGRU) technique is employed. Lastly, the zebra optimizer algorithm (ZOA) is implemented for the tuning process. Extensive experiments conducted on a polymers dataset with 19,500 records and 2048 features demonstrated that OADLNN-DDPC achieves an accuracy of 98.58%, outperforming existing models, such as LSTM (83.37%), PLS-DA (88.18%), and K-NN (98.36%). The simulation process of the OADLNN-DDPC model is performed under the polymer classification dataset. The experimental analysis specified that the OADLNN-DDPC model demonstrated improvement over another existing model. Full article

Due to the high demand for fuel efficiency, electric vehicles have come into the picture, as they only use batteries to power the vehicle. This requires constant charging of the batteries at charging stations, which are costly and impractical to install. But it is possible to install charging stations by making use of photovoltaic (PV) cells and demagnetization currents to self-charge batteries under stand-still conditions. The design of a bidirectional converter with asymmetrical half-bridge converter based on a switched reluctance motor (SRM) drive, using PV for electric vehicles, is implemented in this paper. It consists of developing a control unit (GCU), Li-ion battery pack, and photovoltaic (PV) solar cells that are integrated with a bidirectional converter and asymmetrical half-bridge converter (AHBC) to provide power to the SRM drive. The solar-assisted SRM drive can be operated in either the motoring mode or charging mode. In the motoring-mode GCU, the battery or PV energy can be used in any combination to power the SRM. In the charging-mode PV, the GCU and AC grids are used to charge the battery under stand-still conditions. This work helps in the self-charging of batteries using either the GCU or PV cells, as well as aids in the improvement in the performance characteristics. Also, this work compares the performance metrics for the proposed system and conventional system. The performance of the drive system using PV cells/GCU is evaluated and verified through MatLab/Simulink and experimental results. Full article

The dual-active-bridge (DAB) converter has emerged as a promising topology for renewable energy applications and microgrid systems due to its high power density and bidirectional energy-transfer capability. Enhancing the overall efficiency and reliability of DAB converters requires the simultaneous realization of zero-voltage switching (ZVS) across all switches and the minimization of current stress over wide load and voltage ranges—two objectives that are often in conflict. Conventional modulation strategies with limited degrees of freedom fail to meet these dual goals effectively. To address this challenge, this paper introduces an enhanced integrated optimization strategy based on triple phase shift (EIOS-TPS). This approach formulates the power transmission requirement as an equality constraint and incorporates ZVS and mode boundary conditions as inequalities, resulting in a comprehensive optimization framework. Optimal phase-shift parameters are obtained using the Karush–Kuhn–Tucker (KKT) conditions. To mitigate zero-current switching (ZCS) under a light load and achieve full-range ZVS with reduced current stress, a modulation factor λ is introduced, enabling a globally optimized control trajectory. An experimental 1176 W prototype is developed to validate the proposed method, which achieves full-range ZVS while maintaining low current stress. In the low-power region, it improves efficiency by up to 2.2% in buck mode and 2.0% in boost mode compared with traditional control strategies, reaching a peak efficiency of 96.5%. Full article