Search Results (210)

To address the issues of efficiency and robustness in UAV trajectory planning under complex environments, this paper proposes a Graph Multi-Head Attention Policy Optimization Network (G-MAPONet) algorithm that integrates Graph Attention (GAT), Multi-Head Attention (MHA), and Group Relative Policy Optimization (GRPO). The algorithm adopts a three-layer architecture of “GAT layer for local feature perception–MHA for global semantic reasoning–GRPO for policy optimization”, comprehensively achieving the goals of dynamic graph convolution quantization and global adaptive parallel decoupled dynamic strategy adjustment. Comparative experiments in multi-dimensional spatial environments demonstrate that the Gat_Mha combined mechanism exhibits significant superiority compared to single attention mechanisms, which verifies the efficient representation capability of the dual-layer hybrid attention mechanism in capturing environmental features. Additionally, ablation experiments integrating Gat, Mha, and GRPO algorithms confirm that the dual-layer fusion mechanism of Gat and Mha yields better improvement effects. Finally, comparisons with traditional reinforcement learning algorithms across multiple performance metrics show that the G-MAPONet algorithm reduces the number of convergence episodes (NCE) by an average of more than 19.14%, increases the average reward (AR) by over 16.20%, and successfully completes all dynamic path planning (PPTC) tasks; meanwhile, the algorithm’s reward values and obstacle avoidance success rate are significantly higher than those of other algorithms. Compared with the baseline APF algorithm, its reward value is improved by 8.66%, and the obstacle avoidance repetition rate is also enhanced, which further verifies the effectiveness of the improved G-MAPONet algorithm. In summary, through the dual-layer complementary mode of GAT and MHA, the G-MAPONet algorithm overcomes the bottlenecks of traditional dynamic environment modeling and multi-scale optimization, enhances the decision-making capability of UAVs in unstructured environments, and provides a new technical solution for trajectory planning in intelligent logistics and distribution. Full article

Hybrid Gas–Magnetic Bearings (HGMBs) are an emerging technology ready to completely change high-speed oil-free rotor support in aerospace electric motors. Because HGMBs combine the stiffness and load capacity of gas bearings with the active control of magnetic bearings, enabling oil-free, contactless rotor support from zero to ultra-high speeds. They offer more load capacity of standalone magnetic bearings while maintaining full levitation across the entire speed range. Dual-mode operation, magnetic at low speeds and gas film at high speeds, minimizes control power and thermal losses, making HGMBs ideal for high-speed aerospace systems such as cryogenic turbopumps, electric propulsion units, and hydrogen compressors. While not universally optimal, HGMBs excel where extreme speed, high load, and stringent efficiency requirements converge. Advances in modeling, control, and manufacturing are expected to accelerate their adoption, marking a shift toward hybrid electromagnetic–aerodynamic rotor support for next-generation aerospace propulsion. This review provides a thorough overview of emerging HGMBs, emphasizing their design principles, performance metrics, application case studies, and comparative advantages over conventional gas or magnetic bearings. We include both a historical perspective and the latest developments, supported by technical data, experimental results, and insights from recent literature. We also present a comparative discussion including future research directions for HGMBs in aerospace electrical machine applications. Full article

Accurate and generalizable prediction of infectious disease incidence is essential for proactive public health response. This study proposes a novel hybrid VLGA-Transformer model to address this challenge, validated through tuberculosis (TB) and hepatitis B case studies. Utilizing monthly TB data from Zhejiang Province (2013–2023), raw sequences were first decomposed via Variational Mode Decomposition (VMD) to extract intrinsic temporal patterns. To overcome Transformer parameter optimization difficulties, we innovatively integrated the Lorenz attractor into a Genetic Algorithm (GA), creating a Lorenz-attractor-enhanced GA (LGA) that dynamically balances exploration and exploitation. The resulting VLGA-Transformer framework demonstrated superior performance, achieving R² values of 0.96 for TB and 0.93 for hepatitis B prediction, significantly outperforming benchmark models in both accuracy and stability. When tested on hepatitis B data, the model confirmed its robust cross-disease generalizability. These findings highlight the framework’s dual strengths—high-precision forecasting and robust generalization—providing actionable insights for public health authorities to optimize resource allocation and intervention strategies, thereby advancing data-driven infectious disease control systems. Full article

Battery energy storage systems can mitigate power fluctuations and enhance system reliability; however, cell-to-cell inconsistencies and aging in large-capacity battery packs can lead to imbalance. To address the limitations of passive balancing, which suffers from high energy loss and low efficiency, this work proposes a high-current active balancing system based on a single-input multiple-output (SIMO) topology. The system enables energy transfer through a full-bridge converter and transformer, supporting series discharge and selective charging of lithium iron phosphate (LFP) cells. To optimize system performance, a small-signal model was established, and corresponding control strategies were designed: the primary-side inverter employs quasi-open-loop control, while the secondary-side charging modules use a voltage–current dual-loop control. The effectiveness of the model and control strategies was validated via QSPICE simulations. Furthermore, a hybrid active–passive balancing strategy based on a voltage-difference threshold was proposed, allowing for real-time dynamic adjustment of the operating mode according to individual cell voltages. Experimental results on a large-capacity LFP battery demonstrate that the system achieves fast balancing with high accuracy, maintaining cell voltage differences within 30 mV. This provides a practical and effective solution for maintaining cell consistency in electric vehicles and grid-scale energy storage systems. Full article

To address the challenges in identifying effective fault features and achieving sufficient diagnostic accuracy and robustness in variable-speed printing press bearings, where complex mixed-condition vibration signals exhibit non-stationarity, strong nonlinearity, ambiguous time-frequency characteristics, and overlapping fault features across multiple operating conditions, this paper proposes an adaptive optimization signal decomposition method combined with dual-modal time-series and image deep feature fusion for variable-speed multi-condition bearing fault diagnosis. First, to overcome the strong parameter dependency and significant noise interference of traditional adaptive decomposition algorithms, the Crested Porcupine Optimization Algorithm is introduced to adaptively search for the optimal noise amplitude and integration count of ICEEMDAN for effective signal decomposition. IMF components are then screened and reorganized based on correlation coefficients and variance contribution rates to enhance fault-sensitive information. Second, multidimensional time-domain features are extracted in parallel to construct time-frequency images, forming time-sequence-image bimodal inputs that enhance fault representation across different dimensions. Finally, a dual-branch deep learning model is developed: the time-sequence branch employs gated recurrent units to capture feature evolution trends, while the image branch utilizes SE-ResNet18 with embedded channel attention mechanisms to extract deep spatial features. Multimodal feature fusion enables classification recognition. Validation using a bearing self-diagnosis dataset from variable-speed hybrid operation and the publicly available Ottawa variable-speed bearing dataset demonstrates that this method achieves high-accuracy fault identification and strong generalization capabilities across diverse variable-speed hybrid operating conditions. Full article

Accurate prediction of photovoltaic power generation is a pivotal factor for enhancing the operational efficiency of electrical grids and facilitating the stable integration of solar energy. This study introduces a holistic forecasting framework that achieves seamless integration of dual-stage decomposition, deep learning architectures, and an advanced metaheuristic algorithm, thereby significantly improving the prediction precision of PV power generation. Initially, the raw PV power sequences are processed using Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) to capture multi-scale temporal characteristics. The derived components are subsequently categorized into high-, medium-, and low-frequency groups through K-means clustering to manage complexity. To address residual noise and non-stationary behaviors, the high-frequency constituents are further decomposed via Variational Mode Decomposition (VMD). The refined subsequences are then input into a TCN_BiGRU_Attention network, which employs temporal convolutional operations for hierarchical feature extraction, bidirectional gated recurrent units to model temporal correlations, and a multi-head attention mechanism to prioritize influential time steps. For hyperparameter optimization of the forecasting model, an Improved Crested Porcupine Optimizer (ICPO) is developed, integrating Chebyshev chaotic mapping for initialization, a triangular wandering strategy for local search, and Lévy flight to strengthen global exploration and accelerate convergence. Validation on real-world PV datasets indicates that the proposed model attains a Mean Squared Error (MSE) of 0.3456, Root Mean Squared Error (RMSE) of 0.5879, Mean Absolute Error (MAE) of 0.3396, and a determination coefficient (R²) of 99.59%, surpassing all benchmark models by a significant margin. This research empirically demonstrates the efficacy of the dual decomposition methodology coupled with the optimized hybrid deep learning network in elevating both the accuracy and stability of predictions, thereby offering a reliable and stable forecasting framework for PV power systems. Full article

This paper presents a novel temperature compensation approach for dual-axis Micro–Electro–Mechanical System (MEMS) accelerometers, integrating Adaptive Mode Decomposition (AMD) with Grey Wolf Optimization (GWO) and Hybrid Convolutional–Recurrent Temporal Network (HCR-TN). The proposed method aims to address temperature-induced bias drift, which significantly affects accelerometer performance. Experiments were conducted across a temperature range from −40 °C to +60 °C to evaluate the effectiveness of the compensation algorithm. The results show considerable improvements in bias stability, with the compensation method successfully reducing temperature-induced drift across both axes. Additionally, the algorithm was tested under realistic conditions, including noise and mechanical disturbances, demonstrating its robustness in practical applications. These findings highlight the potential of the proposed method for enhancing the reliability and accuracy of MEMS accelerometers in real-world sensing environments. Full article

Electric vehicles (EVs) are experiencing rapid global adoption driven by environmental concerns and fuel security. This article presents a new dual-source converter based on a hybrid modular multilevel configuration (DCHMMC) designed for optimal cell utilisation in EV battery systems. Contrary to conventional converters that can either charge or discharge the cells using a single source, thereby leaving several cells/modules (Ms) idle during each time step, the proposed converter enables the integration of two sources that can utilise the cells simultaneously. This dual source feature minimises idle cells/Ms, enhances energy efficiency, and supports flexible bidirectional power flow. The proposed converter operates in three distinct modes. The first involves dual-source charging for fast charging and improved vehicle availability. The second involves one source charging while the other discharges for dynamic operation. Finally, the last involves dual-source discharging for maximum power delivery and support vehicle-to-grid (V2G) operation. The simulation results demonstrated smooth multilevel sinusoidal output voltages (Vout_a and Vout_b), each with a peak of 350 V, generated simultaneously using 132 cells (six cells per M, 22 Ms). The total harmonic distortion (THD) values for Vout_a and Vout_b were 0.42% and 2.25%, respectively, confirming the high-quality performance. Furthermore, only 0–36 cells and 0–6 Ms were idle during operation, showing improved cell utilisation. Full article

To address the pronounced asymmetry and strong nonlinearity exhibited by the tractor electro-hydraulic hitch system during lifting and lowering operations, this study proposes a distributed parameter identification method based on a dual-mode grey-box modelling approach. Following a mode decomposition strategy, the lifting and lowering processes are regarded as two independent subsystems. Benchmark transfer function models are established for each subsystem through theoretical derivation. Considering the nonlinear characteristics and unmodeled dynamics that cannot be accurately captured by the benchmark model, a long short-term memory (LSTM) neural network compensator is introduced to enhance the model performance. Ultimately, a series-compensated dual-channel grey-box model is established, which effectively integrates mechanistic interpretability with high modelling accuracy. Then, to cope with the high-dimensional and heterogeneous parameter space of the constructed grey-box structure, a distributed parameter identification framework is proposed. This framework employs a staged optimization process that combines the whale optimization algorithm (WOA) with the gradient descent (GD) method to efficiently identify the hybrid parameter set. The identified models are validated through bench experiments. The results show that the proposed grey-box models achieve root mean square errors (RMSEs) of 0.33 mm and 0.48 mm, and mean absolute errors (MAEs) of 0.24 mm and 0.40 mm for the lifting and lowering processes, respectively. Compared with a single transfer function model, the RMSE is reduced by 57.6% and 87.3%, and the MAE is reduced by 59.2% and 87.9%, respectively. The proposed method substantially improves the modelling accuracy of the electro-hydraulic hitch system, providing a reliable foundation for system characterization and the design of high-performance control strategies for tractor electro-hydraulic hitch systems. Full article

The proliferation of algorithmically generated malicious URLs necessitates a shift from syntactic detection to semantic analysis. This paper introduces PhishGraph, a disk-aware Approximate Nearest Neighbor (ANN) search system designed to perform billion-scale semantic similarity searches on URL embeddings for threat intelligence applications. Traditional in-memory ANN indexes are prohibitively expensive at this scale, while existing disk-based solutions fail to address the unique challenges of the cybersecurity domain: the high velocity of streaming data, the complexity of hybrid queries involving rich metadata, and the highly skewed, adversarial nature of query workloads. PhishGraph addresses these challenges through a synergistic architecture built upon the foundational principles of DiskANN. Its core is a Vamana proximity graph optimized for SSD residency, but it extends this with three key innovations: a Hybrid Fusion Distance metric that natively integrates structured attributes into the graph’s topology for efficient constrained search; a dual-mode update mechanism that combines high-throughput batch consolidation with low-latency in-place updates for streaming data; and an adaptive maintenance policy that monitors query patterns and dynamically reconfigures graph hotspots to mitigate performance degradation from skewed workloads. Our comprehensive experimental evaluation on a billion-point dataset demonstrates that PhishGraph’s adaptive, hybrid design significantly outperforms strong baselines, offering a robust, scalable, and efficient solution for modern threat intelligence. Full article

(1) Background: Ultra-short-term photovoltaic (PV) power prediction is crucial for optimizing grid scheduling and enhancing energy utilization efficiency. Existing prediction methods face challenges of missing data, noise interference, and insufficient accuracy. (2) Methods: This study proposes a single-step hybrid neural network model integrating Temporal Convolutional Network (TCN), Temporal Shift Transformer (TST), and Bidirectional Gated Recurrent Unit (BiGRU) to achieve high-precision 15-minute-ahead PV power prediction, with a design aligned with symmetry principles. Data preprocessing uses Variational Mode Decomposition (VMD) and random forest interpolation to suppress noise and repair missing values. A symmetric parallel dual-branch feature extraction module is built: TCN-TST extracts local dynamics and long-term dependencies, while BiGRU captures global features. This symmetric structure matches the intra-day periodic symmetry of PV power (e.g., symmetric irradiance patterns around noon) and avoids bias from single-branch models. Tensor concatenation and an adaptive attention mechanism realize feature fusion and dynamic weighted output. (3) Results: Experiments on real data from a Xinjiang PV power station, with hyperparameter optimization (BiGRU units, activation function, TCN kernels, TST parameters), show that the model outperforms comparative models in MAE and R²—e.g., the MAE is 26.53% and 18.41% lower than that of TCN and Transforme. (4) Conclusions: The proposed method achieves a balance between accuracy and computational efficiency. It provides references for PV station operation, system scheduling, and grid stability. Full article

Lift–cruise-type unmanned aerial vehicles (UAVs) powered by hydrogen fuel cells often integrate secondary energy storage devices to improve responsiveness to load fluctuations during different flight phases, which necessitates an efficient energy management strategy that optimizes power allocation among multiple power sources. This paper presents an innovative fuel cell DC–DC converter (FDC) design for the hybrid power system of a lift–cruise-type UAV comprising a multi-stack fuel cell system and a battery. The novelty of this work lies in the development of an FDC suitable for a multi-stack fuel cell system through a dual-input single-output converter structure and a control algorithm. To integrate inputs supplied from two hydrogen fuel cell stacks into a single output, a controller with a single voltage controller–dual current controller structure was applied, and its performance was verified through simulations and experiments. Load balancing was maintained even under input asymmetry, and fault-tolerant performance was evaluated by analyzing the FDC output waveform under a simulated single-stack input failure. Furthermore, under the assumed flight scenarios, the results demonstrate that stable and efficient power supply is achieved through power-supply mode switching and application of a power distribution algorithm. Full article

Restoration of structurally compromised teeth often requires cusp coverage, yet the influence of preparation design and material type on performance remains unclear. This study evaluated the effect of cusp coverage design and hybrid resin–ceramic material on the marginal adaptation and fracture resistance of partial coverage restorations in mandibular molars. Eighty extracted teeth were prepared for indirect restorations and allocated to four groups (n = 20) according to design, either functional cusp coverage (FC) or complete cusp coverage (CC) and material, either GC Cerasmart (CS) or VITA Enamic (EN). Restorations were bonded with dual-cure resin cement, thermocycled, and subjected to cyclic loading. Fracture load, marginal adaptation, and failure mode were evaluated (α = 0.05). CC-CS and CC-EN exhibited significantly higher fracture loads than FC-CS and FC-EN (p < 0.001), while no difference was found between materials within each design. For marginal adaptation, CS showed significantly greater marginal gaps than EN in both designs (p < 0.001). CC designs demonstrated a higher proportion of repairable failures (Type I and II), whereas EN showed more catastrophic fractures. Within the limitations of this in vitro study, cusp coverage design significantly affected fracture resistance, while material type primarily influenced marginal adaptation. Both hybrid resin–ceramics provided acceptable mechanical performance for partial coverage restorations. Full article

Background: Angiogenesis, the physiological process by which new blood vessels originate from pre-existing ones, can be triggered by tumor cells to promote the growth, survival, and progression of cancer. Malignant tumors require a constant blood supply to meet their needs for oxygen and nutrients, making angiogenesis a key process in tumor development. Its pathologic role is caused by the dysregulation of signaling pathways, particularly those involving VEGFR-2, a key mediator of angiogenesis, and the K-RAS G12C mutant, a promoter of VEGF expression. Given their critical involvement in tumor progression, these targets represent promising candidates for new cancer therapies. Methods and Results: In this study, we applied an in silico hybrid and hierarchical virtual screening approach to identify potential dual VEGFR-2/K-RAS G12C inhibitors with anticancer and antiangiogenic properties. To this end, we screened the National Cancer Institute (NCI) database through ADME filtering tools. The refined dataset was then submitted to the ligand-based Biotarget Predictor Tool (BPT) in a multitarget mode. Subsequently, structure-based analysis, including molecular docking studies on VEGFR and K-RAS G12C, was performed to investigate the interactions of the most promising small molecules with both targets. Conclusions: Finally, the molecular dynamics simulations suggested compound 737734 as a promising small molecule with high stability in complex with both VEGFR-2 and K-RAS G12C, highlighting its potential as a dual-target inhibitor for cancer therapy. Full article

To solve the unrelated parallel batch processing machine scheduling problem (UPBPMSP) with dynamic job arrivals, heterogeneous processing times, and machine heterogeneity, this paper presents an improved artificial bee colony (IABC) algorithm aimed at minimizing the makespan. Three improvements include the following: (1) a hybrid encoding scheme that combines machine allocation coefficients and priority weights, allowing for flexible consideration of machine capabilities and dynamic job priorities; (2) a dual-mode variable neighborhood search strategy to optimize machine allocation and job sequencing simultaneously; (3) a dynamic weight tournament selection mechanism to enhance population diversity and avoid premature convergence. Experimental results show that IABC reduces the makespan by 5% to 25% compared to traditional ABC and genetic algorithms (GAs), with the most significant advantages observed in concentrated job arrival scenarios. Statistical tests confirm that the improvements are statistically significant, validating the effectiveness of the proposed algorithm. Full article