Search Results (5,652)

Ship maneuvering models based on MMG or Abkowitz formulations often suffer from systematic mismatches under real operating conditions, where shallow water, hull fouling, rudder degradation, and wind loads may coexist. This study proposes a physics-structured residual learning framework for multi-source disturbance decomposition and compensation. Disturbance-specific expert networks are introduced to map different disturbance sources into separate residual channels. A CNN-SE-BiLSTM encoder is further designed to estimate the slowly varying latent disturbance states from residual sequences, whereas wind is treated through an external pathway owing to its directly measurable and higher-frequency nature. Simulations on the KVLCC2 benchmark vessel under single-source, triple-source, and wind-inclusive disturbance scenarios demonstrate stable long-horizon closed-loop autoregressive prediction, with position-RMSE reductions of 74.7–91.7% relative to the corresponding nominal-MMG and wind-ablation baselines. These results indicate that the proposed physics-structured residual learning framework improves long-horizon prediction accuracy while retaining interpretable and modular disturbance-specific correction channels under complex operating conditions. Full article

In the current energy context, enhancing the precision of wind power prediction serves as a key enabler for the stable development of the power grid. In the existing wind power prediction models, there are often problems of modal aliasing and noise residue, or the prediction accuracy of the model is not high. In an effort to solve the problem of short-term wind power forecasting, a wind power series decomposition and reconstruction method based on improved complete ensemble empirical mode decomposition with adaptive noise-variational modal decomposition (ICEEMDAN-VMD) secondary decomposition is proposed. Using ICEEMDAN, wind power data (wind direction, wind speed, temperature, humidity, air pressure, etc.) is decomposed into several IMF sub-series, and these IMF sub-series are categorized into three different frequency components by combining sample entropy, Q statistics and sequence frequency. Secondly, the gray wolf optimization (GWO) is improved by using the empirical exchange strategy (EES), and the optimization performance of the EES-GWO proposed in this paper is verified by using 10 test functions. Finally, the EES-GWO-convolutional neural network–bidirectional gated recurrent unit–global attention (EES-GWO-CNN-BiGRU–Global attention) high-frequency component prediction model is constructed. Finally, we employ the XGBoost model to forecast the mid- and low-frequency components, thereby generating the corresponding forecasting results. The support vector machine (SVM) model nonlinearly integrates all the forecasting results to produce the final forecasting results. Through example analysis and comparison, the performance of the proposed model is verified from two perspectives. Full article

While cost-effective austenitic stainless steels like AISI 304 are utilised in intermediate-temperature concentrated solar power (CSP) components, autogenous welding can compromise their structural integrity. This work investigates the corrosion behaviour of autogenous TIG-welded AISI 304 joints exposed to commercial molten solar salt at 550 °C for up to 1350 h under static conditions. Gravimetric and microstructural analyses revealed a stochastic bimodal breakaway oxidation mechanism. After an initial transient passivation regime (0–650 h) attributed to the formation of a protective Fe₃O₄/FeCr₂O₄ bi-layer, a sharp kinetic acceleration occurred. This localized breakdown was synergistically catalysed by trace chloride impurities, which triggered deep pitting along the microsegregated dendritic networks of the weld metal. Furthermore, due to severe X-ray attenuation under massive late-stage oxides, definitive proof of sensitisation was established using the standardised ASTM A262 Practice A topographic evaluation. The appearance of continuous ditch structures only in the heat-affected zone (HAZ) suggests severe intergranular anodic dissolution. This failure is thermodynamically driven by unmitigated residual tensile stresses, highlighting that the long-term reliability of these components is interpreted to be dictated by the localised, asymmetric breakdown of the weldment rather than uniform global oxidation. Full article

In laser metal deposition (LMD), complex thermo-mechanical coupling and irregular layer morphology significantly affect residual stress distribution. However, most simulations rely on idealized geometries, limiting prediction accuracy. This study proposes a data-driven framework integrating in situ vision-based morphology reconstruction with thermo-mechanical simulation for high nitrogen steel (HNS). An improved DeepLabv3+ network is developed to extract deposition layer contours under strong illumination and spatter interference, achieving a mean intersection over union (mIoU) of 97.32% and an overall accuracy of 99.42%. The reconstructed morphology is incorporated into a finite element model to enable dynamic heat source tracking and realistic geometric representation. The proposed method demonstrates high morphology reconstruction accuracy, with all measurement errors controlled within 0.91%. The simulated temperature field agrees well with experimental measurements. Furthermore, the predicted residual stress distribution is consistent with X-ray diffraction (XRD) results under different laser power conditions. The results indicate that local surface morphology significantly influences stress concentration, with protrusion regions exhibiting stress peaks up to 989 MPa, markedly higher than those in concave regions. This study improves the accuracy of residual stress prediction in LMD by incorporating real morphology data and provides insight into the relationship between morphological features and stress evolution in additively manufactured HNS components. Full article

Cell-free network architectures are a promising candidate for sixth-generation (6G) communications, as densely distributed access points (APs) flexibly accommodate traffic demands and mitigate inter-cell interference. In practical cell-free systems employing direct-conversion receivers, however, performance is severely degraded by analog front-end impairments such as in-phase/quadrature (IQ) imbalance and carrier frequency offset (CFO). Conventional orthogonal frequency division multiplexing (OFDM)-based algorithms address these impairments separately, but their joint impact is insufficiently mitigated because IQ imbalance and CFO mutually interfere, leaving residual errors when either is estimated first. To overcome this, we extend our previously proposed adaptive compensation scheme based on time-frequency interferometry-OFDM (TFI-OFDM) by introducing a decision-feedback mechanism. Preliminary CFO estimation and compensation are first performed to suppress inter-symbol interference (ISI), followed by joint estimation and compensation of IQ imbalance and CFO via decision feedback, achieving accurate channel estimation with low pilot overhead. Simulation results demonstrate that the proposed scheme effectively mitigates the mutual interference of both impairments, achieving bit-error-rate (BER) performance close to an ideal impairment-free system. These results confirm that TFI-OFDM-based joint compensation with decision feedback is a promising approach for practical 6G cell-free deployments. Full article

Granite residual soil slopes are highly water-sensitive and prone to rapid collapse, strength degradation, and rainfall-induced erosion. This study investigates the improvement effects and underlying mechanisms of carboxymethyl cellulose (CMC) on the water stability, mechanical properties, and rainfall erosion resistance of granite residual soil from Fuzhou, Fujian Province, China. Laboratory tests, including unconfined compressive strength (UCS) tests, direct shear tests, disintegration tests, slope rainfall scouring model experiments, X-ray diffraction test (XRD) and scanning electron microscopy (SEM) observations, were conducted to evaluate the performance and microstructural behavior of CMC-stabilized soils. The results indicate that the addition of CMC significantly enhances soil resistance to disintegration: the 24 h disintegration ratio decreased to 0.5% at 0.5% CMC content. The incorporation of CMC can significantly enhance the unconfined compressive strength (UCS) of the soil and lead to an increase in cohesion, while its effect on the internal friction angle is limited. Under simulated rainfall conditions (30° slope, 120 mm·h⁻¹ rainfall intensity, 60 min duration), slopes stabilized with 0.5% CMC exhibited suppressed rill formation and a 47.5% reduction in sediment yield, accompanied by delayed moisture increase at different depths and reduced infiltration rates. Microstructural analyses reveal that CMC hydration forms gel-like films and filamentous bridges, promoting particle aggregation and pore filling, thereby constructing a denser particle network without generating new chemical compounds. This microstructure collectively enhances soil disintegration resistance, mechanical strength, and slope erosion resistance. Full article

The global construction industry urgently requires sustainable alternatives to ordinary Portland cement (OPC) to mitigate its immense carbon footprint. Red mud (RM), a highly alkaline bauxite residue, presents tremendous but challenging potential as a supplementary cementitious material. This review systematically bridges the gap between atomic-level interfacial bonding mechanisms and macroscopic engineering performance, highlighting how these properties are significantly dictated by specific RM sources (e.g., Bayer vs. Sintering processes). We first elucidate advanced pretreatment strategies, notably CO₂ mineralization, which synergistically mitigates extreme alkalinity and sequesters carbon. Crucially, the fundamental bonding mechanisms are decoded: beyond physical filling, RM integration induces significant micro-morphological densification via intense aluminosilicate depolymerization—evidenced by the Al[VI] to Al[IV] coordination shift—and the quantitative integration of approximately 40% reactive iron phases into stable Fe-S-H networks. By clearly distinguishing between traditional hydration and clinker-free alkali-activation pathways, we evaluate holistic structural parameters beyond mere 28-day compressive strength (40–67 MPa), explicitly addressing flexural capacity, modulus of elasticity, and volume stability. Environmental assessments confirm exceptional heavy metal immobilization (>95% efficiency, leaching < 0.010 mg/L) and a substantial 50–80% reduction in Global Warming Potential (GWP), provided the environmental burden of alkaline activators is rigorously accounted for. Furthermore, the long-term risk of Alkali–Silica Reaction (ASR) is evaluated as a primary durability concern. Finally, to overcome persistent rheological bottlenecks, this paper highlights transformative future trajectories, particularly data-driven Machine Learning (ML) for complex mix optimization and 3D concrete printing for advanced infrastructure. Ultimately, this review provides a robust theoretical foundation and a pragmatic roadmap for upcycling RM into safe, high-performance, and ultra-low-carbon building materials. Full article

The quality of Global Navigation Satellite System (GNSS) observations on smartphones is highly susceptible to multipath and non-line-of-sight (NLOS) effects in urban environments, resulting in complex and highly variable observation errors. These challenges highlight the necessity of a reliable stochastic model to ensure robust and unbiased parameter estimation. However, conventional empirical stochastic models, such as elevation-dependent or signal-to-noise ratio (SNR)-based weighting schemes, are often insufficient to capture the rapidly changing stochastic behavior of observations in dense urban environments. To overcome this limitation, an adaptive GNSS stochastic model based on a deep neural network (DNN) is developed by integrating SNR, satellite elevation angle, and post-fit pseudorange residuals, which provide a strong indicator of observation quality and environmental context. Specifically, a fully connected DNN is designed to use SNR, satellite elevation angle, and post-fit pseudorange residual as input features, representing signal strength, satellite geometry, and residual information, respectively, and to learn their nonlinear relationship with measurement uncertainty. The network output is then used to adaptively update the diagonal elements of the measurement noise covariance matrix, thereby realizing epoch-wise adaptive weighting within the Kalman filtering process. The proposed DNN-based stochastic model, together with several conventional models, was evaluated using GNSS observations collected by a low-cost u-blox ZED-F9P receiver (u-blox AG, Thalwil, Switzerland) and a Samsung Galaxy S21+ smartphone (Samsung Electronics Co., Ltd., Suwon, Republic of Korea) during vehicle experiments in dense urban canyons. The code-based single point positioning (SPP) results demonstrate that the DNN-based model consistently outperforms traditional stochastic models under both open-sky and urban conditions. The improvement is particularly pronounced for smartphone observations in severely obstructed environments. The proposed DNN-based model reduces the 3D RMSE from 14.25 m, 13.68 m, and 13.05 m, obtained with the elevation-, SNR-, and integrated elevation–SNR-based models, respectively, to 8.94 m, representing an improvement of approximately 35%. A similar improvement is observed for the u-blox ZED-F9P receiver, where the 3D RMSE decreases from 5.71 m, 4.69 m, and 5.15 m to 3.10 m. These results suggest the effectiveness of the proposed DNN-based stochastic model in mitigating complex observation errors and improving positioning accuracy, providing a promising solution for reliable positioning of low-cost GNSS receivers in challenging urban environments. Full article

A high-precision and efficient surface defect detection for printed circuit board (PCB) is critical to ensuring the reliability of electronic systems. However, the presence of complex circuit backgrounds and the small scale of defects often limit the precision and effectiveness of conventional inspection approaches. To address these challenges, this paper proposes FMW-YOLO, a lightweight and accurate detection framework based on YOLO11n. Specifically, a Frequency-Enhanced Channel-Transposed and Local Feature backbone network is developed to improve feature extraction. By designing a Dual-Frequency and Channel Attention Aggregation module and a Lightweight Edge-Gaussian Block, the original C3k2 structure is refined to suppress noise interference while preserving high-frequency details, thereby enhancing feature representation. Furthermore, a neck network incorporating a Multi-Scale Context-Aware Enhancement mechanism is constructed, in which an Attention-Integrated Feature Pyramid is employed to facilitate more effective cross-scale feature interaction. In addition, a Dilated Reparam Residual Module is embedded into the C3k2 structure to expand the receptive field without significantly increasing computational burden. Finally, Wise-IoU is adopted to optimize bounding box regression by assigning greater importance to anchors of moderate quality. Extensive experiments conducted on the HRIPCB and DeepPCB datasets demonstrate that FMW-YOLO improves mAP50 by 2.1% and 0.3%, respectively, while reducing the number of parameters by 23%. These results indicate that the proposed method achieves improved detection accuracy and demonstrates strong potential for practical industrial applications. Full article

Environmental fires pose a serious threat to energy security, ecosystems and public safety, whilst traditional halogenated flame retardants suffer from limitations such as high environmental residue risks and insufficient flame-retardant efficacy. In this study, sodium alginate (SA) was utilised as the matrix, with the incorporation of ammonium polyphosphate (APP) and phytic acid (PA), in conjunction with SiO₂-APTES surface modification, to prepare nitrogen–phosphorus synergistic bio-based flame-retardant gels. The present study systematically investigated the influence of the N/P molar ratio on the gelation kinetics, rheological behaviour, microstructure and flame-retardant performance of the gel. The study revealed a nitrogen–phosphorus coupled gas–solid two-phase synergistic flame-retardant mechanism. The results indicate that at an N/P ratio of 1/4, the gel forms a stable dual-network structure comprising ionic cross-links and Si–O–P covalent bonds. In the gas phase, the thermal decomposition of APP releases inert NH₃, which dilutes oxygen and quenches gas-phase radicals (·OH, ·H). In the condensed phase, the phosphate groups of PA-catalysed SA form Si–O–P covalent bonds with SiO₂ under the mediation of APTES, creating a dense, insulating char layer. In comparison with the control group (N/P = 0/0), the optimal gel sample (N/P = 1/4) demonstrated a 33% increase in shear stress, a 10% reduction in the peak heat release rate (HRR), a 75% decrease in total smoke production (TSP), and a 150% increase in char layer thickness after combustion, while maintaining adequate mechanical strength, thermal stability, and environmental friendliness. This work provides novel insights and strategies for the development of green, highly efficient flame-retardant materials for environmental fire prevention and control. Full article

Background: Hemagglutinin (HA) is the primary surface protein of the influenza A virus, determining its subtype and antigenic properties. Traditional subtype classification methods rely on DNA or amino acid sequence analysis, which does not account for protein spatial folding. Methods: In this work, we propose EpitopeGNN—a graph neural network (GNN) that constructs a residue interaction network (RIN) from the 3D structure of HA and classifies the virus subtype. The model was trained on 249 structures from the Protein Data Bank (PDB), containing H1N1, H3N2, H5N1, and other subtypes. Results: After rigorous sequence redundancy reduction (92% identity), the model maintained 95–100% accuracy on non-redundant data, significantly outperforming sequence-only baselines (the best baseline achieved 85% for multi-class and 92.3% for binary classification). A significant correlation was found between the obtained structural embeddings and phylogenetic distances (r = 0.38, p < 0.001), confirming their biological relevance and opening opportunities for structural monitoring of virus evolution, as well as rapid analog searching for novel strains. Conclusions: We developed a new graph neural network that classifies influenza A virus subtypes directly from the 3D structure of hemagglutinin using residue interaction networks and physicochemical features, which can serve as a foundation for predicting influenza virus receptor specificity and epitope immunogenicity. Full article

Accurate ultra-short-term photovoltaic (PV) power forecasting is essential for secure grid dispatch and renewable-rich system operation, yet it remains difficult because of rapid weather fluctuations and error accumulation in multi-step prediction. This paper proposes a decoupled physics-guided residual-correction framework, built on an attention-based sequence-to-sequence (Seq2Seq) architecture, for deterministic 4 h ahead rolling PV forecasting at 15 min resolution. In the first stage, a physical model maps numerical weather prediction (NWP) inputs to a deterministic baseline trajectory while preserving physical bounds. In the second stage, an Attention-Seq2Seq network learns the structured residual trajectory from historical sequences. The global attention mechanism allows the decoder to focus on the most informative historical states, helping reduce information loss and error accumulation over extended horizons. Experiments on a 22-month real-world PV dataset show that the proposed framework outperforms conventional linear and nonlinear benchmarks, reducing root mean square error (RMSE) and mean absolute error (MAE) by 23.79% and 39.17%, respectively, relative to the physical baseline. The framework also maintains robust instantaneous tracking under rapidly changing cloud conditions and preserves a 30–40% error reduction rate at Steps 12–16, supporting reliable intraday scheduling. Full article

High-resolution remote sensing image change detection holds significant application value in the fields of urban planning, disaster assessment, and others. However, it faces the dual challenge of pseudo-change interference and loss of detailed information. To address these issues, a frequency-domain-aware Siamese detail recovery network (FSD-Net) is designed in this paper. Firstly, from the perspective of frequency domain analysis, a theory on the dual roles of frequency domain components is introduced to reveal the robustness of low-frequency components to pseudo-changes and the dual semantic noise attributes of high-frequency components. Based on this theory, a frequency-aware context-guided difference (FCGD) module is designed. By explicitly decoupling the difference features into low-frequency global components and high-frequency residual components, it utilizes the prior low-frequency scene as a semantic gate to adaptively modulate the high-frequency differences, which effectively suppress pseudo-change interference. Subsequently, a detail recovery block (DRB), based on sub-pixel convolution, is constructed. This achieves unbiased spatial rearrangement through the semantic redundancy of channel dimensions, which avoids the checkerboard artifacts of traditional upsampling, and by employing a progressive multi-stage upsampling strategy to integrate shallow detail features from the encoder. The experimental results on the three public datasets of LEVIR-CD, WHU-CD, and CDD-CD demonstrate that the FSD-Net outperforms current mainstream methods (e.g., ChangeFormer, BAN, and so on) in core metrics such as F1 score and IoU, with a particularly significant improvement in recall. The ablation experiments validate the effectiveness and complementarity of the FCGD and DRB. Parameter sensitivity analysis indicates that the auxiliary loss weight λ is dataset dependent, with λ = 0.1 serving as a robust default choice. This study provides an efficient and reliable solution for change detection in high-resolution remote sensing imagery. Full article

High-frequency volatility and extreme tail risks in offshore wind power pose severe challenges to grid stability and economic operation. Conventional storage planning often relies on deterministic profiles or static allocation rules, failing to capture the non-stationary temporal dynamics of marine wind resources. To bridge this gap, this paper proposes a closed-loop framework that integrates ultra-short-term probabilistic forecasting with dynamic hybrid energy storage optimization. A novel Dual-Channel Residual Network is developed to provide well-calibrated predictive uncertainty quantification, which explicitly drives a Prediction-Guided Dynamic Hybrid Storage Optimization Framework. By dynamically coordinating lithium-ion batteries and liquid air energy storage based on evidential predictive variance, the proposed approach achieves superior synergy between short-term power response and long-duration energy shifting. Case studies on an offshore wind farm validate that the framework significantly reduces the Levelized Cost of Energy and loss-of-load risks while enhancing frequency regulation capabilities compared to state-of-the-art benchmarks. Full article

Accurate estimation of vehicle sideslip angle and lateral velocity is essential for the stability control of Advanced Driver Assistance Systems (ADASs). Traditional physics-based observers often exhibit dynamic response distortions under stability-limit conditions due to unmodeled tire relaxation effects, while data-driven methods lack physical interpretability. This paper proposes a Physics-Driven Hybrid Estimation Framework (PD-HEF) to bridge this gap. First, a nonlinear nominal model is constructed as a physical skeleton, and dynamic residual equations are derived to define learning targets. Second, a Spatio-Temporal Feature Coupled Residual Network is designed to capture time-domain phase lag and compensate for spatial nonlinear deviations. Furthermore, a hybrid unscented Kalman filter is developed to inject predicted residuals into the sigma-point evolution. A Dual-Layer Adaptive Mechanism is also introduced to regulate trust weights based on innovation statistics. Joint simulations demonstrate that the proposed framework reduces the root mean square error by over 60% compared to traditional observers while satisfying real-time constraints. Full article