Search Results (118)

To address the performance degradation caused by coupling interference between control and identification filters in the active control of ship hydraulic systems, a multi-strategy collaborative optimization algorithm based on “Signal–Amplitude–Time” is proposed. The method constructs a variable-power white-noise module based on power factors to reduce auxiliary noise interference. It employs an improved variable-step-size LMS algorithm to achieve fast and high-precision online identification of the secondary path. Furthermore, an adaptive prediction error filter is introduced to decouple the control and identification processes, effectively resolving the conflict between convergence speed and steady-state precision. Simulation and experimental results demonstrate that the proposed optimization algorithm exhibits superior robustness and adaptive capability under various operating conditions. It can track complex load fluctuations in real time and achieve a line-spectrum pulsation attenuation of more than 90%. This multi-strategy collaborative scheme significantly enhances the pulsation suppression accuracy and dynamic response capability of ship hydraulic systems, providing an efficient and reliable technical approach for the acoustic stealth control of naval ship hydraulic systems. Full article

Accurate segmentation of ship targets in high-resolution remote sensing images is crucial for maritime monitoring, traffic management and naval security. However, existing methods struggle to simultaneously address extreme scale variations in ships and severe complex background interference, leading to unsatisfactory accuracy and generalization in scenarios with shoreline occlusion and ocean wave noise. To tackle this challenge, we first construct a large-scale, high-quality multi-scale ship dataset containing 69,407 professionally annotated samples. Then, we propose ShipMS-BSNet, a multi-scale feature fusion network based on nnU-Net. At the encoder, the Multi-Scale Receptive Field Enhancement (MSRF) module captures multi-scale contextual information, while the Background Suppression Channel Attention (BSCA) module suppresses invalid background responses via learnable negative bias. At the decoder, dynamic upsampling restores spatial details, and a final Multi-Scale Refinement (MSR) module optimizes target boundaries. Extensive experiments on our self-built dataset and the public HRSC2016 dataset show that our method outperforms mainstream approaches. On the self-built dataset, it achieves 0.879 precision, 0.875 Recall, 0.868 F1-score and 0.761 IoU, validating its strong robustness for multi-scale ship segmentation in complex marine environments. Full article

The target price for naval equipment orders is driven by the coupling of multidimensional technical and economic factors, exhibiting typical characteristics such as high dimensionality, strong nonlinearity, multicollinearity, and small-sample fluctuations. Traditional cost estimation methods struggle to achieve high-precision fitting and interpretable decision support. To address these issues, this paper constructs an integrated prediction model that combines Boruta–Lasso two-stage feature selection, grid search-optimized CatBoost, and SHAP interpretability analysis. First, the Boruta algorithm is used for rough screening of feature significance, then Lasso regression is applied for sparse fine screening, effectively eliminating redundant features and significantly mitigating multicollinearity; grid search and five-fold repeated cross-validation are employed to optimize CatBoost hyperparameters, while 10 repeated experiments with random seeds are conducted to verify model generalization robustness. SHAP is used to quantify the marginal contribution of features, revealing nonlinear associations and statistical response transition points between core features and price. This study is based on 33 publicly available real data from main combat vessels, from which 198 modeling samples were generated through interpolation-based small-sample data augmentation. The interpolated samples were only used for data augmentation and were not considered independent empirical samples. All core conclusions were validated on the 33 original real samples, and there are no missing values in the dataset. Experimental results show that the proposed model achieved the best individual results on the test set, with a coefficient of determination of R² = 0.8949, root mean square error RMSE = 0.0554, and mean absolute error MAE = 0.0476. Across 10 repeated robustness experiments, the average results were R² = 0.8828, RMSE = 0.0586, and MAE = 0.0529, with overall performance better than comparison models such as XGBoost, random forest, and standard CatBoost. Ablation experiments validated the effectiveness of the two-stage Boruta–Lasso selection strategy in improving model accuracy and stability. SHAP attribution analysis shows that full-load displacement, number of vertical missile launch cells, number of phased array radars, and combat capability are core features highly correlated with price, all showing significant nonlinear positive correlations and clear statistical response transition points. The dataset in this study has no missing values, is entirely constructed based on publicly traceable data, and does not include confidential information such as internal shipyard costs. The findings reflect statistical associations rather than causal effects. However, the sample size and ship-type coverage are limited, so the model’s applicability is somewhat constrained, and its generalization ability needs to be further verified on larger-scale, multi-ship-type independent datasets. This model combines high prediction accuracy, strong robustness, and good interpretability, providing reliable technical support for ship equipment procurement pricing demonstration, full lifecycle cost management, and scientific procurement decision-making. Full article

The next generation of naval and defense systems will strain current naval ship cooling systems. Throughout its life-cycle, this strain will alter the behavior of the physical system, and any virtual representation of the system will become outdated due to component aging. Digital twins are a trending tool that can assimilate real-time sensor data to tailor a virtual representation to its physical counterpart. The online faithful virtual representation of the physical system provided by digital twins can be used for real-time system optimizations and proactive fault detection, diagnostics, and control adjustments, alleviating the stress of component aging. To support these complex power systems throughout their lifecycles, data-driven solutions for digital twin tuning will become essential. This paper investigates the application of a parameter-tuning digital twin framework to enhance the performance of a multi-physics model. The digital twin framework comprises a digital twin tuning scheme, a physical testbed designed to emulate the cooling system of a ship, and a multi-physics representation of that system. The digital twin tuning scheme leverages a swarm of particles and online sensor data to evaluate permutations of parameters to update the digital representation periodically. The digital twin framework was applied to a physical system to provide experimental data results demonstrating the usefulness of the tuning system. The physical system was designed and constructed to emulate the heat generation and dissipation from 6 liquid-cooled power converters under loads ranging from 10–15 kW at 99% efficiency. Two scenarios were applied to evaluate the performance of the digital twin framework. Results demonstrate that the digital twin framework can adapt to system changes in real-time and improve the accuracy of the related virtual representation by more than 90% when measured at four points of the system under test. Full article

Underwater explosion bubbles generate intense pressure pulses and high-speed re-entrant jets during their expansion and collapse processes, posing significant threats to ships and submerged structures. In practical engineering, plate-like structures with different orientations are widely encountered; therefore, investigating the influence of boundary orientation on bubble dynamics is of great importance. In this study, underwater electrical explosion experiments were conducted using a capacitor discharge voltage of 300 V, with stand-off distances ranging from 1 mm to 30 mm. Two typical boundary configurations were established, namely a vertical plate and a horizontal plate. High-speed imaging was employed to capture the complete bubble evolution process, while coupled Eulerian–Lagrangian (CEL) simulations were performed to analyze bubble dynamics and structural response. The results indicate that, under the vertical plate condition, the maximum bubble diameter decreases monotonically with increasing stand-off distance, whereas the oscillation period exhibits a non-monotonic variation. At a stand-off distance of 5 mm, the maximum bubble diameter in the vertical plate configuration is 40.3% larger than that in the horizontal plate configuration. The reflected shock wave from the elastic boundary modifies the surrounding pressure field, thereby influencing the evolution of the bubble interface. In the presence of a vertical elastic plate, the bubble exhibits a centroid displacement during the expansion phase, and a re-entrant jet directed toward the boundary forms during collapse. In contrast, under the horizontal elastic plate condition, the bubble maintains a nearly axisymmetric evolution, and the re-entrant jet develops along the vertical direction. As the standoff distance between the plate and the charge center increases, the boundary effect gradually weakens, and the bubble morphology approaches that under free-field conditions. This study provides experimental evidence for understanding bubble–structure interaction (BSI) between underwater explosion bubbles and ship plate structures, and offers valuable insights for blast-resistant design of naval structures and the evaluation of underwater explosion loads. Full article

Zonal ship central cooling systems, which are primarily implemented in naval platforms and advanced specialized vessels to ensure high survivability, exhibit complex fluid–thermal interactions and multi-level valve networks, challenging conventional resilience analysis, especially under large-scale fault scenarios and dynamic topology reconfiguration. This paper presents a physics-informed dynamic resilience assessment and reconfiguration optimization method tailored for such systems. To address the high-dimensional reconfiguration search space, a physics-informed pruning mechanism combining topological reachability filtering and nodal continuity-based feasible-flow verification is introduced, eliminating 42.6% of invalid topologies and reducing optimization time by approximately 38%. Additionally, a cumulative thermal severity (CTS) metric is developed to capture transient thermal shock risks, quantitatively assessing deviation from the 50 °C system safety boundary at the most critical node. Simulation results for a main seawater pump failure scenario demonstrate that the proposed reconfiguration strategy, which coordinates cross-zone tie valves and leverages healthy zones’ pressure margins, shortens recovery time by 47%, suppresses peak temperature from 51.5 °C to 50.2 °C, reduces maximum over-temperature from 1.5 °C to 0.2 °C, and decreases CTS from 8.5 °C·s to 0.1 °C·s (a 98.8% reduction). These findings demonstrate that physics-informed pruning substantially reduces the computational burden of high-dimensional reconfiguration, while the proposed CTS metric enables quantitative assessment of transient thermal-shock risk. Together, they offer robust methodological guidance for resilience-oriented decision support and fault-tolerant design in complex shipboard fluid–thermal systems. Full article

Accurate prediction of ship wave-making resistance is a critical challenge in naval architecture, particularly during the preliminary design stage. This study presents a comprehensive hybrid artificial intelligence (AI) framework for predicting the wave-making resistance coefficient (C_W) of the DTMB 5415 naval hull model, integrating both numerical hull parameters and image-derived hydrodynamic features. A systematic parametric study was conducted by varying the hull’s principal dimensions—length, beam, and draft—by ±25% from their nominal values, resulting in 135 distinct hull configurations, where for each combination, C_W is computed using Maxsurf software (Academic Version 25). Corresponding wave fields are captured as images and preprocessed through resizing, grayscale conversion, contrast enhancement, and edge detection to emphasize key hydrodynamic characteristics for AI training. A dual neural network architecture is employed, combining a Feed-Forward Artificial Neural Network (C_W) for numerical inputs with a Convolutional Neural Network (CNN) for image-based feature extraction. The hybrid model demonstrated superior predictive performance, achieving a coefficient of determination (R²) exceeding 0.99, significantly outperforming standalone FFAN and CNN models. This study contributes a novel, physically interpretable AI framework capable of capturing complex nonlinear interactions between hull geometry and wave patterns, providing a reliable and computationally efficient alternative to towing tank experiments and high-fidelity CFD simulations. Full article

The increasing demand for reliability and safety in naval and offshore structures has accelerated the adoption of advanced Structural Health Monitoring (SHM) techniques. Among them, acoustic methods—ranging from passive acoustic emission monitoring to guided ultrasonic waves—have demonstrated exceptional potential for early detection, localization, and characterization of structural damage under harsh marine environments. This review provides a comprehensive and critical synthesis of the state-of-the-art in acoustic-based SHM applied to ships, submarines, offshore platforms, and floating renewable energy systems. Special emphasis is placed on the comparative performance of different acoustic techniques, their integration with numerical modeling and data-driven methods, and their suitability for real-world deployment considering hydrodynamic, operational, and environmental constraints. By bridging current achievements with future challenges, the paper highlights research gaps and outlines key directions to accelerate the transition of acoustic SHM technologies from laboratory studies to widespread industrial applications. This review aspires to serve as a reference work for both academic researchers and practitioners, consolidating knowledge and inspiring innovation in the field. Full article

The wave-making characteristics and resistance performance of a naval vessel are fundamental to its hydrodynamic design, directly impacting its speed, stealth, and energy efficiency. To reveal the performance trade-offs inherent in different design philosophies, a systematic comparative study on the hydrodynamic performance of two representative mainstream naval destroyers from China and the United States was conducted using Computational Fluid Dynamics (CFD). Full-scale three-dimensional models of both vessels were established based on publicly available data. Their flow fields in calm water were numerically simulated at both economical (18 knots) and maximum (30 knots) speeds using an unsteady Reynolds-Averaged Navier–Stokes (RANS) solver, the Volume of Fluid (VOF) method for free-surface capturing, and the SST k-ω turbulence model. The performance differences were meticulously compared through qualitative observation of wave patterns, quantitative measurements (such as the transverse width of the wave-making region), and analysis of resistance data. Numerical results indicated that the wave-making generated by the vessel of the United States was more pronounced during steady navigation. To validate the reliability of the CFD results, supplementary towing tank tests were performed using a small-scale model (1.1 m in length) of the vessel from China. The test speed (1.5 m/s) was scaled to correspond to the full-scale ship speed through dimensional analysis. The experimental data showed good agreement with the simulation results, jointly confirming the aforementioned performance trade-off. This study clearly demonstrates that, at the economic speed, the design of the mainstream vessel from China tends to prioritize superior wave stealth performance at the expense of higher resistance, whereas the mainstream vessel from the U.S. exhibits the characteristics of lower resistance coupled with more significant wave-making features. These findings provide an important theoretical basis and data support for the future multi-objective optimization design of surface vessels concerning stealth, speed, and comprehensive energy efficiency. Full article

In the naval sector, hydrofluorocarbons (HFCs) are the primary refrigerants in use. To face global environmental challenges, international treaties have established stringent regulations aimed at transitioning towards more sustainable alternatives. Natural refrigerants are proposed as valid solutions, with a particular focus on carbon dioxide (R744) due to its very low direct environmental impact and high safety. This paper evaluates the potential of using R744 as a refrigerant for refrigeration systems onboard cruise ships; based on the R744 innovative solutions currently proposed in the literature for cruise ship applications, the aim is to assess whether the transition to R744 would provide advantages in terms of energy performance and total environmental impact compared with conventional systems employing HFCs. The analysis includes a description of the conventional provision and air conditioning systems mounted onboard and innovative technologies utilizing R744 as a refrigerant, proposed in the literature. These systems are numerically analyzed and compared. The numerical results show that the exclusive use of R744 in onboard systems would significantly reduce the direct environmental impact compared with the current HFCs-based configurations. However, when considering the total impact, further technological advancements in R744 systems are required to achieve a reduction in indirect emissions as well. While progressing toward full R744 adoption, some promising pathways are proposed to enhance current system efficiency. Full article

Shipborne fighters play a critical role in far-sea operations. However, their landing process on aircraft carrier decks involves significant risks, where accidents can lead to substantial losses. Timely and accurate risk prediction is, therefore, essential for improving flight training efficiency and enhancing the combat capability of naval aviation forces. Machine-learning algorithms have been explored for predicting landing risks in land-based aircraft. However, owing to the challenges in acquiring relevant data, the application of such methods to shipborne aircraft remains limited. To address this gap, the present study proposes a deep learning-based method for predicting landing risks of shipborne aircraft. A dataset was constructed using simulated ship movements recorded during the sliding phase along with relevant flight parameters. Model training and prediction were conducted using up to ten different input combinations with artificial neural networks, long short-term memory, and transformer neural networks. Experimental results demonstrate that all three models can effectively predict landing parameters, with the lowest average test error reaching 3.5620. The study offers a comprehensive comparison of traditional machine learning and deep learning methods, providing practical insights into input variable selection and model performance evaluation. Although deep learning models, particularly the Transformer, achieved the highest accuracy, in practical applications, the support of hardware performance still needs to be fully considered. Full article

Small fishing vessels are highly susceptible to stability-related accidents due to their limited size and vulnerability to rough seas. Although both international and Korean regulations mandate minimum stability standards, accurately estimating the metacentric height (G₀M) during the early design stage—when detailed drawings or hydrostatic data are unavailable—remains a challenge. To address this gap, this study proposes a deep neural network (DNN)-based predictive model that estimates the G₀M of small vessels using only fundamental hull dimensions and derived design variables, such as length-to-breadth ratio and length multiplied by block coefficient. A dataset comprising 118 Korean fishing vessels and 359 different loading conditions was constructed using parameters typically available in the early stages of ship design. These inputs do not require detailed hydrostatic calculations or structural drawings, making the approach practical for conceptual design. The model demonstrates strong predictive accuracy across diverse hull configurations and loading cases. Unlike conventional methods that depend on finalized designs or roll-period measurements, the proposed model enables quick and approximate stability assessments at the preliminary design phase. It serves as an efficient design support tool to allow naval architects to assess regulatory compliance and overall stability early in the development process, contributing to safer and more effective vessel design practices. In addition, by enabling fast and data-driven assessment of vessel stability, the proposed model may also serve as a foundational tool in broader maritime digitalization efforts, including intelligent ship design and ship-port logistics automation. Full article

Early-stage dynamic responses of naval structures under underwater explosion shock loads exhibit high-frequency, intense amplitude fluctuations and short durations, serving as critical factors for the development of plastic deformation and other damage characteristics. These structural dynamics demonstrate prominent nonlinear and non-stationary features. This study focuses on the nonlinear evolutionary patterns of early-stage plastic shock responses in underwater explosion-impacted ship structures. Utilizing phase space reconstruction, unimodal mapping, and symbolic dynamics theory, we analyze the nonlinear and non-stationary characteristics along with their evolutionary patterns in experimental data. First, scaled model experiments under varying shock factors were conducted based on a stiffened cylindrical shell prototype, investigating the spatiotemporal evolution of nonlinear and non-stationary dynamic responses under different shock loads while characterizing their uncertainty features. Second, model tests were performed on deck-type cabin structures and plate frameworks derived from a naval vessel’s deck prototype, further analyzing the evolutionary patterns of early-stage plastic dynamic responses and verifying the method’s effectiveness and universality. Research findings indicate that (1) early-stage plastic shock responses of ships under underwater explosions exhibit multiple dynamical behaviors including chaotic motion, periodic motion, and quasi-periodic motion, and (2) during the initial plastic phase, orbital parameters approximate 0.8, providing guidance for test condition setup and initial parameter selection in underwater explosion experiments on naval structures. Full article

Artificial Intelligence (AI) is increasingly integrated into ship design workflows, offering enhanced capabilities for hydrodynamic and structural optimization. This review focuses on AI-based methods applied to key design tasks such as hull resistance prediction, structural weight reduction, and performance-driven form optimization. Techniques examined include deep neural networks (DNNs), support vector machines (SVMs), tree-based ensemble models, genetic algorithms (GAs), and surrogate modeling approaches. Comparative analyses from the literature indicate that ensemble tree methods, such as XGBoost, have achieved predictive accuracies up to $R^2$ = 0.995 in speed–power modeling, marginally surpassing DNN performance, while GA-based structural optimization studies have reported weight reductions exceeding 10%. The findings confirm that no single method is universally superior; rather, effectiveness depends on the problem definition, data quality, and computational resources available. Hybrid strategies that combine physics-based modeling with data-driven learning have demonstrated improved generalization, reduced data requirements, and enhanced interpretability. Practical challenges remain, including limited access to open high-fidelity datasets, the computational demands of complex models, and balancing predictive accuracy with explainability. The review concludes that AI should be employed as a complementary toolkit to augment human expertise, with method selection guided by design objectives, constraints, and integration within the broader ship design process. Full article