ObjectiveConventional multimodal alignment and fusion methods struggle to adapt to complex underwater detection environments. Owing to the divergences in imaging mechanisms between acoustic sonar and optical cameras, cross-modal features are often spatially misaligned, resulting in degraded fusion performance. This issue significantly limits the accuracy of underwater target detection in turbulent and turbid marine environments. To address these challenges, this study proposes an acoustic-optical multimodal fusion detection architecture for underwater perception tasks. MethodAn end-to-end five-layer detection framework is developed, comprising an input layer, a feature extraction layer, a multimodal fusion layer, a target perception layer, and output layers. Two independent ResNet50 branches are employed to extract multi-scale feature representations from sonar and optical images, respectively. A novel spatial alignment module is designed to estimate affine transformation parameters, including scaling and translation factors, enabling pixel-level spatial registration between modalities. Integrated with channel and spatial attention mechanisms, the dynamic weighted fusion module adaptively adjusts the contribution of each modality, thereby suppressing low-quality and noisy features. Furthermore, a hierarchical interactive fusion encoder incorporating DenseNet and a cross-attention mechanism is constructed to achieve deep complementary fusion of multi-scale cross-modal features. The Transformer decoder and Hungarian matching loss inherited from DETR are utilized for end-to-end target classification and bounding-box regression, eliminating the need for additional non-maximum suppression operation. ResultsComparative and ablation experiments are conducted on a self-constructed real-world paired acoustic-optical underwater dataset. The proposed method achieves an mAP50 of 95.6% and an mAP50-95 of 50.7%, consistently outperforming state-of-the-art unimodal detectors (YOLOv12-X, YOLOv13-X, RTDETR) and advanced multimodal fusion methods (DenseFusion, U2Fusion, SwinFusion). Ablation studies confirm the critical contributions of both the spatial alignment module and the dynamic weighted fusion module to overall detection performance. In addition, noise injection experiments demonstrate that the dynamic weighting strategy exhibits strong robustness against speckle noise and random pixel occlusion in challenging underwater environments. ConclusionThe proposed framework effectively mitigates cross-modal spatial misalignment and fusion degradation between sonar and optical imagery, resulting in significant improvements in underwater target detection accuracy. It delivers a feasible fusion paradigm for underwater multimodal perception.
With the in-depth development of maritime digitalization and the comprehensive application of the S-100 universal hydrographic data model, traditional electronic navigational charts are undergoing a paradigm evolution towards smart charts. Based on the S-100 unified data model and integrating shipborne and shore-based multi-source dynamic information, smart charts serve as a comprehensive navigation intelligent platform that provides spatial analysis, situational awareness and auxiliary decision support for intelligent navigation. Based on systematically sorting out the technical system and research progress of smart charts, this paper summarizes the research from four dimensions: spatial analysis foundation, data model system, visualization expression and application services. In terms of spatial analysis, it analyzes the enlightenment of geographic information technology evolution on chart reconstruction, and discusses the construction of continuous water depth field and spatial interpolation methods; in terms of data model, it explains the architectural characteristics of static basic data, dynamic environmental data and information interoperability model under the S-100 framework; in terms of visualization expression, it analyzes the expression methods in multi-source data integration from two dimensions of production-oriented cartographic visualization and application-oriented spatiotemporal visualization; in terms of application services, it expounds typical application scenarios from four aspects: multi-source data fusion, complex environmental situational awareness, intelligent route planning and risk early warning decision-making. The research shows that smart charts are evolving from basic display tools to comprehensive navigation intelligent platforms, which can provide key technical support for intelligent ships and smart shipping; although its core technical system has been initially formed, it still faces challenges in standardized production, real-time fusion computing, 3D visualization evaluation, human-machine collaborative decision-making and other aspects. This study can provide a reference for the subsequent research in the field of intelligent navigation and smart charts.
ObjectiveAircraft carrier flight deck aviation operations constitute a critical process for generating and sustaining the sortie generation capability of carrier-based aircraft. Their high-risk, highly constrained, and tightly coupled nature places stringent demands on the safety, reliability, and interpretability of intelligent decision-support systems. MethodFocusing on decision support for aircraft carrier flight deck aviation operations, this paper systematically reviews the foundational research on rule-based constraints, situational awareness, and scheduling optimization. It further examines the key challenges associated with the application of large models in this domain, including trustworthy output, multimodal cross-domain fusion, adaptation to diverse operational scenarios, and causal reasoning across multiple operational processes. Using two representative scenarios as case studies—pre-launch coordinated support involving aircraft towing, weapon loading, refueling, and catapult-window coordination, and dynamic replanning during recovery operations under conditions such as arresting-gear malfunctions or parking-space congestion—this paper analyzes task objectives, input modalities, operational constraints, output forms, validation mechanisms, and performance evaluation metrics. Based on this analysis, the paper clarifies how large models can be integrated into practical support workflows. The former scenario emphasizes resource coordination under efficiency and safety constraints, whereas the latter focuses on risk mitigation and recovery-oriented scheduling in the presence of operational disturbances. Together, these scenarios encompass both routine operational planning and contingency-driven reconstruction in flight deck aviation support. On this basis, this paper proposes a large-model-driven decision support framework for high-safety-level aviation support operations. The framework establishes a closed-loop decision-making process integrating generation, verification, screening, and confirmation. First, physical mechanisms, operational regulations, spatial constraints, safety separation requirements, and process dependencies are incorporated into the model generation process. In parallel, external verification is achieved through the integration of rule engines, collision detection, formal verification, discrete-event simulation, and digital-twin-based reasoning. Second, to handle heterogeneous information sources, such as flight plans, deck surveillance videos, target-position time series, voice commands, equipment status data, engineering geometric constraints, and operational logs, a unified multimodal representation and encoding framework is developed to support situational awareness, event correlation, and task-state representation. Third, retrieval-augmented generation, lightweight fine-tuning, prompt templates, and scenario recognition are integrated to establish a domain-knowledge-driven cross-scenario adaptation mechanism, thereby enhancing the model's transfer capabilities across tasks such as launch, recovery, refueling, weapon loading, maintenance, and contingency response. Finally, for continuous operational processes including towing, support, launch, recovery, and maintenance, a process-level causal reasoning and multi-agent collaboration framework is constructed to characterize how local disturbances propagate through downstream tasks, trigger resource reallocation, and drive process reconstruction. Furthermore, considering shipborne edge-computing conditions, an engineering deployment framework is proposed that integrates lightweight inference, local knowledge enhancement, rule- and simulation-based verification, and command workflow integration. Structured outputs are adopted to represent task objects, state evidence, candidate actions, verification outcomes, risk levels, and human-confirmation status.Results The results show that large models for flight deck aviation support should not be employed as direct generators of execution-commands. Instead, they should function as decision-support modules for candidate-scheme generation, situational interpretation, risk assessment, and process-level reasoning within a closed-loop framework incorporating local verification and human confirmation. ConclusionThe proposed framework can effectively mitigate untrustworthy outputs, while enhancing multimodal situational awareness, cross-scenario adaptability, proactive replanning capability, and engineering integration capability. It provides both theoretical foundations and methodological guidance for the safe and controllable application of large models in complex military support systems.
[Objectives]This study aims to investigate the dynamic response and damage evolution mecha-nisms of sandwich structures composed of woven C/C laminates and polymethacrylimide(PMI)foam under low-velocity impact loading,and to clarify the effects of impact energy and key structural parameters on their mechanical performance.[Methods]A numerical simulation model was developed,in which a progressive damage model for the composite laminates was implemented using a VUMAT subroutine,while the PMI foam was modeled using a crushable foam plasticity model that accounts for strain rate effects.A systematic investi-gation was conducted on the dynamic response of the sandwich panels under low-velocity impact,quantitatively evaluating the influence of the foam core's strain rate effect on the simulation results.Furthermore,a sensitivi-ty analysis was performed on the key structural parameters of the sandwich panel.[Results]The results in-dicate that neglecting the strain rate effect leads to a significant underestimation of the dynamic load-carrying capacity of the sandwich structure.The primary failure mechanisms of the C/C-PMI sandwich panels include matrix tensile failure,matrix compressive failure,and foam core crushing.Plastic crushing of the PMI core serves as the dominant energy dissipation mechanism,accounting for 82.3%of the total energy absorption.The maximum indentation depth increases nonlinearly with impact energy,and a transition from non-penetrating damage to local penetration occurs at approximately 60 J under the present configuration.The core-to-face-sheet thickness ratio is identified as the most influential structural parameter;energy absorption efficiency in-creases significantly as the ratio increases to 8.25,whereas further increases promote premature face-sheet penetration and localized core crushing.For naval engineering applications,a core-to-face-sheet thickness ra-tio of approximately 8.25 is recommended for energy-absorbing structures.For decks and bulkheads where global load-bearing capacity and damage tolerance are prioritized,a lower ratio is preferable,with greater em-phasis on increasing the thickness of the front face-sheet.[Conclusions]The results provide a reference for the impact-resistant design and safety assessment of lightweight composite ship structures.
ObjectiveTo address the trajectory tracking problem of underactuated unmanned surface vehicles (USVs) subject to external disturbances and communication constraints caused by limited transmission resources, this paper proposes an improved dynamic super-twisting-algorithm (IDSTA)-based quantized control strategy without velocity measurements. MethodFirst, considering that the underactuated USV system lacks a relative degree in the input-output channel, a virtual input-based dynamic inversion method is introduced to establish the required relative degree. Subsequently, a second-order observer is developed to accurately estimate both trajectory and velocity states in the absence of direct velocity measurements. In addition, a radial basis function neural network (RBFNN) is employed to online approximate unknown nonlinear dynamics. Based on these components, an improved dynamic STA controller is designed to suppress chattering and enhance system robustness while explicitly incorporating input quantization effects into the control framework. ResultsThe simulation results demonstrate that the proposed velocity observer can estimate the actual velocity within finite time. Furthermore, the proposed control strategy achieves high-precision trajectory tracking while maintaining excellent transient and steady-state performance in complex marine environments. Specifically, the position tracking errors converge to within 0.2 meters and the yaw-angle tracking errors are constrained within 0.01 rad. Meanwhile, the communication frequencies in the surge and yaw channels are reduced by 89% and 72.9%, respectively. ConclusionThe proposed control algorithm provides accurate trajectory tracking performance for underactuated USVs through the integration of a velocity observer, a RBFNN, and an improved dynamic STA. The research findings provide a valuable reference for the reliable control of the USVs operating in the complex marine environments.
[Objective]To address low reliability of fault diagnosis in ship motor rolling bearings,caused by weak fault signals and the difficulty of extracting fault features,this paper proposed a feature extraction method that integrates variational mode decomposition(VMD)with wavelet packet fuzzy entropy(WPFE).Furthermore,a support vector machine model optimized by the black-winged kite algorithm(BKA-SVM)is introduced to enhance diagnostic accuracy.[Method]First,collected motor bearing vibration signals are de-composed via VMD,and optimal IMF components are selected by minimum envelope entropy.Next,selected IMFs undergo wavelet packet decomposition to compute fuzzy entropy.Finally,a BKA-SVM model is con-structed for fault diagnosis and classification with extracted feature data.[Results]Simulation experiments with SVM optimized by different algorithms,combined with validation on a self-constructed experimental platform,show that the diagnostic accuracy of the BKA-SVM model for three different sample sets reaches 98.33%-100%.Compared with SVM models optimized by the particle swarm optimization(PSO)algorithm,sparrow search algorithm(SSA)and newton-raphson-based optimizer(NRBO),the BKA-SVM demonstrates superior classification performance and higher accuracy in the extraction and diagnosis of rolling bearing faults.[Conclusion]The findings of this study provide a valuable reference for the fault diagnosis of ship motor bearings.
ObjectiveTo address the challenge in marine propulsion shafting fault diagnosis where fault types can be identified but the faulty equipment is difficult to localize, this study proposes an intelligent diagnostic method that integrates mechanism-based feature modeling with knowledge graph-constrained reasoning. MethodsA three-layer ShaftAgent diagnostic framework is developed. The mechanism modeling layer is used to extract equipment-level vibration features and auxiliary system features. The interpretable analysis layer employs XGBoost for fault classification and introduces an equipment-level SHAP attribution aggregation method to enable automatic localization of faulty components. The knowledge-enhanced reasoning layer is designed to build a hierarchical knowledge graph of “equipment-phenomenon-mechanism-fault”, which, together with multi-stage prompt engineering, guides large language models to generate diagnostic reports. A consistency verification mechanism is further incorporated to ensure that the generated outputs conform to physical laws. ResultsExperimental results show that ShaftAgent achieves a fault classification accuracy of 96.8%, an equipment localization accuracy of 94.2%, and an expert-evaluated comprehensive score of 4.70 for diagnostic reports. Ablation experiments validate the effectiveness of each module. ConclusionThe results indicate that ShaftAgent can effectively address the limitations of traditional methods in terms of insufficient equipment-level localization capability and weak interpretability. Moreover, the study verifies the feasibility of applying large language models to industrial fault diagnosis under knowledge graph constraints, providing a new technical pathway for intelligent operation and maintenance of marine propulsion shafting systems.
[Objective]Accurate and continuous wave-direction perception is an essential prerequisite for shipborne marine environmental awareness,intelligent navigation,route optimization,and safe offshore opera-tions.However,vision-based wave-direction estimation onboard a moving vessel remains challenging,as the observed sea-surface texture is highly susceptible to nighttime low illumination,partial rain-fog occlusion,strong specular reflections,and dynamic vessel motions such as roll,pitch,and yaw.These factors may lead to texture degradation,viewpoint disturbances,image blur,and unstable wave-direction regression.To address these challenges,this paper proposes a multispectral monocular-vision and inertial measurement unit(IMU)-assisted method for shipborne wave-direction estimation to meet all-weather sensing requirements.Dominant wave-direction estimation is treated as the core task,and the feasibility of the proposed method is validated us-ing limited field data collected in real shipborne scenarios.[Methods]A visible-light and long-wave in-frared multispectral imaging system with synchronized attitude acquisition is first constructed.The image streams and IMU measurements are temporally aligned using timestamps,and sequential samples are generat-ed via a sliding-window strategy.To enhance the visibility and stability of sea-surface texture under nonuni-form illumination and low-contrast conditions,contrast limited adaptive histogram equalization(CLAHE)is applied to the input images.A U-Net-based segmentation network is then employed to extract the effective sea-surface region while suppressing interference from the sky,vessel structures,wake,and localized high-intensity reflections.On this basis,a ResNet-18 backbone initialized with transfer learning is used to encode visual features from each frame.The synchronized vessel attitude angles are represented using sine-cosine en-coding to avoid angular discontinuities and are further embedded into the same feature space as the visual rep-resentations via a multilayer perceptron.The visual and attitude features are fused and fed into a lightweight multi-head self-attention module,which models cross-frame temporal dependencies and learns stable direc-tional representations from evolving wave textures.The final wave direction is represented as a two-dimensional unit vector on the angular circle and is recovered using the arctangent function,thereby mitigat-ing discontinuities near the 0°/360° boundary.In a subset of system-level validation experiments,three orthog-onally arranged cameras perform independent inference.Their outputs are verified using geometric consisten-cy constraints,and valid results are fused in post-processing to improve output stability.[Results]Field ex-periments were conducted in the Guangzhou-Zhuhai coastal waters.Under visible-light conditions,the pro-posed method achieved a mean absolute error of 0.41°,a standard deviation of 0.28°,and a success rate of 99.90%for wave-direction estimation.Under long-wave infrared conditions,the mean absolute error was 1.14°,the standard deviation was 0.89°,and the success rate was 98.94%.These results show that visible-light imagery provides clear wave-crest and wave-trough texture cues under daytime illumination,whereas long-wave infrared imaging still preserves effective sea-surface texture information under nighttime and low-illumination conditions included in this study.The multispectral configuration therefore improves the continu-ity of shipborne wave-direction estimation across varying illumination conditions.In addition,the incorpora-tion of IMU-based attitude information and temporal attention modeling helps mitigate the effects of vessel motion and single-frame fluctuations,resulting in more stable wave-direction estimation over time.[Conclusions]The proposed multispectral monocular-vision-IMU multimodal temporal estimation method shows good stability on the collected visible-light daytime samples,long-wave infrared low-light/nighttime samples,and a limited set of complex-environment samples.The results indicate that the integration of multi-spectral imaging,attitude assistance,effective sea-surface extraction,and temporal correlation modeling is fea-sible for shipborne dominant wave-direction estimation.It should be noted that the current dataset does not systematically cover varying rain intensities,fog conditions,or different wind-wave coupling regimes.There-fore,the results should be regarded as a feasibility validation based on limited field data rather than a compre-hensive demonstration of adaptability to all-weather operating conditions.Future work will focus on expand-ing the field dataset,improving model robustness under severe weather and complex sea states,and extending the framework from dominant wave-direction estimation to more comprehensive wave-parameter perception.
ObjectiveTo address the feature drift induced by inter-individual variability in marine main engines and the scarcity of fault data in the target domain, this study leverages digital twin technology and transfer learning to achieve cross-individual fault diagnosis. MethodBased on marine main engine performance parameters and an adaptive mechanism, a digital twin-enhanced cross-individual fault diagnosis model (DT-DANN) is developed. Particle swarm optimization (PSO) is employed to adaptively tune performance parameters factors, aiming to construct a high-fidelity individual digital twin model and generate healthy-state data samples under variable operating conditions. By integrating a multi-scale one-dimensional convolutional neural network (1D-CNN) with an improved domain adversarial neural network (DANN), a healthy-state anchor strategy is proposed to enable cross-individual fault diagnosis for marine diesel engines. ResultsSimulation results demonstrate that the adaptively tuned performance parameter factors achieve a MAPE of 0.052 0%, while the proposed DT-DANN model reaches a diagnostic accuracy of 100%. ConclusionThe proposed method effectively mitigates the model mismatch problem caused by inter-individual variability and data scarcity, enabling high-accuracy zero-shot cross-individual fault diagnosis for marine main engines.
With the evolution of cross-domain unmanned systems, including unmanned aerial vehicles (UAVs), unmanned surface vehicles (USVs), and unmanned underwater vehicles (UUVs), from single-platform employment to mission-chain coordination, the close-in protection of ship formations is increasingly challenged by asymmetric threats characterized by low observability, multi-directional approach, low-cost attrition, and saturation penetration. Accordingly, the focus of protection has shifted from intercepting individual targets to mission-chain identification, degradation, disruption, strike-effect assessment, and terminal mission sustainment. This paper reviews the development and key technologies of maritime multi-domain counter-unmanned systems (C-UxS) protection under confrontation scenarios between ship formations and cross-domain unmanned systems. The discussion focuses on small unmanned threats operating within close-in line-of-sight ranges in low-altitude, sea-skimming, surface, and shallow-water spaces, including small UAVs, sea-skimming loitering munitions, small USVs, small/micro UUVs, divers, and suspicious underwater devices. First, the types of maritime unmanned systems, layered operational scenarios, and mission-chain pressure on traditional ship formation protection systems are analyzed. Then, key technologies are reviewed from four aspects: reconnaissance and early warning, jamming and deception, strike and neutralization, and terminal damage protection, including multi-domain cooperative sensing, communication and navigation suppression, electromagnetic spectrum confrontation, multimodal deception, layered strike, strike-effect assessment, and platform mission sustainment. Finally, a mission-chain-oriented maritime multi-domain C-UxS protection framework based on reconnaissance, jamming, strike, and protection is proposed, and future trends are discussed in cross-domain integration, soft-hard kill coordination, cost-effectiveness balance, damage assessment, and system-level validation.
With the rapid advancement of artificial intelligence, big data, the Internet of Things, and other emerging intelligent technologies, with their deep integration into the military domain, modern naval warfare is undergoing an accelerated transformation from information-centric warfare to intelligent warfare. The intelligentization of surface warships has become a core development direction for naval equipment modernization and major naval powers worldwide. Focusing on the demand for full-life-cycle intelligent upgrading of surface warships, this paper systematically identifies their core development trends and provides an in-depth analysis of the application status and evolutionary pathways of key technologies. The research indicates that the intelligentization of surface warships is characterized by four major development trends: First, design and manufacturing are shifting from experience-driven paradigms to data- and knowledge-driven collaborative approaches, enabling full-process intelligent iteration through generative design, physics-informed neural networks, and digital twin technologies. Second, operation and maintenance is transitioning from manual inspection and scheduled maintenance to minimally manned and autonomous modes, achieving condition awareness, fault diagnosis, and predictive maintenance through ship-shore integrated intelligent systems. Third, perception and decision-making are evolving from traditional sequential architectures into integrated closed loop systems featuring multi-source fusion, autonomous cognition, and real-time decision-making, thereby supporting autonomous navigation and rapid battlefield response of surface warships. Fourth, maritime warfare is advancing from platform-centric confrontation to distributed and networked system-of-systems operations, forming a globally integrated combat architecture characterized by manned-unmanned collaboration, edge autonomy, and high resilience. This paper focuses on key technologies across four major domains: intelligent design and manufacturing, minimally manned operation and maintenance, integrated perception and decision-making, and system-of-systems maritime warfare. The coverage includes parametric design, performance simulation and prediction, digital welding, intelligent fault diagnosis, condition-based maintenance, multi-source data fusion, intelligent decision-making and planning, cluster coordination, and system security. This study provides theoretical support and technical references for the evolution of surface warships in China from localized intelligence toward global system-level intelligence, promotes the overall improvement of the intelligent level of surface warships, and supports the development of future maritime intelligent warfare capabilities.
[Objective]Intelligent ship navigation has become a core technological enabler for accelerating the digital,intelligent and low-carbon transformation of the global shipping industry.Driven by the Interna-tional Maritime Organization's greenhouse gas emission reduction targets and China's strategic policies for in-telligent shipping development,ship intelligent navigation systems are evolving from experimental validation toward engineering applications.However,several key challenges remain in practical implementation.In par-ticular,the coordination mechanism among navigation decision-making,propulsion response,and energy-efficiency constraints lacks a unified architectural representation.In addition,the adaptive mapping logic be-tween shipboard intelligent capability levels and shore-based hierarchical operation modes has not yet been systematically established.To address these gaps,this study focuses on the architectural design of a bridge-engine integrated ship intelligent navigation system and investigates the adaptive mechanisms of ship-shore collaborative operation.[Method]In terms of research methods,this paper firstly defines the functional connotation,system boundaries,and essential characteristics of bridge-engine integration based on existing regulations for intelligent ships and relevant domestic and international research outcomes.Secondly,a hierar-chical intelligent navigation architecture is established.A three-stage evolution pathway for shipboard autono-my is proposed,including enhanced navigation,assisted navigation and autonomous navigation.In parallel,three shore-based operation modes are defined,namely monitoring,remote control,and supervisory naviga-tion.On this basis,an asymmetric ship-shore functional adaptation matrix is developed to systematically clari-fy recommended combinations,restricted feasible combinations,and inapplicable combinations,with typical application scenarios clearly specified.Finally,key enabling technologies are comprehensively analyzed,in-cluding environmental perception and situational awareness,navigation decision-making and path planning control,intelligent engine room operation and energy efficiency management,system testing and evaluation,as well as ship-shore human-machine collaborative control.[Results]The research results systematically present the overall hierarchical architecture of a bridge-engine integrated ship intelligent navigation system under ship-shore collaboration.They clarify the functional connotation and operational boundaries of each shipboard capability level and shore-based operation mode,and reveal the asymmetric adaptation rules and principles of control authority allocation between shipboard and shore-end systems.[Conclusion]It is con-cluded that the proposed system architecture and asymmetric adaptation matrix can provide a solid theoretical foundation and technical reference for the engineering implementation of intelligent ship navigation systems and the development of relevant industrial standards.Furthermore,the findings offer important theoretical guidance for improving ship-shore collaborative operation mechanisms,standardizing control authority switching,and promoting the development and application of a new-generation intelligent and green maritime transportation system.
[Objective]An integrated sensing and communications(ISAC)system operating in a dynamic heterogeneous maritime network environment faces multiple challenges,including frequent node mobility,se-vere time-varying channel interference,and cross-network eavesdropping threats.Conventional optimization methods for sensing and communication scheme design suffer from high computational complexity and lack the capability for real-time adaptation.To address these limitations,this paper proposes an intelligent beam-forming optimization framework based on deep reinforcement learning(DRL).[Method]The proposed framework first formulates the security energy efficiency(SEE)maximization problem as a Markov decision process.The reward function integrates a core SEE term with penalty terms associated with power constraint violation,quality-of-service and sensing constraint violation,as well as a small incentive for feasible solutions,thereby enabling the agent to learn near-optimal policies under multiple constraints.Second,rate-splitting mul-tiple access(RSMA)is introduced to effectively manage cross-network interference between the ISAC net-work and a multicast communication network.By splitting user messages into common and private compo-nents,RSMA enables flexible interference mitigation with low complexity.Third,the concept of"inherent green interference"is proposed,in which sensing signals are exploited as an effective jamming source against eavesdroppers.The proximal policy optimization(PPO)algorithm is employed to address the high-dimensional continuous action space.To accelerate training and improve adaptability,a hybrid training mechanism combin-ing supervised pre-training(based on offline data generated by conventional optimization methods)and online fine-tuning is adopted.[Results]Simulations are conducted under typical offshore parameters,including a carrier frequency of 18 GHz,a typical transmit power of 35 dBm(within the maximum power limit of 40 dBm),and a multicast user number of N=3.In addition,a parametric sensitivity analysis is performed for N=2 to 12.The proposed DRL-RSMA scheme achieves a median SEE of 2.45 bit/J,representing a 22.5%im-provement over the conventional RSMA-based alternating optimization scheme(2.00 bit/J).The online infer-ence latency of DRL-RSMA is only 0.85 ms,with a standard deviation of 0.05 ms,satisfying the sub-millisecond latency requirement for 5GA/6G ultra-reliable low-latency communications.The hybrid training mechanism accelerates convergence by approximately 58.3%compared with conventional DRL approaches.Under periodic topology mutations occurring at time steps 50,100,and 150,DRL-RSMA maintains an aver-age SEE of 2.41 bit/J,achieving a 14.1%improvement over RSMA-based alternating optimization.In the pres-ence of channel state information(CSI)estimation errors with an error bound of up to 0.3,DRL-RSMA re-tains 91%of its optimal SEE,demonstrating superior robustness compared with RSMA(83%),NOMA(79%),SDMA(75%),and OMA(69%).Parameter analysis further reveals that SEE initially increases and subse-quently decreases with transmit power,reaching a maximum value of 3.10 bit/J at 35 dBm.As the number of multicast users increases from 2 to 8,SEE improves to 2.75 bit/J;however,performance gradually declines when the number exceeds 8.Notably,DRL-RSMA still maintains 94%of its peak performance at N=12,indi-cating strong scalability.[Conclusion]The proposed DRL-RSMA scheme jointly enhances three key per-formance metrics in complex maritime environments,i.e.,SEE,real-time response,and robustness.It pro-vides a novel solution for intelligent resource management in the ISAC and shows strong potential for practi-cal deployment in dynamic maritime scenarios characterized by imperfect CSI and topology variations.
ObjectiveThis study addresses oscillatory instability in trajectory tracking errors of unmanned surface vehicles (USV) caused by propulsion saturation under complex navigation conditions. A prescribed-performance reinforcement learning-based optimal control method is proposed. MethodFirst, a novel saturation function is introduced to handle USV input saturation. Second, an improved prescribed performance control scheme is designed, in which tracking error convergence is constrained by an asymmetric performance boundary, thereby relaxing the strict dependence on initial error conditions. Then, a reinforcement learning optimization framework based on an Actor-Critic architecture is constructed to iteratively learn the optimal control policy and value function, enabling performance optimization under state constraints. Finally, the stability of the closed-loop tracking system is rigorously proven using Lyapunov stability theory. ResultsNumerical simulations conducted on the KVLCC2 tanker model demonstrate that the proposed method effectively addresses trajectory tracking under saturation constraints, with all tracking errors strictly confined within the prescribed performance boundaries. ConclusionThe study provides a new solution for high-performance tracking control of constrained USVs and demonstrates strong potential for practical engineering applications.
Escalating maritime security demands higher comprehensive stealth,energy efficiency,structural re-liability and multifunctional integration performance for naval vessels.Conventional design modes dependent on metal materials and empirical design suffer inherent drawbacks such as long R&D cycles and high costs.Against this backdrop,the collaborative innovation of new functional-structural integrated materials and intel-ligent design has become a core route to break through the performance bottlenecks of naval vessels.This pa-per systematically reviews the research progress of marine new materials and intelligent design technologies,and analyzes their synergistic relationship and engineering constraints.In terms of new materials,fiber-reinforced polymer composites(carbon,glass,aramid fiber composites)feature outstanding specific strength,corrosion resistance and designability,and are widely adopted in hulls,superstructures,propellers and pres-sure cabins.Composite sandwich structures(foam,balsa,honeycomb,foldcore,lattice core)further realize lightweight design and integrate sound absorption,heat insulation and anti-impact functions.As a new type of artificial material,acoustic metamaterials(phononic crystals,local resonance structures,Helmholtz resonators,acoustic cloaks)solve the low-frequency wideband sound absorption defects of traditional materials and pro-vide new ideas for underwater acoustic stealth.Artificial intelligence technologies reconstruct the functional-structural integrated design system of ships.Artificial neural networks act as high-efficiency surrogate models to rapidly predict mechanical and acoustic properties of composite materials and metamaterials.Generative large models can create innovative topological structures to expand the design space beyond empirical limits.Intelligent optimization algorithms handle multi-objective and multi-constraint optimization tasks to balance lightweight,bearing and stealth performance.The closed-loop"generate-predict-optimize"design framework greatly shortens design cycles and maximizes material performance potential.This paper further summarizes the key engineering bottlenecks.For novel marine materials,the main challenges include large-scale forming stability,long-term marine aging degradation and recycling difficulties.For intelligent design methods,criti-cal limitations lie in insufficient professional datasets,poor interpretability of black-box AI models and the dis-connection between design optimization and manufacturing constraints.In the end,this paper prospects future research trends,including multifunctional composite integration,cross-scale multi-physics coupled design,in-terpretable intelligent design systems and full-lifecycle structural intelligent management.This review pro-vides theoretical support and technical references for the development of high-performance,lightweight and intelligent naval vessels.
Shipborne rotorcraft UAVs, characterized by high maneuverability, vertical take-off and landing capabilities, and superior environmental adaptability, serve as critical platforms for conducting highly dynamic collaborative detection missions in complex maritime conditions. Motion planning technology is a key enabler for ensuring mission effectiveness. This paper first summarizes the key technologies involved, including dynamically constrained feasible trajectory modeling, complex maritime environment perception, and collaborative localization. It then systematically reviews and categorizes the state of the art in related research both domestically and internationally into four major categories: spatial geometric constraint-based path planning, space-time trajectory optimization under differential flatness constraints, learning-based maneuver decision-making, and multi-UAV collaborative motion planning. The maneuverability and real-time performance of these approaches are further analyzed and compared. Finally, in response to existing technical challenges, future development trends and research directions are proposed, including deep collaboration tailored to complex shipborne environments, LLM-enabled high-level decision-making, and end-to-end reactive maneuvering within an embodied intelligence framework. These efforts aim to provide technical references for the autonomous and intelligent development of future shipborne UAV swarms.
ObjectiveTo address the challenges of balancing accuracy and computational efficiency, excessive mesh density under high-frequency incidence conditions, and high computational resource consumption in the RCS calculation of large-scale array antennas, a subarray extrapolation method based on Gordon's integral method is proposed. By utilizing full-wave simulation results of small-scale subarrays, the RCS characteristics of large array antennas can be efficiently and accurately extrapolated. Method Considering the differences in the spatial characteristics of array elements, the entire array is divided into several typical subarray units, and the aperture fields of these units are extracted from different regions. Gordon's integral method is introduced to convert the two-dimensional surface integral into a line integral along polygon boundaries, thereby accelerating the near-field-to-far-field transformation, reducing mesh density requirements, and improving the computational efficiency of equivalent surface current calculations. A spatial extrapolation mapping of scattering characteristics is achieved through phase correction factors, and the overall scattering field of the target array is subsequently obtained.Results For Vivaldi array antennas and multi-layer stacked patch array antennas, the proposed method is validated through monostatic and bistatic RCS extrapolation experiments, respectively. Compared with full-wave simulation results, the proposed method achieves a threefold increase in computational speed while maintaining a relative root mean square error of less than 5%.Conclusion The proposed RCS extrapolation method achieves both high computational accuracy and excellent efficiency, providing an efficient and reliable approach for RCS calculation of large-scale array antennas.
Against the background of intelligent transformation and high-quality development in the shipbuild-ing industry,large models represented by large language models(LLMs)and multimodal large models have gradually become core technologies driving the intelligent upgrading of the entire ship life cycle.This paper systematically reviews the research progress of integrating large model technologies with the shipbuilding in-dustry,and clarifies the technical principles,capability boundaries and existing limitations of large models in engineering applications.By summarizing the development route of artificial intelligence and the underlying mathematical logic of large models with Transformer as the core architecture,this study analyzes the key capa-bilities of large models in natural language interaction,multi-step reasoning,multimodal understanding,few-shot learning and code generation,as well as inherent defects such as hallucinations,weak causal reasoning and poor real-time performance.According to the engineering characteristics and safety requirements of the shipbuilding industry,this paper proposes three basic application principles for large models:1)introducing ship industry knowledge as constraints to improve output reliability;2)taking large models as planning en-gines to realize the decomposition of complex tasks and the collaboration of professional tools;3)and building multi-agent systems with large models as the decision-making center to support autonomous decision-making and closed-loop execution.Guided by these principles,this paper sorts out and evaluates the application cases of large models in four typical scenarios:ship design,ship manufacturing,operation and maintenance,and navigation decision-making.It is found that the knowledge-constrained scheme is suitable for standardized scenarios such as rule compliance and design consulting;the planning engine framework is efficient in com-plex task decomposition;and the agent system shows unique advantages in autonomous decision-making and multi-ship collaboration.Furthermore,this paper discusses the technical bottlenecks restricting the large-scale engineering implementation of large models in the shipbuilding industry,including data quality and gover-nance,real-time response for navigation control,decision interpretability and safety verification.On this basis,a step-by-step integration idea of"technology alignment-scenario adaptation-system implementation"is put forward to promote the reliable landing of large models in the whole life cycle of ships.Finally,the future de-velopment trends are prospected from the aspects of multimodal fusion,causal reasoning enhancement,human-in-the-loop reinforcement learning and digital twin-driven simulation verification.The conclusions and meth-ods of this paper can also provide theoretical references and practical guidance for the intelligent transforma-tion of other complex industrial fields such as aerospace,astronautics,energy and electrics.
To meet the requirements of green, intelligent, and high-quality development in the shipbuilding and marine engineering industries, fiber-reinforced polymer (FRP) composites have emerged as one of the most critical lightweight structural materials, owing to their high specific strength, excellent corrosion resistance, and superior design flexibility. However, the large-scale and standardized application of marine FRP composites is still constrained by several key challenges, including the lack of unified performance standards, incomplete risk control and verification systems, insufficient long-term durability evaluation, and immature full-life-cycle management mechanisms. This study proposes a systematic engineering implementation framework for the application of marine FRP composites across the full life cycle. First, the development status of marine FRP composites and the latest specifications and guidelines issued by the International Maritime Organization (IMO) and leading classification societies (DNV, BV, CCS) are comprehensively reviewed and compared. Second, the key constraints limiting the widespread adoption of FRP materials are analyzed from the perspectives of material performance, industry standardization, risk identification, and engineering validation. Subsequently, with a focus on green application, material inventory management, recyclable design, and intelligent maintenance, novel requirements for full-life-cycle maintenance systems are proposed. Finally, by integrating risk control theory, digital technologies, and artificial intelligence, a systematic engineering implementation pathway is constructed, covering design assessment, collaborative simulation, manufacturing inspection, and full-life-cycle operation and maintenance. The results indicate that FRP composites offer significant advantages in structural lightweighting, energy efficiency, and corrosion resistance. However, unified performance standard system, long-term degradation mechanism, and full-life-cycle verification system still require further development. The proposed framework supports the safe, green, and intelligent application of FRP materials in ship structures and provides a technical foundation for their standardized adoption. Future research should focus on multi-fidelity modeling, multi-objective collaborative optimization, recyclable material development, and digital twin-based intelligent maintenance to further enhance the engineering applicability and robustness of marine FRP technologies.
ObjectivesTo address the acute contradiction between the extremely high power demands of high-energy pulsed weapons and the requirement for full-spectrum stealth capability, this paper systematically reviews research progress and challenges in integrating energy adaptation and stealth coordination within shipboard integrated power systems. MethodsA systematic review methodology is employed to establish a three-dimensional collaborative analysis framework integrating energy, stealth, and intelligence. Within this framework, an in-depth assessment is provided of energy management strategies for pulsed power adaptation, global signal management techniques, and intelligent collaborative design methods based on digital twin technology. Furthermore, the study systematically reviews the current state of research on key technologies such as hybrid energy storage system topologies, multi-physics-based characteristic signal suppression, and cross-domain collaborative decision-making mechanisms. ResultsIn terms of energy matching, hybrid energy storage systems are widely recognized as a mainstream solution for mitigating pulsed power impacts and ensuring grid stability. Regarding stealth coordination, active control technologies such as digital degaussing and active noise control are increasingly replacing traditional passive suppression methods. At the system integration level, the introduction of artificial intelligence and digital twin technologies shows strong potential for addressing challenges related to millisecond-level dynamic response requirements and inefficient R&D iteration cycles. ConclusionsTheoretical research and technical analysis indicate that establishing an integrated collaborative design framework for precise energy supply and intelligent signal control is a fundamental approach to addressing compatibility challenges associated with high-energy weapons aboard naval vessels. In particular, intelligent dynamic trade-off control and cross-domain collaborative optimization are expected to become key future research directions, carrying significant strategic importance for enhancing the combat effectiveness and survivability of next-generation naval vessels.
