As a strategic national asset ensuring the security of China’s energy resources, the summer extreme heat environmental condition and complex air flow composition of the ocean drilling vessels have become one of the key challenges in the design and construction. By establishing the balance formula of air volume inside a galley, this study sorts and analyzes the airflow parameters such as air conditioner air supply, air intake outside and inside the cabin and air mechanical exhaust. Based on the cooling capacity calculation method for fresh air conditioners specified in ISO 9943:2009, and incorporating personnel comfort requirements, this study proposes a solution for adjusting air conditioning cooling capacity parameters under extreme heat conditions exceeding standard environmental design specifications. Using an ocean drilling vessel as a case study, calculations were performed to develop recommended cooling capacity parameters for such extreme conditions on this vessel. This provides a reference for engineers to clarify air flow composition in complex cabins and to select appropriate cooling equipment under extreme heat environments.

Ropes are critical components for mooring ships and offshore floating structures under periodic axial loads. To investigate the tensile properties and stiffness characteristics of deep-sea mooring polyester ropes, they are categorized into three stages: preloading, initial installation, and aging. Initially, the tensile properties of the ropes under static loads are examined, quantifying strain and reversible elongation rates at each stage and comparing mechanical properties of polyester ropes with those of nylon ropes. Subsequently, creep coefficient solution tests under varying tensions are designed, establishing a quasi-static stiffness empirical equation with consideration of the rope creep coefficients. Experiments have shown that the mooring ropes still undergo reversible elongation after unloading, and sufficient break-in period of the ropes can reduce their inherent deformation and increase their structural stability. Static stiffness of the ropes increases with loading time and force until it reaches a constant value. Polyester ropes have greater stiffness, smaller deformation and more stable structure than nylon ropes, making them more suitable for deep-sea mooring. The findings enable comprehensive analysis of rope stiffness evolution throughout its service life, thereby offering references for reasonable design of deep-sea taut-line mooring systems.

High-precision localization of pipeline damage using acoustic emission technology in the marine environment remains challenging. A hybrid path optimization-based localization method for structural damage source localization is proposed. First, the short-time Fourier transform (STFT) maps acoustic signals into the time-frequency domain, with K-means cluster grouping signals to separate different damage sources. Subsequently, the ROTH dual-weighted cross-correlation algorithm is employed to accurately estimate the time difference of acoustic wave arrivals at sensors under strong noise conditions, extracting temporal characteristics of the acoustic waves. Next, an initial propagation path is generated via the Rapidly-exploring Random Tree (RRT) algorithm, and further optimized through an improved D* dynamic path optimization algorithm to determine the optimal propagation path. Finally, acoustic emission source locations are calculated by using hyperbolic equations and weighted least squares based on geometric localization methods. Experimental results demonstrate that this method can accurately locate the structural damage source in complex environments, significantly outperforming traditional approaches.

The Western-Pacific region contains abundant polymetallic nodule resources. Effectively exploiting these resources is of great significance for the metal resources supply in China. To verify the feasibility of deep-sea mining and achieve commercial mining, it is necessary to conduct in-situ sea trials of the mining system in the mining area and develop environmental monitoring procedures to assess the impact of the mining operations on the environment. This study focuses on the monitoring content and monitoring plans by establishing a set of environmental monitoring and impact assessment procedures. It details the environmental monitoring procedures for sea trials across pre-trial, in-progress, and post-trial phases. The results show that polymetallic nodule mining is feasible in the Western-Pacific region. However, the impacts of mining plumes and sediments on the bottom marine ecosystem should be considered carefully, alongside the formulation of effective mitigation measures.

The Hangzhou-Ningbo Canal is of great significance to the economy and material circulation in the eastern Zhejiang region. This study focuses on the automatic modeling and hull form optimization of container vessels sailing in the Hangzhou-Ningbo Canal by coupling CAESES with computational fluid dynamics (CFD). First, the hull structure is deformed based on semi-parametric modeling. A new hull form is iteratively generated according to the geometric parameters given by the optimization algorithm. In each iteration, the hydrodynamic performance of the hull model is solved by using CFD software to provide geometric parameters for the next iteration. The optimal hull form is eventually identified in the geometric configuration space through this iterative process. The results show that the optimized hull form achieves a drag reduction of 5.8%, and the pressure distribution on the hull surface is significantly improved, with a reduced negative pressure area and less stress concentration. This study can provide theoretical and technical support for the hull form optimization of inland container vessels.

The design ideas, key technologies and construction process of a shipborne paleomagnetic laboratory in low magnetic field environment are elaborated based on the construction of a paleomagnetic laboratory for an ocean drilling vessel. The article begins with a brief introduction to the basic principles and research significance of paleomagnetism, and the current technical development status of shipboard paleomagnetic laboratories. The overall design scheme and construction process of the shipboard paleomagnetic laboratory are then elaborated in detail, including the simulation design of the paleomagnetic laboratory, the optimization of the laboratory layout, the innovative structural design, the magnetic shielding technology, the vibration and noise reduction control, and the key construction technology. The key performance indicators, such as the average residual magnetic field in the laboratory and the overall shielding effect, meet the requirements for shipboard paleomagnetic laboratories through the optimization of structure, equipment and material selection, and the innovative application of technologies of hole optimization simulation design, flexible support design, and special construction technology for shielding layers. Finally, a scientifically reasonable debugging and measurement scheme is introduced for detecting the magnetic shielding effectiveness of the shipboard paleomagnetic laboratory, which fully verifies the feasibility and effectiveness of the design and construction of the low-magnetic environment paleomagnetic laboratory.

To enhance the stability and safety of the underwater structure of the submersible pressure hull, this study focuses on its multi-objective optimization design, aiming to achieve a synergetic improvement of quality, strength and stability. The parametric analysis process is used to analyze the initial ring-stiffened pressure shell scheme, using the optimal Latin hypercube sampling method to explore the influence of design variables on target responses. A high-precision response surface model and a multi-objective optimization model are also established, thereby enabling the multi-objective optimization of the pressure hull using the NSGA-II genetic algorithm. The results show that among the four optimized schemes, the weight of scheme A and scheme C is reduced by 7.3 kg and 6.6 kg, respectively, while the ultimate strength of scheme B and scheme D is increased by 0.177 MPa and 0.031 MPa, respectively. It is confirmed that the multi-objective optimization method integrating response surface models and genetic algorithm can effectively improve the performance of submersible pressure hull. It can provide a valuable reference for the design of deep-sea exploration equipment.

The analysis object of this paper is a cylindrical pressure shell with a single orthogonally nozzle and reinforcement structures, consisting of a nozzle wall and an insert plate. Taking the non-iteration design process of the reinforcement structures of this cylindrical pressure shell as an example, this paper proposes a non-iteration design method based on the gradient boosting decision tree (GBDT). This work provides a reference for the design of structures without the need of iteration design process. The non-iteration design method proposed in this paper includes three parts: dataset generation, generation of the non-iteration design surrogate model, and development of a dedicated APP for non-iteration design. Firstly, a machine learning dataset is obtained by the parametric finite element analysis through ABAQUS-Python for the reinforcement structures of the cylindrical pressure shell. Then, based on the Gradient Boosting Decision Tree and the multi-output regressor, a non-iteration design surrogate model is generated based on the dataset. Finally, a dedicated forward design APP (HUST-FWD01) is developed to standardize the non-iteration design and verification processes for the reinforcement structures. The results show that the dimensions of the reinforcement structure can be obtained without the need of iteration by the non-iteration design surrogate model, which is generated based on the non-iteration design framework proposed in this paper. In the surrogate model, the maximum stress near the opening of the pressure shell is used as the input, and the dimensions of the reinforcement structures are the outputs. The verification examples show that the errors are all within 3% between model inputs and the FEA results corresponding to model outputs. The research results can provide a design method without the need of iteration for the reinforcement structures of cylindrical pressure shell with a single orthogonally hole as well as the structures akin to them.

Currently, marine security is becoming increasingly severe, with incidents of harassment, attack, and sabotage against vessels occurring frequently. Aquaculture vessels, operating long-term in deep seas, are particularly susceptible to various forms of harassment, attack, and sabotage, which seriously threaten their safe operation. Additionally, aquaculture vessels also face significant internal security risks. It is therefore necessary to establish a complete security system for the aquaculture vessels to ensure their safe operation. The potential security risks are categorized into external risks and internal risks based on the characteristics of an aquaculture vessel. Accordingly, it constructs the external and internal risk security systems, clarifies the overall composition and workflow of the external security system, and establishes a “scenario-personnel” double closed-loop laboratory security system, as well as proposes specific security measures against violent and terrorist crimes. From the perspectives of monitoring, emergency, and supervision, an integrated security system is established to ensure the safe operation of aquaculture vessels.

Emergency risk assessment provides a basis for offshore operators to identify hazards, reduce risks to an appropriate level and protect people from the impact of accidents. The aquaculture vessel will be affected by adverse natural conditions during navigation and operations, not only facing risks such as collision and grounding, but also encountering additional emergencies arising from engineering operations such as mooring operations and aquaculture farming. It is therefore necessary to carry out risk assessment for the emergencies it faces. Firstly, the characteristics of the aquaculture vessel is analyzed. Subsequently, the types, probabilities, causes, processes, and severity of potential emergencies throughout the whole process of the navigation and operation of the aquaculture vessel are examined based on these characteristics. Finally, a risk assessment of the emergencies faced by the aquaculture vessel is conducted to develop a FMEA worksheet by using the failure mode and effects analysis (FMEA) method. It provides valuable date decision support for emergency decision-making and emergency management system construction.

As the core equipment for deep-sea aquaculture, the hydrodynamic research on ship-shaped aquaculture cages is crucial for ensuring their structural safety and farming reliability under extreme sea conditions. This paper systematically integrates the framework of "theoretical research-numerical simulation-model validation" used in the hydrodynamic study of ship-shaped aquaculture cages and reviews the relevant hydrodynamic analysis theories. The research status is reviewed from three aspects: hydrodynamic responses of the hull and mooring system, hull structural strength, and fluid-structure interaction effects of the netting. Furthermore, the key challenges in the hydrodynamic analysis of ship-shaped cages are analyzed: the complexity of multi-physics strong-coupling modeling, the accuracy-efficiency trade-offs in netting simulation, the bottlenecks in predicting nonlinear responses under extreme environments, and the lack of full-scale validation data. Finally, four future research directions are proposed: developing a multi-field wave-structure-mooring-netting interaction model, advancing the refined modeling technology for complex marine environments such as typhoons and internal waves, introducing intelligent algorithms to optimize the dynamic response of mooring systems, and developing hydrodynamic optimization and control technologies for intelligent submersible systems. This review provides theoretical support for the hydrodynamic mechanism research and engineering safety application of ship-shaped aquaculture cages.

In underwater hull cleaning tasks, the detection and precise identification of fouling and obstacles by target detection technology are critical for enhancing the efficiency of automated cleaning. The current underwater-hull cleaning robots primarily rely on manual visual inspection for environmental perception and target localization, which imposes efficiency bottlenecks and safety hazards. An improved model, YOLO-HC, is proposed based on the YOLOv11 framework. The model enhances cross-scale feature extraction capability by constructing a Multi-scale Dilated Attention module (MSDA_C2PSA), optimizes multi-level target representation fusion by using a Bi-directional Weighted Feature Pyramid, and further improves detection robustness by integrating multiple attention mechanisms into the dynamic detection head. In experiments on a self-built underwater hull surface dataset, the model achieved 87.0% and 62.4% on the mAP@0.5 and mAP@0.5:0.95 metrics, with increases of 2.2% and 3.4% compared to the baseline model, respectively. It provides an accurate and efficient target detection method for underwater hull cleaning tasks, advancing the goal of intelligent and unmanned hull cleaning.

This article summarizes the four main stages of the development of international ocean scientific drilling: deep sea drilling project, international ocean drilling program, integrated ocean drilling program and international ocean discovery program, and introduces the main scientific achievements obtained during each stage. China also participated in the above stages, leading four voyages across three ocean scientific drilling projects, and achieved a series of scientific achievements in the South China Sea. The development of international ocean scientific drilling is closely related to the development of ocean drilling vessels. The development of worldwide ocean scientific drilling equipment is chronologically introduced with a focus on the technical characteristics of China's first ocean scientific drilling vessel, the “Mengxiang”. Finally, the development of the ocean scientific drilling technology is analyzed based on the development history of the ocean drilling and the update and iteration of the ocean drilling vessels. It can provide references for the development of the international ocean scientific drilling.

Corrosion and biofouling impose serious hazards to the normal operation of marine propellers. The current research on the protection methods for marine propellers focuses on the propeller material itself, with insufficient attention to the propeller protective coating technology. This study introduces the anti-fouling principle of low surface energy fouling-release coatings and the development of relevant technologies, discusses the prospects and development directions of organosilicon-modified low surface energy anti-fouling coatings applied to marine propellers, and looks to the future development of anti-fouling coatings for marine propellers.

The epidemic prevention assistant robot refers to an automated device designed to assist crew members in epidemic prevention. In maritime epidemic prevention, the application of such robots onboard helps reduce the workload of crew members and mitigate the risk of epidemic transmission. Based on existing technical documents and market product information, combined with practical requirements, this study analyzes the feasibility of deploying two conventional functions—delivery and disinfection—of epidemic prevention assistant robots on ships. It further compares and analyzes their advantages over alternative methods. To implement the delivery and disinfection function of the robots onboard, the adaptability of key technologies for these conventional functions of the epidemic prevention assistant robots is demonstrated and analyzed around the issues such as ship oscillation during navigation and limited compartment spaces. Technical recommendations for shipboard robot applications are then provided.

With the increase of the installed engine power and redundancy requirements, the specification of the engine room ventilation system has been expanded, imposing difficulties on the design and layout of the engine room. A compound engine room ventilation system is introduced by combining frequency conversion fans and water-cooled internal circulating system. The CFD method is utilized to simulate a ship under several basic working conditions, optimizing the parameters of engine room fans, the layout of engine room air coolers, and the nozzle angles of jet fans. The results show that the compound engine room ventilation system effectively reduces the specification of the engine room ventilation with improved economy and flexibility. It can provide a reference for the design of engine room ventilation system for similar vessels.

Hydrogen fuel cells have emerged as an important development direction for future marine power sources. With rapidly increasing complexity in ship power systems, traditional document-centric systems engineering methods fail to meet the research and development demands for rapid iterative of hybrid power systems. To address this, a design and verification method is proposed for the hybrid power system of hydrogen-fueled ships based on Model-Based Systems Engineering (MBSE) method. Firstly, the SysML language is employed to perform the hierarchical decomposition modeling at the overall, system and subsystem levels according to the requirement definition, functional analysis and logical design based on the overall engineering requirements. The functional logic rationality of the model is then verified through the integrated simulation verification of the model. Finally, a Simulink simulation model is built to simulate and calculate the performance parameters of the hybrid power system of the hydrogen-fueled ship. The feasibility of the design and verification process and the effectiveness for the design iteration of complex systems are validated on the hybrid power system of a hydrogen-fueled ship. It can provide a reference for the application of MBSE method in other ships.

The migration of China's ship design software to domestic platforms becomes crucial for enhancing national innovation autonomy and reducing technological dependence against intensifying international competition. However, conventional domestic cross-platform strategies, such as system reconstruction or Browser/Server (B/S) architecture conversion, remain incompatible with ship design software. The domestically developed NuCAS system is examined to explore a new cross-platform migration strategy for message mechanisms applicable to shipbuilding industrial software. Through in-depth analysis of the technical framework and code structure of the message mechanism of the NuCAS system, multiple migration strategies are evaluated to innovatively proposed a migration strategy that rewrites the underlying core message mechanism of MFC (Microsoft Foundation Classes, a Windows API class library) based on the cross-platform Qt framework while preserving the upper-layer application code. This strategy successfully resolves the challenge of the seamless conversion of message mechanisms between MFC and Qt frameworks. The results demonstrate that the modified NuCAS system operates stably on domestic platforms, meeting the localization requirements of ship design software. It provides a groundbreaking approach for the cross-platform migration of message mechanisms in shipbuilding industrial software.

To address the issues of high training costs and low efficiency in conventional manual hull modeling methods, an intelligent software for 3D geometric hull model generation from 2D lines plan has been developed, enhancing the automation of modeling and production efficiency. This modeling software, which is developed and designed using python, simulates the human visual system to extract, analyze and interpret the hull lines information from 2D drawings in units of pixel clusters. First, it reads, identifies and processes 2D lines plan (JPEG or PNG format) obtained from screenshots or scans, and maps the 2D profile points to 3D point cloud data according to the spatial relationships among the three views. Then, it generates the hull surface through information densification, thereby simplifying the modeling process from 2D plans to 3D models. Finally, accuracy verification results show that the modeling software based on computer vision technology can quickly convert the 2D lines plan in image form into the 3D hull models, demonstrating its reliability.

A three-dimensional (3D) parametric modeling method is proposed for structural design, combining a design logic-based modeling approach with a parametric modeling approach. By utilizing the linking mechanism of CATIA V6 software, the structural design hierarchy and 3D modeling hierarchy are unified, reflecting design relationships through model associations among 3D features to form a layer-driven 3D model. The user-defined feature-based parametric method addresses the stability limitations of traditional modeling methods while enabling batch control of design objects through parametric tools, significantly improving design efficiency. Furthermore, this method has been applied to the structural design and preliminary design calculations for a ship’s cargo hold, with results being validated. The presented method can provide references for the 3D structural design of other ship types.

In the era of digital transformation, to address uncertainty, improve quality and efficiency, and enhance enterprise profitability, integrating digital technology into ship design technology to reconstruct a full three-dimensional (3D) ship design model has become a design development trend. A model-based integrated 3D digital design definition and technical connotation are proposed by using Hexagon Smart 3D as the 3D design platform. The solutions for 2D-driven 3D rapid modeling, integration of CAD/CAE, integration of detailed design and production design, 3D submission for approval and design tool development are also discussed. A number of design tools are developed based on parametric modeling and knowledge-driven approaches, forming a modeling strategy and design master schedule (DMS). This addresses the integration of CAE/CAD and the integration of detailed design and production design, enabling the share and reuse of the unified data sources and model data, as well as the 3D design collaboration among various design departments. The research results have been applied in merchant ships and cruise ships, laying a solid foundation for reconstructing the fully 3D design model of ships.

Considering that the research on intelligent ship technology in China is still developing, intelligent ship systems have not yet been widely applied in large ocean-going carriers. The design principles are formulated for the intelligent ship system scheme of a 14 000 TEU container ship in compliance with the class notion requirements. According to the actual configuration of the hardware facilities for data sampling in the perception layer of this ship, an integrated architecture is developed by combining the intelligent ship integration platform with various intelligent application functions. The system composition, data utilization, and functional implementation of intelligent navigation, intelligent engine room, and intelligent energy efficiency management system are introduced in detail. The results indicate that the system can achieve intelligent upgrades in route optimization, system monitoring, energy consumption control, decision-making support, and ship management for operating ships. The network security protection strategies are implemented for the risks existing in ship shore data interaction. It provides the selection basis and optimization direction for the future engineering applications of integrated ship intelligence.

To improve the efficiency of ship entry into the lock chambers and intelligently guide the ship into the ship lift chambers safely and efficiently, the Markov decision-making model is used to model the ship entry process based on the reinforcement learning method. The model training results are compared to identify the optimal solution by setting different reward functions and time steps. Subsequently, an intelligent navigation aid system is obtained by software development. Finally, a sea trail is conducted by using a typical ship passing through the lock chamber. The results show that the optimal maneuvering strategy not only reduces the number of operations but also enables faster arrival at the destination. Furthermore, the theoretical entry time planned by the navigation aid system is 124 seconds shorter than the actual entry time, corresponding to a 34.4% reduction in entry time. The research can provide references for the intelligent guidance of ship entry into the lock chambers.

To address the complexities, high costs, and iterative challenges between theoretical research and practical deployment in the recovery process of multi-unmanned surface vehicles (USVs), a virtual-real simulation method and system have been designed based on virtual-real data synchronization mechanisms and high-fidelity rendering via Unity 3D technology. This approach enables simultaneous theoretical research and practical debugging, effectively reducing iteration cycles and lowering costs. The system comprises physical USVs, virtual USVs, and a USV virtual testing platform, and the corresponding method is implemented through this system architecture. Physical USVs generate motion state data through their hardware, software systems, and recovery control strategies, while virtual USVs produce corresponding data through simulations. Through real-time synchronization and interaction of virtual-real data, the constructed USV virtual testing platform facilitates high-fidelity state monitoring, intuitive visualization, and high-confidence validation of recovery strategies. Comprehensive experiments indicate that this method can replace large-scale physical deployments with small-scale physical tests, fully integrating the advantages of real hardware and virtual environments to enable efficient, safe, and low-cost validation of multi-USV recoveries. Furthermore, the designed virtual-real simulation method and system provide a convenient and efficient testing platform for validating the recovery process of larger-scale USV formations and clusters.

Autonomous navigation systems serve as the foundation for unmanned surface ship operations, with local path planning algorithms being crucial components of these systems. The local path planning algorithms for unmanned surface ships are systematically reviewed, focusing on commonly used algorithms including the A*, Artificial Potential Field, Rapidly-exploring Random Trees, Dynamic Window Approach, Velocity Obstacle and intelligent optimization algorithms. It analyzes their fundamental principles, strengths and limitations, and summarizes their applications in path planning of unmanned surface ships. Current local path planning algorithms have demonstrated practical utility in simple scenarios such as open waters. However, significant challenges remain in complex situations, primarily due to high-density unstructured navigation environments, highly dynamic and strongly nonlinear environmental disturbances, and multi-constraint, multi-objective mission scenarios. It is recommended to further investigate the constraint-loading mechanisms of maneuvering motion models, advance multi-algorithm collaborative planning theories for full-mission scenarios and develop large model-driven decision-making and planning methodologies for unmanned surface ships. These efforts aim to address local path planning challenges in complex environments and missions. It can provide systematic references for theoretical research and engineering applications of local path planning technologies for unmanned surface ships.

Maritime autonomous surface ships (MASS) represent a critical direction for the development of current maritime industry. Their health development requires support from a comprehensive equipment system. Aligned with the International Maritime Organization’s Maritime Autonomous Surface Ships Code framework, this study focuses on the implementation of remotely operated vessels with autonomous capabilities. Through systematic analysis of the technological requirements for autonomous marine equipment, this study investigates the establishment of an overall architectural framework, a supporting equipment system, and processes for autonomy design and level evaluations. The key points and recommendations for the research and development of onboard autonomous functional systems and digital-intelligent equipment are proposed. It provides a systematic framework for the commercial application of autonomous ship equipment.

Azimuth waterjet propulsion system can broaden the navigation range of the ship, enhance the adaptability of ships in the shallow water area and other complex environments, and improve the mobility of the ship, which has a wide range of application prospects. In this paper, the numerical simulation was applied to investigate internal flow of azimuth waterjet propulsion system, the accuracy of numerical simulation was validated by experiment. The thrust and efficiency at different speeds were compared, the entropy generation rate is introduced to evaluate the loss ratio of different hydraulic component, the internal flow fields of azimuth waterjet propulsion system were analyzed in detail to reveal the flow mechanism caused by the variation of speed, which will provide guidance for the optimization design of azimuth waterjet propulsion system.

To investigate the flow field characteristics of a low specific speed axial flow pump under different flow conditions ( Q/ Q _des=0.9, 1.0, 1.1), the particle image velocimetry (PIV) technique is employed to measure the axial cross-sections of the pump at four locations: upstream of the impeller, inside the impeller, inside the guide vane, and downstream of the guide vane. And the pressure transducer is used to obtain the pressure distribution of the wall in the flow field of the pump. The results indicate that the velocity distribution upstream of the impeller shows consistent trends with axial acceleration along the axial direction under all three working conditions. A large velocity gradient is observed inside the impeller at different phases, displaying obvious acceleration near the hub along with concentrated high-speed regions. The velocity distribution inside the guide vane is similar, with more uniform high-speed regions and more stabilized flow under the design flow rate. The flow velocity downstream of the guide vane gradually increases in the mainstream direction, slowly accelerating at low flow rates and rapidly approaching the velocity in the mainstream region at high flow rates. As the flow rate increases, the pressure values at the monitoring points in the pump flow channel decrease. The main frequency of the pressure fluctuation is the blade passing frequency. And the pressure transition between the impeller and the guide vane gap is relatively smooth under the design flow rate with reduced flow losses. The experimental results can provide references for the design and performance optimization of the axial flow pump.

An ensemble deep transfer learning method for fault diagnosis based on soft voting is proposed for diagnosing waterjet pump faults under variable working conditions. The source domain and few target domain data samples are normalized after FFT transformation and then fed into three deep transfer learning diagnosis models for training: the CORAL based deep transfer metric learning model, the MMD based deep transfer metric learning model, and the transfer component-based deep belief network. The target domain test samples are diagnosed and analyzed based on this approach. An ensemble deep transfer diagnosis model is subsequently established by combing the soft voting method to obtain the final diagnosis results. Through the diagnosis of three different types of faults in waterjet pumps under variable working conditions, the results show that the proposed ensemble deep transfer diagnosis model not only effectively addresses the high-precision fault diagnosis of waterjet pumps under variable working conditions, but also has better diagnostic accuracy than the single deep transfer fault diagnosis model.

In view of the continuous technological innovation in marine engineering and the growing demand for enhanced adaptability to complex sea conditions, the binocular vision-based KCF (Kernelized Correlation Filters) algorithm is used as the target detection method based on the wave compensation device detection system. Based on the binocular vision, this method detects the load motion, capture the image feature points, calculates the position of the load in the inertial reference frame through coordinate system transformation, and monitors the spatial position and attitude of the replenished object in real time. The relative movement between the load and the replenishment ship can be eliminated by controlling the six-degree-of-freedom motion of the load, thereby achieving wave compensation. Program is developed under the Ubuntu system based on the robot operating system (ROS). Comparison and simulation are then conducted with a wave compensation prototype to validate the feasibility of the proposed detection and tracking method. The results indicate that this method is suitable for wave compensation systems.