Marine Ship Research Articles

CSEF-Net: Cross-Scale SAR Ship Detection Network Based on Efficient Receptive Field and Enhanced Hierarchical Fusion

Ship detection using synthetic aperture radar (SAR) images is widely applied to marine monitoring, ship identification, and other intelligent maritime applications. It also improves shipping efficiency, reduces marine traffic accidents, and promotes marine resource development. Land reflection and sea clutter introduce noise into SAR imaging, making the ship features in the image less prominent, which makes the detection of multi-scale ship targets more difficult. Therefore, a cross-scale ship detection network for SAR images based on efficient receptive field and enhanced hierarchical fusion is proposed. In order to retain more information and lighten the weight of the network, an efficient receptive field feature extraction backbone network (ERFBNet) is designed, and the multi-channel coordinate attention mechanism (MCCA) is embedded to highlight the ship features. Then, an enhanced hierarchical feature fusion network (EHFNet) is proposed to better characterize the features by fusing information from lower and higher layers. Finally, the feature map is input into the detection head with improved bounding box loss function. Using SSDD and HRSID as experimental datasets, average accuracies of 97.3% and 90.6% were obtained, respectively, and the network performed well in most scenarios.

Analysis and prediction of vibro-acoustic characteristics of parallel propulsion systems for large-scale marine ships

The parallel power propulsion system is the preferred option for large-scale ships. The improper configuration of multidimensional power parameters is a significant factor contributing to the vibration and noise generated by the system. This study examines the sensitivity and dependence of the vibro-acoustic characteristics of the system on various power parameters through theoretical and experimental methods, and reveals the evolution mechanism of the dynamic behaviors under the coupling effect of multidimensional power parameters. Firstly, the nonlinear dynamic model considering the lateral–torsional–axial coupling of the propulsion system is established and the effects of different combinations of power parameters on the vibration response and system stability are investigated. Secondly, an experimental platform of the parallel propulsion system is constructed, and the comprehensive description of the effects of multidimensional power parameters on the vibration and noise of the system under asymmetrical input power is further provided. Finally, the radial basis function (RBF) neural network is innovatively employed to predict and approximate the vibro-acoustic characteristics of the system under the combined influence of rotating speed, torque ratio, and drag current. The research results are of significant theoretical and practical importance in breaking through the technical bottleneck related to reducing the vibration and noise of such parallel propulsion systems.

Automatic berthing systems: a review on artificial intelligence methods for marine ship

Automatic berthing systems: a review on artificial intelligence methods for marine ship

A Critical Review of On-Line Oil Wear Debris Particle Detection Sensors

In the field of marine engineering, the friction and wear experienced by rotating mechanisms are recognized as significant contributors to the failure of marine machinery. In order to enhance the safety and dependability of marine ship operations, the implementation of on-line oil wear debris particle detection sensors enables the on-line monitoring of oil and facilitates the rapid identification of abnormal wear locations. This paper provides a critical review of the recent research progress and development trends in the field of sensors for on-line detection of oil wear debris particles. According to the method of sensor detection, wear debris particle detection sensors can be classified into two distinct categories: electrical and non-electrical sensors. Electrical sensors encompass a range of types, including inductive, capacitive, and resistive sensors. Non-electrical sensors encompass a range of technologies, such as image processing sensors, optical sensors, and ultrasonic sensors. Finally, this review addresses the future research directions for wear debris particle detection sensors in light of the challenging problems currently faced by these sensors.

Ship detection and identification in SDGSAT-1 glimmer images based on the glimmer YOLO model

ABSTRACTRemote sensing technology has been widely used for marine monitoring. However, due to the limitations of sensor technologies and data sources, effective monitoring of marine ships at night remains challenging. To address these challenges, our study developed SDGST, a high-resolution glimmer marine ship dataset from SDGSAT-1 satellite and proposed a ship detection and identification method based on the YOLOv5s model, the Glimmer YOLO model. Considering the characteristics of glimmer images, our model has made several effective improvements to the original YOLOv5s model. In particular, the improved model incorporates a new layer for detecting small targets and integrates the CA (Coordinate Attention) mechanism. To enhance the original feature fusion strategy, we introduced BiFPN (Bi-directional Feature Pyramid Network). We also adopted the EIOU Loss function and replaced the initially defined anchors with clustering results, thus improving detection performance. The mean Average Precision (mAP%) reaches 96.7%, which is a 5.1% improvement over the YOLOv5s model. Notably, it significantly improves the detection of small ships. This model demonstrates superior performance in ship detection under glimmer conditions compared to the original YOLOv5s model and other popular target detection models, and may serve as a valuable reference for achieving high-precision nighttime marine monitoring.

Continuous basalt fibers into fireproof and thermal insulation architectures using an additive manufacturing manipulator

Continuous basalt fiber is an emerging high-performance foundational material that can be widely used in fields such as road construction, energy conservation and environmental protection, aerospace, military equipment, and marine ships. However, it is difficult for existing processing techniques to form continuous basalt architectures with three-dimensional (3D) complex shapes. In addition, the basalt fibers in the architectures are filled with polymers, which cannot fully utilize the performance of basalt fibers. Therefore, here, we report the fabrication of continuous basalt fibers with fireproof and thermal insulation performance through the combination of an Additive manufacturing (AM) manipulator, two-step precursor infiltration and pyrolysis (PIP) processes. Using SiOC ceramics to fill between continuous basalt fibers will help improve the architectures' fire and thermal insulation performance. The continuous basalt fibers coated with thermoplastic polyurethanes (TPU) were processed into 3D architectures under the action of the laser. Through the vacuum infiltration of the SiOC precursor and debinding process, TPU in the 3D architectures was removed. In order to reduce the structural defects generated by the first PIP process, the final part with fireproof and thermal insulation performance was fabricated through the second PIP process. We further demonstrated the final part with excellent fireproof and thermal insulation performance. The final part had a shell temperature of 788.8 ℃ and an internal temperature of about 50 ℃ under the flame spray gun for the 20 s. By replacing polymers with inorganic materials, our basalt architectures exhibit their potential applications in military, aviation, and civil fireproof and thermal insulation equipment.

A review of intelligent ship marine object detection based on RGB camera

AbstractThe article presents a comprehensive summary of Intelligent Ship Marine Object Detection (ISMOD) based on the RGB Camera. Marine object detection plays a pivotal role in enabling intelligent ships to acquire crucial data and security assurances for autonomous navigation. Among the various detection sensors, the RGB Camera is an informative and cost‐effective tool with a wide range of civil applications. In the beginning, the ISMOD metrics based on the RGB camera is analyzed from three significant aspects, namely accuracy, speed, and robustness. Subsequently, the latest research status and comparative overview are presented, encompassing three mainstream detection methods: traditional detection, deep learning detection, and sensor fusion detection. Finally, the existing challenges of ISMOD are discussed and future development trends are recommended. The results demonstrate that forthcoming development will predominantly concentrate on deep learning approaches, complemented by other techniques. It is imperative to advance detection performance in domains such as deep fusion, multi‐feature extraction, multi‐fusion technology, and lightweight detection architecture.

Submarine optical fiber communication provides an unrealized deep-sea observation network

Oceans are crucial to human survival, providing natural resources and most of the global oxygen supply, and are responsible for a large portion of worldwide economic development. Although it is widely considered a silent world, the sea is filled with natural sounds generated by marine life and geological processes. Man-made underwater sounds, such as active sonars, maritime traffic, and offshore oil and mineral exploration, have significantly affected underwater soundscapes and species. In this work, we report on a joint optical fiber-based communication and sensing technology aiming to reduce noise pollution in the sea while providing connectivity simultaneously with a variety of underwater applications. The designed multifunctional fiber-based system enables two-way data transfer, monitoring marine life and ship movement near the deployed fiber at the sea bottom and sensing temperature. The deployed fiber is equally harnessed to transfer energy that the internet of underwater things (IoUTs) devices can harvest. The reported approach significantly reduces the costs and effects of monitoring marine ecosystems while ensuring data transfer and ocean monitoring applications and providing continuous power for submerged IoUT devices.

Abnormal Detection Method of Transship Based on Marine Target Spatio-Temporal Data

<p>Marine target situational awareness is developing towards intelligence. The practical application of marine law enforcement, route control, fishery supervision and other fields makes marine ship track mining and anomaly analysis a hot direction of technology development. At present, most of the research focuses on the feature recognition of single target or single target signal, while the research on correlation anomaly detection based on multi target or multi target signal is relatively less. In this paper, based on the large spatio-temporal data of ocean targets such as radar and AIS track, the corresponding recognition algorithm is designed for the abnormal transport behavior. The real-time batch detection of illegal transshipment is realized, which verifies the effectiveness of the algorithm and shows good performance in practical application scenarios.</p> <p> </p>

Analysis of ship accident resulting from bad weather conditions in the port of Khor Al-Zubair, Iraqi crane accident Aba Thar: a case study

The Arabian Gulf region is regarded as one of the world's most significant commercial areas, with large-scale and continuous marine shipments of commodities and goods to and from the Gulf. Iraqi ports are one of the most important ports in the Gulf, and they are a vital source of revenue for the Iraqi economy because of the money they bring in, as any stoppage of operations or damage to the ports may lead Iraq to lose a significant amount of money and halt shipping operations. Maritime accidents are one of the most significant concerns that have resulted in the suspension of maritime navigation and loading and unloading activities in Iraqi ports since there are various forms of marine accidents and many causes. With this study, we will look at maritime accidents caused by bad weather, as there have been many recent marine mishaps and ship collisions caused by bad weather, resulting in the loss of life and equipment and halting marine activities. We'll look at a few incidents, the meteorological conditions that contribute to them, and the link between them and the most likely cause of the accident. We will study an accident that occurred in the port of Khor Al-Zubair in 2018, which is considered one of the most important ports of Iraq, as it contains berths for importing and exporting goods, as well as on many of the Iraqi oil export berths, the accident of the Iraqi crane, Aba Thar. This report advises Iraqi port officials to limit activity in severe weather to reduce accidents that lead to loss of life and equipment and significant economic losses to the country. Keywords: Khor Al-Zubair, Maritime accidents, Aba Thar, Bad weather, The Arabian Gulf

Indirect measurement of propeller fluctuating forces using an inverse analysis: Numerical and experimental studies

The propeller fluctuating force is being recognized as the dominant source of underwater radiated noise, its accurate acquisition is thus necessitated for a reliable acoustic-structure analysis and optimization of marine ships. However, such dynamic operational forces are frequently impossible or expensive to directly measure due to various practical challenges. To alleviate this limitation, this paper presents an inverse method for the indirect estimation of propeller forces using measured shafting vibration responses. The force reconstruction procedure is constructed based on the state-space model of the propeller–shafting system, which can be derived by a data-driven subspace identification algorithm in conjunction with either the numerical or experimental models of the system. To ensure the robustness of the inverse analysis in the presence of inevitable measurement noise, a modified regularization strategy based on homotopy continuation is introduced. The effectiveness of the proposed algorithm is demonstrated through numerical simulations and experimental investigations. The obtained results demonstrate the potential feasibility of indirect measurement for accurately identifying propeller fluctuating forces in the time domain.

Comprehensive Evaluation of Marine Ship Fires Risk Based on Fuzzy Broad Learning System

Ship fires exhibit the main characteristics of a high possibility of occurrence, large load, fast spreading, high difficulty in extinguishing, and serious losses. Therefore, once a fire occurs, it will cause huge loss in terms of economic and personnel safety. Firstly, a ship fire risk evaluation indicator system was constructed based on the causes and severity of the fires. Secondly, a comprehensive evaluation method for the fuzzy broad learning system (FBLS) was proposed. The fuzzy system was used to implement feature mapping on the input data, and the extracted fuzzy features were further input into the BLS enhancement layer. A fuzzy broad learning neural network structure was constructed by combining fuzzy features, feature nodes, and enhancement nodes. The method was applied to the field of risk assessment for the first time, and is a reference for subsequent studies. Finally, the risk levels of ship fires were classified and compared with evaluation methods such as fuzzy support vector machine (FSVM) and Fuzzy BP neural network (FBPNN) to demonstrate effectiveness and accuracy. The proposed FBLS method was used to predict actual cases, and the results showed consistency with the level determined by the accident investigation report published by the Maritime Bureau Administration.

Dynamic modeling of spur gear system under marine ship heaving-pitching motion

Sea waves often result in multi-freedom motions of ships, and affect the stability of marine gear systems. This study presents a novel dynamic modeling method for spur gear system considering the influence of marine ship heaving-pitching motion and investigates the spur gear dynamics. An excitation transmission path from wave to gear is illustrated and incorporated into the gear dynamic model. The hydrodynamic force is analyzed and the hull heaving-pitching motion is solved using the New Strip Method (NSM). Considering the time-varying meshing stiffness, transmission error, and tooth side clearance, the motion differential equation of the spur gear system impacted by the heaving-pitching coupling motion of the hull is established. The influences of key wave and navigation parameters on gear dynamics are analyzed. The results show that ship heaving-pitching motion causes additional stiffness and damping excitation, and leads to typical nonlinear phenomena of the spur gear system in a marine ship, such as period, quasi-period, and chaos, and causes a sharp increase in the meshing impact amplitude up to a maximum of 36.81%. The changes in wave frequency, the hull's heading angle, and hull's speed have a significant impact on gear dynamics, whereas the wave amplitude has less of an impact.

Application and Development of Fiber Optic Gyroscope Inertial Navigation System in Underground Space

Fiber Optic Gyroscope Inertial Navigation System (FOG-INS) is a navigation system using fiber optic gyroscopes and accelerometers, which can offer high-precision position, velocity, and attitude information for carriers. FOG-INS is widely used in aerospace, marine ships, and vehicle navigation. In recent years, it has also played an important role in underground space. For example, in the deep earth, FOG-INS can be used in directional well drilling, which can enhance recovery in resource exploitation. While, in shallow earth, FOG-INS is a high-precision positioning technique that can guide construction in trenchless underground pipelaying. This article extensively reviews the application status and latest progress of FOG-INS in underground space from three aspects—FOG inclinometer, FOG drilling tool attitude measurement while drilling (MWD) unit, and FOG pipe-jacking guidance system. First, measurement principles and product technologies are introduced. Second, the research hot spots are summarized. Finally, the key technical issues and future trends for development are put forward. The findings of this work are useful for further research in the field of FOG-INS in underground space, which not only provides new ideas and directions for scientific research, but also offers guidance for subsequent engineering applications.

Adaptive backstepping fast terminal sliding mode control of dynamic positioning ships with uncertainty and unknown disturbances

Considering the complexity of the operating environment of marine ships, higher demands are placed on the positioning accuracy and positioning performance of Dynamic Positioning (DP) systems. This paper designs an Adaptive Backstepping Fast Terminal Sliding Mode Control (ABFTSMC) to solve the problems of low positioning accuracy, slow convergence, and poor anti-interference performance in ship positioning due to uncertainty of dynamic model parameters and unknown time-varying environmental disturbances. A Fast Terminal Sliding Mode Control (FTSMC) is combined with backstepping techniques to ensure the robustness of the system to uncertainties and disturbances. Meanwhile, an adaptive law is used to estimate the unknown uncertainty terms. Moreover, the Lyapunov stability criterion is used to prove the convergence and stability of the designed controller. Multiple simulation results show that ABFTSMC has better control performance compared with Adaptive Backstepping Control (ABC) and Adaptive Backstepping Sliding Mode Control (ABSMC). All the comparisons could fully verify the effectiveness and superiority of the proposed control method.

SwinSeg: Swin transformer and MLP hybrid network for ship segmentation in maritime surveillance system

Accurate identification and segmentation of moving ships to ensure maritime traffic safety has become an important task in maritime intelligent transportation system. With the development of artificial intelligence, maritime surveillance system based on computer vision has been widely studied. However, there are still some problems when applied to the actual maritime scene. For example, the degradation of visible image quality caused by rain, haze, and low illumination leads to a significant reduction in segmentation performance. To improve the performance of ship identification and segmentation under adverse weather conditions, we propose SwinSeg, a hybrid network combining Swin Transformer and lightweight multi-layer perceptron (MLP). To address the lack of suitable open-source datasets in the community, we have collected and labeled a semantic segmentation dataset of marine ships, named SeaShipsSeg. It consists of 1200 visible marine ship images and covers six common ship types (bulk cargo carrier, container ship, fishing boat, general cargo ship, ore carrier, and passenger ship). In addition, synthetic degraded images are added to the dataset to increase its diversity and improve the generalization ability of the network. The experimental results show that the performance of our method is significantly better than the state-of-the-art (SOTA) methods in terms of segmentation accuracy, robustness, and efficiency under different weather conditions. The dataset is available at https://github.com/GrimreaperZ-creator/SeaShipsSeg.

A Marine Small-Targets Classification Algorithm Based on Improved Convolutional Neural Networks

Deep learning, especially convolutional neural network (CNN) techniques, has been shown to have superior performance in ship classification, as have small-target recognition studies in safety inspections of hydraulic structures such as ports and dams. High-resolution synthetic aperture radar (SAR)-based maritime ship classification plays an increasingly important role in marine surveillance, marine rescue, and maritime ship management. To improve ship classification accuracy and training efficiency, we proposed a CNN-based ship classification method. Firstly, the image characteristics of different ship structures and the materials of ship SAR images were analyzed. We then constructed a ship SAR image dataset and performed preprocessing operations such as averaging. Combined with a classic neural network structure, we created a new convolutional module, namely, the Inception-Residual Controller (IRC) module. A convolutional neural network was built based on the IRC module to extract image features and establish a ship classification model. Finally, we conducted simulation experiments for ship classification and analyzed the experimental results for comparison. The experimental results showed that the average accuracy of ship classification of the model in this paper reached 98.71%, which was approximately 3% more accurate than the traditional network model and approximately 1% more accurate compared with other recently improved models. The new module also performed well in evaluation metrics, such as the recall rate, with accurate classifications. The model could satisfactorily describe different ship types. Therefore, it could be applied to marine ship classification management with the possibility of being extended to hydraulic building target recognition tasks.

Improved design of transient power sharing strategy for AES multi-gensets in response to high power load mutation

The Medium Voltage Direct Current (MVDC) Integrated Power System (IPS) represents the developing trend of marine ship power. It facilitates the provision of high quality energy for weaponry, however, high power load switching will have a severe impact on power system as well as on gas turbine gensets, which is a critical problem needs to be solved urgently. In this paper, based on the traditional IPS hierarchical control strategy, an improved design method of transient power sharing is proposed for multi-gensets operation. Firstly, by analyzing the transient fluctuation process of voltage and speed, the law of system energy coupling transfer is illustrated and a strategy of equalizing torque impact is proposed. Then, a set of speed compensation factors is introduced to achieve the equalization of transient speed regulation (TSR). Finally, the effectiveness of the proposed improved control strategy is verified by MATLAB/Simulink simulation. Compared to before the improvement, the gensets operate away from the limiting boundary of bearing torque impact and speed deviation, and the bus voltage stability is also enhanced.

A Ship Monitoring Framework Based on Multimodal Remote Sensing Data

Due to the wide monitoring range, remote sensing satellites have more advantages than ground monitoring in large-scale monitoring. In particular, satellite network observations make rapid and frequent ground monitoring possible. In this paper, an all-day and all-weather marine ship monitoring framework based on multimodal remote sensing data was established. Scene recognition method was first used to segment sea areas. Then, we analyzed the ship characteristics of different data and used them for ship detection. Finally, the motion state of the ship was judged and the dynamic ships in the video were tracked. To prove the proposed framework, the data of Sentinel-1/2 and Jilin-1 data were used for verification. The experimental results demonstrated the advantages of the proposed framework for ship monitoring, which achieved the purpose of ship detection and tracking.

A Mathematical Modeling and an Optimization Algorithm for Marine Ship Route Planning

In order to solve the problem of ship route planning at sea, we reduce the economic cost of ship navigation planning and improve the efficiency of ship navigation. As a result, the goal of this work is to delve into the mathematical modeling and the best algorithm for marine ship route planning. To begin, a mathematical model of ship route planning is created, taking into account the impact of nonuniformity in the offshore wind field on ship route planning, with the shortest ship sailing time as the goal. Based on the mathematical model, the ant colony algorithm is used to optimize the initial route of the ship. Finally, through the optimization of the ant colony algorithm, the optimal route with the shortest total length and the smaller steering angle is obtained, and the optimal ship navigation planning scheme is obtained. The simulation results show that, when compared to artificial intelligence and genetic algorithms, the optimization algorithm suggested in this research produces the best ship route planning outcomes and has the lowest economic cost, which may effectively increase the efficiency of ship route work.