Navigated Research Articles

An investigation of geometric feature recognition in 3D ship data

The intelligent recognition of ship geometric features is a prerequisite for enabling computers to automatically generate and deform ship hull surfaces according to requirements, thereby replacing the work of human designers to improve design efficiency. This paper aims to research the recognition of geometric features in three-dimensional ship data using PointNet. To achieve this goal, we first construct two ship point cloud datasets suitable for global feature classification and feature part segmentation of three-dimensional hulls. Subsequently, we conducted recognition capability testing to determine the optimal hyperparameters for identifying ship feature networks. Finally, we employ ship models with non-standard positions to implement data augmentation, enhancing the network's robustness in recognizing the initial positions of ships and achieving rapid cognition of three-dimensional ship geometric features. The findings of this research will provide technical support for ship design based on artificial intelligence technology.

Ship imaging trajectory extraction via an aggregated you only look once (YOLO) model

Maritime traffic community has paid a huge amount of focuses to establish maritime intelligent transportation infrastructure for the purpose of enhancing maritime traffic safety and efficiency. Maritime surveillance video is considered as a type of fundamental data sources for establishing intelligent maritime transportation infrastructure towards smart ship era. To that end, the study proposes an aggregated deep learning model-supported ship imaging trajectory extraction framework. The proposed framework starts by detecting ships from maritime images via a novel You Only Look Once (YOLO) model. More specifically, the proposed ship trajectory extraction framework obtains ship positions in a frame-by-frame manner via the proposed poly-YOLO module. Then, the proposed model maps ship positions in neighboring consecutive maritime images via an Enhanced Deep Sort (EDS) module. Experimental results suggest that the proposed ship trajectory extraction model achieves satisfactory performance due to that the average values of index multiple-object tracking accuracy (MOTa), recall rate (Rid) and index aggregated detection accuracy (Aggid) are larger than 89% (which outperform the comparison algorithms). The study can help varied maritime traffic participants obtain accurate on-site traffic situations in the smart ship era.

Dual‐Loop Control Design for Dynamic Positioning Ships with Prescribed Performance

AbstractDynamic positioning (DP) system is an advanced positioning system widely used in various special operation ships, and the design of control strategies to cope with different constraint conditions is the core technology of DP system research. In this study, a novel dual‐loop control law is proposed to effectively tackle the control challenges encountered by DP ships, particularly in the presence of input saturation and error constraints. Firstly, a saturation handling model is designed to avoid input saturation in the system. Subsequently, a dual‐loop DP control scheme is developed. The outer‐loop is responsible for the ship's position and heading control, while concurrently providing the command velocity signal essential for the inner‐loop. Specifically, a prescribed performance control strategy is designed in the outer‐loop to ensure precise control over positioning errors within predefined ranges and achieve desirable transient and steady‐state performance. The inner‐loop controls the ship's velocity signal, in which a feedback control law is designed based on Hamilton‐Jacobi‐Issacs (HJI) inequality to estimate generalized faults of the DP system. Finally, the proposed control law is validated through numerical simulations on a 76.2 m supply ship, demonstrating superior transient and steady‐state performance compared to existing methods.

AIS Data Manipulation in the Illicit Global Oil Trade

This article takes a close look at the landscape of global navigation satellite system (GNSS) spoofing. It is well known that automated identification system (AIS) spoofing can be used for electronic warfare to conceal military activities in sensitive sea areas; however, recent events suggest that there is a similar interest of spoofing AIS signals for commercial purposes. The shipping industry is currently experiencing an unprecedented period of deceptive practices by tanker operators seeking to evade sanctions. Last year’s announcement of a price cap on Russian crude oil and a new ban on Western companies insuring Russian cargoes is setting the stage for an increase in illegal activity. Our research team identified and documented the AIS position falsification by tankers transporting Russian crude oil in closed ship-to-ship (STS) oil transfers. The identification of the falsified positions is based on the repeated instances of discrepancies between AIS location suggestions and satellite radar imagery indications. Using the data methods at our disposal, we reconstructed the true movements of certain tankers and encountered some surprising behavior. These false ship positions make it clear that we need effective tools and strategies to ensure the reliability and robustness of AISs.

Aerial visual data-driven approach for berthing capacity estimation in restricted waters

Coastal ship berth planning and management necessitate accurate identification of ship position and size, yet this is complicated by the presence of diverse ship types and mixed distribution patterns. Traditional survey-based and position-tracking ship monitoring methods have limitations in reflecting the precise spatial information of coastal ships and their surroundings. This paper introduces a novel aerial visual data-driven methodology to estimate the berthing capacity of sheltered space for stationary ships in geographically dispersed water areas. To measure the berthing capacity, image data from an unmanned aerial vehicle (UAV) survey is collected to reflect the spatial information of all types of ships. A deep learning-based computer vision algorithm is used to automatically detect, identify, and classify ships in sample images. Additionally, we introduce the occupancy factor to empirically quantify the spatial proportional correlation between the ship size and the requisite berthing capacity. A validation test of the proposed method is conducted across all sheltered spaces in Hong Kong, and the UAV survey yields over 7,000 informative images of all types of local ships. The ship identification algorithm achieves an average identification rate of 98.6%, demonstrating higher accuracy and reduced labor and time consumption than observational survey and manual counting methods. Findings indicate that the suggested sheltered space for individual ships is 7.75 times the ship size. The approach provides greater flexibility in estimating berthing capacity for mixed berthing forms in extensive or geographically dispersed water bodies, thereby having the potential to support the design of berths, anchorage areas, and typhoon shelter facilities in coastal regions.

Berthing assistance system for autonomous surface vehicles based on 3D LiDAR

Berthing assistance systems (BASs) for berthing operations of autonomous surface vehicles (ASVs) in restricted waters are very important. Existing BASs are primarily designed for crewed vessels and cannot satisfy the intricate demands of ASV berthing tasks due to limited assistance. In this study, a novel ASV-centric BAS comprising the following four distinctive modules is presented: localization, navigable region acquisition, idle berth determination, and berthing status estimation. The localization module employs a simultaneous localization and mapping (SLAM) algorithm that fuses LiDAR and real-time kinematic (RTK) data to achieve precise ship positioning. The navigable region acquisition module involves segmenting point clouds based on horizontal emission angles and identifies the nearest points within each segment to establish the navigable region. The idle berth determination module employs a shoreline-constrained point cloud linear fitting algorithm, thereby extracting docking zones from nearest point clouds and acquiring idle berth information. The berthing status estimation module leverages the pre-established berth lines to compute essential berthing parameters, encompassing the berthing distance, approaching angle, berthing speed, and yaw rate. Experimental validation shows the high accuracy of the proposed BAS, which maintains a 0.438494 m root mean square error for localization, 0.482% relative error in the berthing distance, and 0.493% relative error in the approaching angle. Furthermore, both the navigable region acquisition and idle berth determination modules consistently provide accurate navigable region and idle berth information. Notably, comparative analysis against existing LiDAR-based solutions demonstrates significant performance improvements of 97.86% in the berthing distance accuracy and 98.12% in the approaching angle accuracy.

Robust adaptive tracking control for dynamic positioning ships subject to dynamic safety constraints and actuator saturation

This paper proposed a novel robust adaptive trajectory tracking control scheme for dynamic positioning (DP) ships subjected to unknown time-varying disturbances, unknown model parameters, dynamic safety constraints, and actuator saturation. The dynamic safety constraints were guaranteed based on the tan-type barrier Lyapunov function (BLF) technique, which ensured the position and velocity of the DP vessel within the given constraints. Moreover, the radial basis function neural network (RBFNN) was adopted to approximate the unknown parameters of the dynamics model, and an adaptive neural disturbance observer (ANDO) was designed to compensate for lumped disturbances. An anti-windup system was developed to handle the actuator saturation effect. By combining the above techniques and back-stepping method, the final control law was presented, and the semi-global asymptotic convergence was achieved via rigorous theoretical analysis and Lyapunov proof. The results of simulations demonstrated the superiority and robustness of this approach in resolving the trajectory tracking challenges of DP ships. Moreover, the proposed control scheme is highly effective in optimizing the trajectory tracking of DP ships, as it takes into account the multiple constraints that may arise during the process, which is a valuable contribution to the field of DP ship trajectory tracking, providing a more comprehensive and effective solution to this complex problem.

A weather optimal heading-based incremental feedback control for dynamic positioning of ships

In this brief, the weather optimal heading-based incremental feedback control algorithm is built for dynamic positioning (DP) of ships in the presence of model uncertainties and unknown environmental disturbances induced by wind, waves and currents. The proposed control algorithm has two parts, i.e., the weather optimal heading portion and the control portion. An improved ZPC-W approach with the deviation of the lateral control force is designed in order to enhance the convergence rate of the desired weather optimal heading and avoid overshoot as well. In addition, based on the iterative sliding mode function, a concise incremental feedback control scheme is designed with the pitch ratio of the thruster as the control input. It is measurable in the practical plant and has nothing to do with ship models with good stability and strong robustness. Lastly, simulation studies are performed to illustrate the performance and the superiorities of the proposed control algorithm.

Neural network-based method for determining vessel position by seabed relief

A seabed relief-based vessel position fixing model on the basis of a four-layered feedforward neural network is proposed. Hidden neurons have hyperbolic tangent activation functions. The model is constructed for 1-D case that can be considered as vessel motion throw a narrow channel or alongside fairway axis. A sequence of spot soundings is given for the network input. The linear coordinate registered for the last sounding forms the network output. The training set is formed by means of the intentional pseudorandom alteration of input samples in accordance with suspected limits of sea level variations and the constant error of its measurements. The validation set is not used. The Adamax algorithm is implemented for the neural network training. The maximum of absolute value of the prediction error is used as a performance criterion of the net. Modeling has been conducted with the Python programming language. The Tensorflow library is used for the creation, training and testing of the neural network. The depth is modelled as a piecewise polynomial function of the coordinate. The results of neural network testing with the use of noised input samples let to state that the neural net can determine a ship position by means of soundings with acceptable accuracy. Different combinations of the sea level error and the number of hidden neurons have been considered. For each of such combinations the network accuracy indicators have been calculated. The best results are obtained for the network with 100 hidden neurons per each layer.

Model predictive controller for path following ships validated by experimental model tests

This paper introduces a practical model predictive controller for surface ships’ path following, with validation through experimental tests. Model predictive control (MPC) is a state-of-the-art modern control technique, providing local optimal control action based on prediction and reference. In this approach, a simple predictive model based upon the Nomoto model is employed to forecast the (near) future ship positions, while the Serret-Frenet frame and the Spline path function are used to generate a smooth ship speed-based reference. Two optimizers, namely the Spline optimizer and the Cobyla (Constrained Optimization by Linear Approximation) optimizer, are used to retrieve an optimal solution that minimizes the difference between the prediction and the reference. To achieve a real-time control feedback, the optimization variables are reduced significantly to lower calculation time by assuming a constant rudder angle throughout the prediction horizon, which is consistent with a realistic human controlled manoeuvre. In addition, an adaptive prediction horizon strategy is proposed to balance overshoot and accuracy.A series of free running model tests were conducted in the Towing Tank for Manoeuvres in Shallow Water (co-operation Flanders Hydraulics – Ghent University) in Ostend, Belgium, in order to evaluate the effectiveness and performance of the proposed controller, and to explore the impact of its parameter settings. The 20 m wide towing tank provides ample space to design complex paths for the ship to follow, which poses a significant challenge for the controller. Essential parameters in MPC, including weight factor for heading error, parameters of predictive model, prediction horizon, gain of adaptive prediction horizon and optimizer, are described in detail and their effects on the control outcomes are discussed with analysis of experimental results. The results demonstrate excellent control performance of the MPC, i.e. high tracking accuracy, smooth track transition, insensitivity to parameter setting and strong robustness in the presence of inherent model uncertainty, despite the simplifications made for practicality.

The prediction of ship motion attitude in seaway based on BSO-VMD-GRU combination model

Short-term prediction of ship attitude holds the potential to provide decision support for precise control and optimal timing selection of ship operations at sea, thereby ensuring the safety and efficiency of offshore activities. However, the time series data representing ship motion attitude exhibits complex nonlinear and non-stationary characteristics, which pose challenges to achieving accurate predictions. To improve prediction accuracy, this study employs two sequence decomposition techniques: Variational Mode Decomposition (VMD) and Adaptive Noise Complete Ensemble Empirical Mode Decomposition (CEEMDAN). These decomposition methods are integrated with a Gated Recurrent Unit (GRU) to forecast ship motion attitude. Firstly, the decomposition techniques are applied to decompose the time series data of ship motion attitude into multiple intrinsic mode function (IMF) components. Subsequently, each IMF component is predicted using the GRU. Ultimately, the final prediction results are obtained by aggregating the GRU’s predictions for each individual component. To alleviate the impact of manual parameter configuration in the VMD algorithm, this study introduces a metaheuristic optimization algorithm called the Binary System Optimization Algorithm (BSO), which is empirically validated for its effectiveness. Moreover, real ship data from the vessel named “Yukun” is utilized to experimentally verify the proposed prediction algorithm. The experimental outcomes reveal that both decomposition algorithms can enhance the prediction accuracy of the GRU, with the VMD algorithm yielding superior prediction results compared to those obtained using CEEMDAN.

Strong fixed-time dynamic inverse adaptive LQR integrated control strategy for dynamic positioning of ship

To ensure compositive capacities for dynamic positioning ship, a dynamic inverse adaptive linear quadratic regulator (DI-ALQR) control strategy is proposed for dynamic positioning ship based on strong fixed-time prescribed performance function (SFPPF) and cascaded fixed-time extended state observer (CFESO). Firstly, a high-fidelity four degree of freedom ship motion model including roll motion is constructed, and an inverse system of the ship is proposed to realize decoupling of variables and pseudo linearization of control systems. Next, the SFPPF is employed to ensure prescribed performance with predefined convergence. The DI-ALQR control strategy is presented to achieve integrated control of position, roll and heading of ship considering the balance between energy consumption and control accuracy. Simulation results and analysis prove that the proposed control strategy makes the position, roll and heading of ship reach in predefined-time and maintain the desired values, which ensures prescribed performance.

Rapid saturation of cloud water adjustments to shipping emissions

Abstract. Human aerosol emissions change cloud properties by providing additional cloud condensation nuclei. This increases cloud droplet numbers, which in turn affects other cloud properties like liquid-water content and ultimately cloud albedo. These adjustments are poorly constrained, making aerosol effects the most uncertain part of anthropogenic climate forcing. Here we show that cloud droplet number and water content react differently to changing emission amounts in shipping exhausts. We use information about ship positions and modeled emission amounts together with reanalysis winds and satellite retrievals of cloud properties. The analysis reveals that cloud droplet numbers respond linearly to emission amount over a large range (1–10 kg h−1) before the response saturates. Liquid water increases in raining clouds, and the anomalies are constant over the emission ranges observed. There is evidence that this independence of emissions is due to compensating effects under drier and more humid conditions, consistent with suppression of rain by enhanced aerosol. This has implications for our understanding of cloud processes and may improve the way clouds are represented in climate models, in particular by changing parameterizations of liquid-water responses to aerosol.

Risk analysis of bridge ship collision based on AIS data model and nonlinear finite element

Abstract To solve the problem of calculating the probability of ship collision in ship bridge collision risk assessment, the impact parameters of ship collision are obtained based on the automatic identification system (AIS) data to solve the problem that the existing methods do not consider the actual navigable ship information in a specific bridge navigation area. Based on AIS data, the dynamics of sailing ships are analyzed, parameters such as ship position, speed, and yaw angle, are obtained, ship traffic flow is analyzed, and the geometric probability in the actual ship traffic flow specification model is modified. The results before and after correction were compared and analyzed. The results show that the maximum transverse displacement of the anti-collision device is about 1.5 s under all working conditions, indicating that the collision force drops continuously from this moment to 0 in the collision force time history. In the process of collision, the anti-collision device absorbs part of the collision energy through its own deformation. Under the premise of a certain initial kinetic energy, the deformation caused by the collision energy absorption after fortification will be reduced. The anti-collision device has local permanent deformation under the impact of 5,000 t ship, but no damage and failure, and will not cause water entry and subsidence. It proves that the constructed fishery ship collision risk assessment model and the developed fishery ship safety management and evaluation system are reliable and the prediction results are credible, which can provide scientific methods for the safety management and evaluation of fishery vessels. For the bridge area with complicated ship navigation conditions, it is necessary to use the actual navigable ship information obtained based on AIS data to estimate the distribution of ships in the bridge area to improve the accuracy of the calculation results.

A graphical collision alert system of power-driven ship in sight situations considering geometric encounter situations

This paper proposes a power-driven ship collision alert model considering geometric encounter situations in sight situations by collecting the natural environment, ship static and dynamitic information. The kernel of the proposed method is to introduce a ship geometric encounter model to determine the ship encounter situation and to identify the influencing factors, including ship position, ship speed and ship heading, by considering ship-ship collision situations. These factors, together with ship static parameters and natural environment, are treated as input variables to derive the collision risk through a fuzzy inference system. The merit of developed model is that the relative bearing, collision distances and relative course are intuitively described by graphical user interface, which can assist the crew well understand the decision of machine and can be applied to human-machine collaboration for intelligent ship (e.g. remotely control ship). Moreover, from further analysis, the nearest point and the actions taken at the nearest point provide a useful alert for collision risk. From these analyses, the proposed model can be used to improve ship handling and reduce the probability of collision during ship encounters.

A Novel Ship Speed and Heading Estimation Approach Using Radar Sequential Images

This paper proposes an approach to estimate ship dynamic features (i.e., speed and heading) using radar sequential images, which can be used to assess the ship-ship collision risk in vessel traffic service (VTS) center. The proposed approach estimates the ship speed and heading in three steps, including ship detection, tracking, and data fusion. First, the ship target, together with its center coordinate, is detected by introducing the background subtraction detector in each radar image. Second, the ship position in one frame is mapped to the consecutive frame, and ship trajectory distribution is established using the Kalman filter and Hungarian algorithms. Third, fuzzy logic is introduced to fuse data from radar and AIS. Specifically, input variables include two parameters, which are the ship speed/heading difference in consecutive frames using radar and AIS, respectively. The variance of ship speed distribution is 1.30 at 10s sampling frequency, and the variance of ship heading distribution is 26.53, the experimental results indicate that the proposed approach can accurately estimate ship speed and heading in the radar sequential images of the Yangtze River. The strength of the proposed approach is its capability to estimate the ship speed and heading quantitatively from radar sequential images, which is interactive and interpretable for VTS operators.

Features of Dynamism Wharf-Cable-Dynamic-Positioning Vessel Rigid-Flexible Coupling Multi-Body System Analysis

The conventional mooring positioning technique is cost-effective; however, it shows poor maneuverability and positioning precision. In this study, to calculate the mooring tension, mooring cables were discretized into lumped mass models using the lumped mass technique. Dock fender nonlinear response forces were modeled in OrcaFlex using the Link unit. The multi-body system’s entire coupling vibrant time-frequency features have been examined. The effect of the side thrusters on removing the vessel motion carried on by the first-order wave loads has been determined under mooring conditions by comparing the difference in horizontal degree of freedom motion and the mooring line’s mooring tension between dynamic and non-dynamic positioning vessels (DPV). The impact of the wharf-cable and target position on side thrusters and positioning capabilities are analyzed, considering the results of both vessels under identical environmental loads. The results demonstrate that deep evaluation of the target position can greatly improve side thruster performance and ship positioning precision. DP systems are weak to cancel linear wave forces, and the missing ship motions for DP ships may be due to the combined action of the fender, moorings and the selection of a good target position. When the selection of the target position is unreasonable, the size of the pre-tension of the mooring line cannot meet the requirement of absorbing the first-order wave load on the vessel.

A numerical investigation on ship-ship overtaking interactions in confined waterways

The whole process of a KCS container ship overtaking a low-speed Neo-Panamax container ship is numerically simulated by solving the unsteady Reynolds Averaged Navier-Stokes (URANS) equations. The dynamic overset mesh technique is adopted to simulate the relative motions between the two ships and the ship attitude variations. The free-surface elevations, ship attitudes, as well as hydrodynamic forces and moments on the two ships are predicted. In order to discuss the effects of different navigation parameters on the ship-ship interactions, a set of ship speeds, lateral distances and water depths are simulated. The results illustrate that the overtaken ship is more significantly impacted by the interaction than the overtaking ship, and the drawdown generated by the overtaking ship is the key factor during the overtaking process. The increase of ship speed, the decrease of lateral distance or water depth can lead to more intense drawdown, and hence even more significant ship-ship interaction effects.

Assessment of ship position probability in the geometrical figure of position lines errors

Accurate and reliable determination of the ship position coordinates is one of the most important tasks for ensuring the safety of navigation at sea. A significant condition that contributes to the effective solution of this task is the use of redundancy in measurements of navigation parameters. The implementation of this redundancy allows the navigator or automatic navigation aid to control the trueness of measurements; eliminate gross and systematic errors; reduce the effect of random errors; apply various methods of analysis and algorithms for processing information in order to obtain the most accurate and reliable ship position. Adequate redundancy of navigation measurements makes it possible to obtain asymptotically unbiased estimates of coordinates, as well as to solve other navigation tasks based on redundant data. The results of a study on the probability of finding the true coordinates of the ship’s position in a geometric figure formed by random measurement errors are presented. It has been shown in the study that a single redundancy of measurements is not enough to achieve the required level of probability. Elements of classical combinatorics based on the Bernoulli scheme and including Newton’s binomial and Pascal’s triangle as tools are used as a mathematical apparatus for the study. These tools allow us to effectively analyze combinations of mathematical signs, such as plus and minus, of random measurement errors, reducing them into binary sequences, which are described by binomial coefficients. It has been argued in the paper that the low level of probability of finding the true values of the coordinates in the geometrical figure of measurement errors is a strong signal that any method of averaging the measurement results can lead to asymptotically biased estimates of the ship position coordinates. This is analogous to the influence of systematic errors on the coordinates within a certain time interval. From the point of view of navigational safety, a low probability can be qualified as a near-miss situation, which can lead to incorrect control of the ship position. The probabilistic criteria for the necessary redundancy of measurements to approach asymptotically unbiased estimates of ship position are presented in the paper.

Global fast terminal sliding mode control for path following of ultra large underactuated ship based on predictive LOS guidance

This study proposes a new line-of-sight guidance method based on position prediction that constructs the total path deviation by predicting the future time position of ships. This method can solve the problem of overshoot, which is prone to occur in the path following process of ultra large underactuated ships. A global fast terminal sliding mode method is used to design controllers that allow path deviations to converge in a finite time. To solve the problems of unknown velocity, disturbances, and sideslip angle during navigation, a high-order nonlinear observer is designed to estimate the system states and obtain the velocity values and external disturbances. The sideslip angle of the ship during navigation is obtained by estimating its velocity. Therefore, the problem of an unknown sideslip angle is solved, and the effectiveness of the proposed algorithm is verified through simulation experiments.