Safe Navigation Of Ships Research Articles

Knowledge transfer strategy for enhancement of ship maneuvering model

The advancement of autonomous vehicles and concerns about ship navigation safety have resulted in a greater need for ship model quality. However, in situations where there is limited prior information or data available about the system, the development of accurate models can be challenging. To address this issue, we propose a knowledge transfer strategy that can migrate and adapt domain knowledge from a well-modeled benchmark ship to a target ship. The benchmark, or source ship, should resemble the target ship in the feature space and reveal similar trends in the prediction horizon. By incorporating informative trends into the data-driven transfer function, the representative model of the target ship can be considerably enhanced. In this study, the experiments are conducted on two full-scale vessels that characterize different dimensions and dynamic properties. A feature vector is introduced to evaluate the configuration similarity between vessels, and ship maneuverability is compared to authorize the security of predictive tendency. The derived target ship model is verified to accurately predict maneuvering trajectories in various scenarios, demonstrating that knowledge transfer from a source ship facilitates the target ship modeling process. This approach provide new insights into the development of models for systems with confined information.

Effect of notch on fatigue performance of marine shaft made of 34CrNi3Mo alloy steel under torsional loading

Joint of flange on a marine shaft subjected to torsional loading was more prone to occur fatigue fracture than the other section on the shaft due to stress concentration effect, so torsional fatigue performance in the vicinity of the joint should be payed more attention in terms of safe navigation of ships. The fatigue analysis of 34CrNi3Mo steel as a novel alloy material with a stress concentration factor of 1.45 under cyclic torsional loads was carried out based on the median S-N experimental method by simplifying the flange and shaft joint into 34CrNi3Mo specimens with u-notch subjected to torsional fatigue loading. The S-N curve and fatigue life of 34CrNi3Mo alloy steel were numerically calculated and compared with experimental fatigue life and the plotted S-N curve. It was found that fitting equation of the S-N curve was close to experimental results. Then, the fatigue performance of 34CrNi3Mo specimens with v-notch at angles of 45°, 90° and 135° was compared by means of the validated numerical method. The fracture macrographs and micrographs of the 14 specimens also were provided to explore the effect of notch on fatigue performance of the 34CrNi3Mo materials and to exploit the failure mechanism of fracture.

An interpretable XGBoost-based approach for Arctic navigation risk assessment.

The Northern Sea Route (NSR) makes travel between Europe and Asia shorter and quicker than a southern transit via the Strait of Malacca and Suez Canal. It provides greater access to Arctic resources such as oil and gas. As global warming accelerates, melting Arctic ice caps are likely to increase traffic in the NSR and enhance its commercial viability. Due to the harsh Arctic environment imposing threats to the safety of ship navigation, it is necessary to assess Arctic navigation risk to maintain shipping safety. Currently, most studies are focused on the conventional assessment of the risk, which lacks the validation based on actual data. In this study, actual data about Arctic navigation environment and related expert judgments were used to generate a structured data set. Based on the structured data set, extreme gradient boosting (XGBoost) and alternative methods were used to establish models for the assessment of Arctic navigation risk, which were validated using cross-validation. The results show that compared with alternative models, XGBoost models have the best performance in terms of mean absolute errors and root mean squared errors. The XGBoost models can learn and reproduce expert judgments and knowledge for the assessment of Arctic navigation risk. Feature importance (FI) and shapley additive explanations (SHAP) are used to further interpret the relationship between input data and predictions. The application of XGBoost, FI, and SHAP is aimed to improve the safety of Arctic shipping using advanced artificial intelligence techniques. The validated assessment enhances the quality and robustness of assessment.

A comprehensive method for causation analysis of ship-ice collision risk in Arctic waters.

The influence of harsh Arctic environmental factors has caused ship-ice collision accidents to become the main threat faced by navigating ships. It is necessary to quantify the causation of ship accidents and perform effective risk management and control measures to ensure ship navigation safety. This study proposes a Bayesian network (BN) model-based risk analysis method for ship-ice collision accidents, which is used to quantitatively analyze the key risk factors and primary risk causation paths of ship accidents. First, the fault tree analysis (FTA) method is proposed to constructing the BN structure model, and the BN parameter solution method is further established. Consequently, a triangular fuzzy and defuzzification method is developed to quantify uncertain expert knowledge. Then, the BN inference method is used to analyze the collision risk causation where the North Atlantic and Arctic waters meet. The results indicate that the main risk factors in Arctic waters come from the environment. There are four primary risk causation paths; the proposed management and control measures of the risk causation paths (A), (B), (C), and (D) can effectively reduce the navigation risk by 29.95%, 9.98%, 25.05%, and 3.99%, respectively; the combination of these four measures can reduce the navigation risk by 54.63%.The proposed method has positive guiding significance for ensuring the safety of ship navigation in Arctic waters.

Experimental study on impact toughness of EH36 ship steel in Arctic areas

ABSTRACT Polar ships are subjected to the ice loading. Low temperature impact toughness of ship steels is important for the ice-breaking efficiency and navigation safety of polar ships. In this paper, the impact absorption energy of EH36 steel under different temperatures, impact velocities and plate thickness is analyzed by experimental test, Taguchi and ANOVA method. The impact absorption energy was divided into crack formation and crack propagation absorption energy. The experimental results show that the impact absorption energy of EH36 steel is positively correlated with plate thickness and temperature, and negatively with impact velocity when it was in the toughness state. The order of significance ranking from high to low is thickness, temperature, and impact velocity. The ratio of the crack propagation absorption energy increases with the temperatures and reflects the impact toughness of EH36 steel. Furthermore, the best factor combination of impact toughness of EH36 steel was obtained.

Marine radar monitoring IoT system and case study of target detection based on PPI images

AbstractTo ensure the ship navigation safety, it is necessary to detect the targets in the background of sea clutter around the ship. The most commonly used target detection equipments for ship navigation are marine radar and automatic identification system (AIS) device. However, marine radar echoes are often mixed with multiple clutter, and weak targets are not always equipped with AIS device, neither provides AIS information with low accuracy, leading to difficulty with target detection. Moreover, existing marine monitoring systems are accustomed to using the traditional information fusion methods for target detection, and the accuracy of identifying the weak targets is relatively low. To make full use of radar echo and AIS information and improve the accuracy of target detection, a Marine radar monitoring Internet of Things system is proposed, in which marine radars work in both scanning and staring modes. By adopting image segmentation and deep learning methods, the proposed design can enable accurate perception of weak target detection based on plan‐position indicator (PPI) images. A case study based on the selected X‐band radar datasets shows that the proposed design can achieve high target identification accuracy.

A High-Precision Insulation Inspection Method Based on the Double-Arm Unbalanced Bridge for Electric Ships

In order to ensure the safe navigation of electric ships, it is especially important to detect the insulation status between the ship’s high-voltage system and the ship’s hull in real time. In this paper, a real-time insulation resistance (IR) detection method based on the double-arm unbalanced bridge method was proposed for the problem that the IR calculation results of electric ships have large errors. The detection principle was described, and an experimental test platform was built. The influence law of each branch resistance and voltage on the IR measurement error in this circuit was studied to provide a reference for the parameter selection of the double-arm unbalanced bridge and the effect of temperature on the measurement results was also considered. Besides, the Extended Kalman filtering (EKF) algorithm was used to reduce the influence of voltage fluctuation on the insulation detection error. The results show that the insulation testing method could accurately measure the IR, and the insulation testing error was less than 2.4%, and the error was about 0.18% after processing with the EKF algorithm. This proves that this paper improves the measurement accuracy of IR from three aspects: circuit design of insulation testing, bridge parameter selection and filtering algorithm.

An improved RRT algorithm based on prior AIS information and DP compression for ship path planning

The slow convergence, excessive turning points and non-smooth path generation are significant challenges in ship path planning by existing RRT-related algorithms. To address these issues, this paper proposes a novel approach called PI-DP-RRT, which combines prior automatic identification system (AIS) information and Douglas-Peucker (DP) compression for ship path planning. Firstly, we cluster the available AIS data to construct guide regions, the guidance region can provide information to guide the target in the RRT algorithm. Next, we improve the algorithm's sampling strategy based on the guide region by using paranoid sampling, which increases convergence rate. Finally, we optimize the path by applying the improved DP algorithm and a new path optimization method to enhance its smoothness and practicability. Comparative simulation experiments are conducted in real scenarios and challenging environments. The results indicate that the proposed PI-DP-RRT algorithm outperforms other RRT-related algorithms in terms of efficiency, achieving a good balance between algorithm efficiency and accuracy. The planned path reduces the turning range and improves the smoothness of the path, which promotes the safety and efficiency of ship navigation.

Regulation aware dynamic path planning for intelligent ships with uncertain velocity obstacles

Risk assessment and collision avoidance are extremely important for the safe navigation of surface ships. In this paper, we propose a regulation aware dynamic path planning method based on uncertain velocity obstacles for intelligent ships. Specifically, we first use the fuzzy logic theory to evaluate the real-time collision risk of the own ship. Based on the closest point of approach criterion, considering the influences of the relative bearing, the distance, and ship speed ratio, the collision risk is used to activate the path planning process. Moreover, we consider the various ship encountering scenarios including crossing, overtaking and head-on. To deal with the uncertainties in the target ship information, the relative cone angle of the traditional velocity obstacles are systematically expanded using a robust tube idea. The reachable velocity set of the own ship is accordingly divided into three subsets that meet the rules specified by COLREGs in crossing, overtaking and head-on scenarios. Real automatic identification system (AIS) data in an area of the Yangtze River in Wuhan, China, is used to demonstrate the effectiveness of the proposed approach.

CSP: A Cost-Aware Ship Proportioning Algorithm Based on Operation Process Simulation

Inland waterway dredging is daily maintenance which is undertaken to ensure the safe navigation of ships. Due to the limitations of river width, bridge height, and other conditions, dredging projects usually require different types of ships, namely dredgers, mud-carrying ships, and mud-blowing ships which work in cooperation with each other. The proportion of these three types of ships affects dredging cost and operation efficiency. Most existing algorithms calculate ship proportion according to the operating speeds of ships without considering the influence of navigation locks on waterways. In this paper, we propose a cost-aware ship proportioning (CSP) algorithm based on operation process simulation. The premise is to save dredging cost by making full use of the three types of ships. First, we establish a model to simulate the operation process of the three types of ships considering navigation locks. Furthermore, we utilize the simulation model to obtain the optimal ship proportion that has the lowest cost through loop iterations. In addition, we quantify the relationship between the opening time of navigation locks and the project cost. We evaluate the effectiveness of CSP in terms of the project cost based on real engineering data. The experiment results show that CSP significantly outperforms the baseline.

Statistical Modeling of Arctic Sea Ice Concentrations for Northern Sea Route Shipping

The safe and efficient navigation of ships traversing the Northern Sea Route demands accurate information regarding sea ice concentration. However, the sea ice concentration forecasts employed to support such navigation are often flawed. To address this challenge, this study advances a statistical interpolation method aimed at reducing errors arising from traditional interpolation approaches. Additionally, this study introduces an autoregressive integrated moving average model, derived from ERA5 reanalysis data, for short-term sea ice concentration forecasts along the Northern Sea Route. The validity of the model has been confirmed through comparison with ensemble experiments from the Coupling Model Intercomparison Project Phase 5, yielding reliable outcomes. The route availability is assessed on the basis of the sea ice concentration forecasts, indicating that the route will be available in the upcoming years. The proposed statistical models are also shown the capacity to facilitate effective management of Arctic shipping along the Northern Sea Route.

A Spatial-Reduction Attention-Based BiGRU Network for Water Level Prediction

According to the statistics of ship traffic accidents on inland waterways, potential safety hazards such as stranding, hitting rocks, and suspending navigation are on the increase because of the sudden rise and fall of the water level, which may result in fatalities, environmental devastation, and massive economic losses. In view of this situation, the purpose of this paper is to propose a high-accuracy water-level-prediction model based on the combination of the spatial-reduction attention and bidirectional gate recurrent unit (SRA-BiGRU), which provides support for ensuring the safe navigation of ships, guiding the reasonable stowage of ships, and flood prevention. The first contribution of this model is that it makes use of its strong fitting ability to capture nonlinear characteristics, and it fully considers the time series of water-level data. Secondly, the bidirectional recurrent neural network structure makes full use of past and future water-level information in the mapping process between input and output sequences. Thirdly, and most importantly, the introduction of spatial-reduction attention on the basis of BiGRU can not only automatically capture the correlations between the hidden vectors generated by BiGRU to address the issue of precision degradation due to the extended time span in water-level-forecasting tasks but can also make full use of the spatial information between water-level stations by emphasizing the influence of significant features on the prediction results. It is noteworthy that comparative experiments gradually prove the superiority of GRU, bidirectional recurrent neural network structure, and spatial-reduction attention, demonstrating that SRA-BiGRU is a water-level-prediction model with high availability, high accuracy, and high robustness.

Ship route planning in the pirate area via hybrid probabilistic roadmap algorithm within the context of the Maritime Silk Road

The frequent occurrence of pirate accidents along the Maritime Silk Road has seriously affected the safety of ships. To guarantee navigation safety in pirate activity area, we present a hybrid probabilistic roadmap (HPRM) algorithm for ship route planning. Our HPRM algorithm consists of the improved learning phase and the enhanced exploration phase. Firstly, to improve the utilization of sampling points, the sampling point reset (SPR) function is introduced to generate new sampling points to replace the sampling points in the dangerous area. Secondly, to reduce the number of ship turns, the Douglas–Peucker (D–P) algorithm is utilized to extract the key waypoints (KWP) for generating the optimized route. Finally, the Euler spiral fitting is applied to smooth the route. Numerical cases verified that the ship route planned via the HPRM algorithm is shorter and smoother. This study is conducive to guarantee the safety of ship navigation in the pirate area and enhance ship navigation efficiency, which is of great practical significance for the advancement of the Maritime Silk Road Initiative.

Reliability and availability evaluation on hydraulic system of ship controllable pitch propeller based on evidence theory and dynamic Bayesian network

The hydraulic system is the main power source for the pitch adjustment of the ship's controllable pitch propeller. The stable operation of the system is the guarantee of ship navigation safety. Therefore, it is necessary to analyze the reliability and availability of the hydraulic system of the controllable pitch propeller. In order to deal with epistemic uncertainty and dynamic characteristics in the reliability and availability assessment process of controllable pitch propeller hydraulic systems，the D-S evidence theory and dynamic Bayesian network were applied to establish a novel approach for assessing its reliability and availability. The proposed approach included: (1) analyzing the working principle of the system to establish a reliability block diagram; (2) according to the reliability block diagram, the system dynamic fault tree is established and transformed into DS-DBN model; (3) parameter learning and structure learning of DS-DBN model of controlled pitch propeller hydraulic system; and (4) system reliability and availability calculation, analysis of epistemic importance and weak links. The applicability of the approach was verified by comparison of Markov calculations.

Sea-Surface Object Detection Based on Electro-Optical Sensors: A Review

Sea-surface object detection is critical for navigation safety of autonomous ships. Electro-optical (EO) sensors, such as video cameras, complement radar on board in detecting small obstacle sea-surface objects. Traditionally, researchers have used horizon detection, background subtraction, and foreground segmentation techniques to detect sea-surface objects. Recently, deep learning-based object detection technologies have been gradually applied to sea-surface object detection. This article demonstrates a comprehensive overview of sea-surface object-detection approaches where the advantages and drawbacks of each technique are compared, covering four essential aspects: EO sensors and image types, traditional object-detection methods, deep learning methods, and maritime datasets collection. In particular, sea-surface object detections based on deep learning methods are thoroughly analyzed and compared with highly influential public datasets introduced as benchmarks to verify the effectiveness of these approaches. The article also proposes the direction of future research for sea-surface object detection based on EO sensors.

Navigation Risk Assessment of Autonomous Ships Based on Entropy–TOPSIS–Coupling Coordination Model

An autonomous ship refers to a ship that achieves autonomous operation in ship navigation, management, maintenance, cargo transportation and other aspects. Due to the uncertainty in the risks posed by autonomous ship navigation, its risk assessment attracts great attention from researchers. By analyzing the historical accident statistics, this paper gives a comprehensive analysis from the perspective of “Man-Ship-Environment-Management”. In addition, a quantitative evaluation method based on the Entropy–TOPSIS–Coupling coordination model is proposed, which presents a comprehensive assessment of the risks of autonomous ship navigation safety. Furthermore, scientific forecasts and suggestions for improvement are put forward according to the evaluation results.

An INS-aided MASS autonomous navigation algorithm considering virtual motion constraints and the leeway and drift angle

Autonomous navigation is one of the critical enabling technologies in developing MASS or intelligent ships. This study proposes an autonomous navigation algorithm with INS-aided shipborne GNSS. The proposed algorithm constructs the ship's virtual motion attitude by considering the leeway and drift angle, and takes into account the one-dimensional speed constraints in the virtual ship body reference frame. This approach addresses the issue that the conventional INS and shipborne GNSS integrated navigation scheme can utilize the three-dimensional position information only, without considering the measurement update from the one-dimensional speed obtained by shipborne GNSS. The algorithm is verified by actual ship departure and cruising experiments in natural marine environments. The experimental results show that the proposed algorithm has a higher accuracy than the conventional algorithm when the GNSS speed and position information are available. In the scenario when the GNSS position information is temporarily lost, the proposed algorithm can continue to derive relatively reliable navigation parameters for the safe navigation of ships with only one-dimensional speed measurement.

A Study on Grid-Cell-Type Maritime Traffic Distribution Analysis Based on AIS Data for Establishing a Coastal Maritime Transportation Network

Recently, marine development plans such as offshore wind farms and marina port facilities have been established to use Korean coastal waters, and research on the development of operational ships such as autonomous ships and water-surface flying ships is being rapidly promoted. Since the marine traffic in Korean coastal waters is expected to increase, the government intends to construct a coastal maritime transportation network that connects Korean coastal waters to guarantee safe ship navigation. Therefore, this study used automatic-identification-system data analysis to obtain quantitative evaluation results on maritime traffic distribution characteristics and utilization levels for the entire Korean coastal waters in grid cell for greater consistency and compatibility. The characteristics of marine traffic distribution at a certain site in coastal Korean waters can be quantitatively examined using the findings of this study, and they may be used as grid-cell-type data-based information. Moreover, the vessel traffic index allows for extensive research while quickly understanding the present level of use of the passing ships by the sea area. In this regard, the findings of this study are expected to be useful for the future development of maritime transportation networks in Korean coastal waters.

A novel deep learning framework for detecting seafarer’s unsafe behavior

The accurate detection of seafarers’ unsafe behaviors is of great significance to improve the ship navigation safety. This study proposes an improved deep learning framework with a self-made dataset to detect the unsafe behavior of seafarers on duty. In order to increase the detection speed, the improved Cross Stage Partial connections (CSP) module is proposed to replace the original CSP module in the neck network of traditional algorithm. The efficient channel attention (ECA) module is also introduced to the backbone network of conventional algorithm as the attention mechanism network. In addition, the learning and representation capacities of the improved deep learning framework are promoted by redesigning the sizes of anchor boxes. The experiment results show that the proposed framework outperforms traditional object detection algorithms (e.g., YOLOv5s, R-CNN) in detecting seafarers’ unsafe behaviors because of the much higher detection speed and detection accuracy.

A Comparison of Machine Learning and Empirical Approaches for Deriving Bathymetry from Multispectral Imagery

Knowledge of the precise water depth in shallow areas of the ocean is of great significance to the safe navigation of ships and hydrographic surveying. Compared with traditional bathymetry, satellite remote sensing for water depth determination makes it possible to cover large areas by dynamic observation. In this paper, we conducted an optically shallow water bathymetric inversion study using a Stumpf empirical model, random forest model, neural network model, and support vector machine model based on Sentinel-2 satellite images and Ganquan Dao measured bathymetry data. We compared and analyzed the inversion results based on the empirical model and different machine learning models. The results show that the Stumpf empirical and machine learning models are capable of inverting optically shallow water depth. Moreover, the machine learning models had better fitting ability than the Stumpf empirical model with a sufficient number of samples, especially when the water depth was greater than 15 m. In addition, the random forest model had the highest overall accuracy among these models, with a root mean square error (RMSE) of 1.41 m and a regression coefficient (R2) of 0.96 for the test data.