Ship Behavior Research Articles

Anomaly Detection and Restoration for AIS Raw Data

With the wide application of location detection sensors in maritime surveillance, a large amount of raw automatic identification system (AIS) data is produced by many moving ships. Anomaly detection and restoration of the big AIS data are important issues in marine data mining, because they offer a reliable support to users to mining the behaviors of ships. This paper develops a novel approach to detect anomaly AIS data based on the ships’ maneuverability, such as the maximum acceleration, the minimum acceleration, the maximum distance, and the maximum angular displacement, which were designed to detect the anomaly AIS data. Furthermore, the performance of the developed approach is compared with that of Daiyong-Zhang’s method and Behrouz-Haji-Soleimani’s method to assess its detection efficiency. The results show that the proposed approach can be applied to easily extract the abnormal data. Finally, based on the developed approach to detect the anomaly data and cubic spline interpolation method to restore the AIS data, experiments are conducted on the AIS data of Xiamen Port of Fujian Province, China, that prove to be effective for marine intelligence research.

Experimental analysis of wave-induced vertical bending moment in steep regular waves

Recent studies have benchmarked the prediction of the wave vertical bending moment (VBM) of ships in waves and found significant scatter among the numerical codes. A long series of tests with segmented hulls have been reported in the literature over the past 70 years to assess the vertical bending moment. However, alongside the improvement in numerical tools and the modeling of ships’ internal loads, the scientific community still requires accurate experimental data measured in steep waves (ratio of wave height H to wavelength λ, H/λ= 0.1) where the ship behavior and loads are modified by non-linearities. Thus, in order to validate simulation codes, and to establish criteria and requirements that make ships safer to sail in severe sea conditions, some experiments were carried out in the 50 m × 30 m × 5 m hydrodynamic and ocean engineering tank of the Ecole Centrale Nantes. A 1/65th scaled model of a 6750-TEU containership was used. The ship was moored and several combinations of wavelength and wave height were tested. The present experiments were performed on a segmented hull with a 6DOF load sensor located close to amidship, where some measurements were available from previous studies. The design, which did not use strain gauges, was done specifically to increase the first structural mode frequency and the stiffness of the model in order to reduce and make it possible to filter out hydro-elastic effects. The model motion was measured through a Qualisys IR tracking system and accelerometers were located on the fore and aft of the beam. Also, each of the 9 segments is equipped with a 3DOF dynamometer to measure the hydrodynamic loads on the hull. A mathematical description of the relations between the hydrodynamic forces, the load measurements and the internal forces is given in the paper. This makes it possible to retrieve the hydrodynamic loads on the segments and then to compute the shear force and bending moment discretized at each intersegment all over the ship length. Particular care was paid to the reproducibility and repeatability of the tests. The experimental setup and the measured data are presented in the paper. Hydrodynamic loads are reconstructed and the obtained VBM is compared with the 6DOF sensor measurement. The non-linear effects of increasing the wave steepness on motions and bending moment are discussed.

Extracting ship stopping information from AIS data

Ship stopping information is important for ship voyage division, ship traffic flow analysis, and maritime trade network analysis. A method of ship stopping information extraction that integrates trajectory features and geographic scenario semantics is proposed based on automatic identification system (AIS) data. First of all, under the constraints of port geographic knowledge, the ship trajectory features are excavated to realize the recognition of ship stopping points in the port area with the recognition accuracy rate of 0.94, the recall rate of 0.91, and the F1 value of 0.92. Secondly, 15 ship stopping mode classification features are selected from both trajectory features and geographic semantics, and a random-forest-based ship stopping classification model is constructed. Two stopping modes, berth stopping and anchorage stopping, are classified with the overall classification accuracy rate of 0.93 and the Kappa coefficient of 0.87. Finally, the port points are generated based on the ship berth stops, and 1,050 port points in the South China Sea Silk Road region are extracted with an accuracy rate of 98.41%. The experimental results show that the proposed method can effectively extract ship stopping information and provide knowledge support for ship behavior understanding and ship traffic analysis.

Ship Steering Adaptive CGS Control Based on EKF Identification Method

In recent years, marine autonomous surface vessels (MASS) have grown into a ship research issue to increase the level of autonomy of ship behavior decision-making and control while sailing at sea. This paper focuses on the MASS motion control module design that aims to improve the accuracy and reliability of ship steering control systems. Nevertheless, the stochastic sea and wind environment have led to the extensive use of filters and state observers for estimating the ship-motion-related parameters, which are important for ship steering control systems. In particular, the ship maneuverability Nomoto index, which primarily determines the designed ship steering controller’s performance, cannot be observed directly due to the model errors and the external environment disturbance in the process of sailing. Hence, an adaptive robust ship steering controller based on a closed-loop gain shaping (CGS) scheme and an extended Kalman filter (EKF) on-line identification method is explored in this paper. To verify the effectiveness of the proposed steering controller design scheme, the motor vessel YUKUN was taken as the control plant and a series of simulation experiments were carried out. The results show the advantages of the dynamic response performance of the proposed steering controller compared with the classical PD and traditional CGS controllers. Therefore, the proposed adaptive CGS steering controller would be a good solution for MASS motion control module design.

Ontological Ship Behavior Modeling Based on COLREGs for Knowledge Reasoning

Formal expression of ship behavior is the basis for developing autonomous navigation systems, which supports the scene recognition, the intention inference, and the rule-compliant actions of the systems. The Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) offers experience-based expressions of ship behavior for human beings, helping the humans recognize the scene, infer the intention, and choose rule-compliant actions. However, it is still a challenge to teach a machine to interpret the COLREGs. This paper proposed an ontological ship behavior model based on the COLREGs using knowledge graph techniques, which aims at helping the machine interpret the COLREGs rules. In this paper, the ship is seen as a temporal-spatial object and its behavior is described as the change of object elements in time spatial scales by using Resource Description Framework (RDF), function mapping, and set expression methods. To demonstrate the proposed method, the Narrow Channel article (Rule 9) from COLREGs is introduced, and the ship objects and the ship behavior expression based on Rule 9 are shown. In brief, this paper lays a theoretical foundation for further constructing the ship behavior knowledge graph from COLREGs, which is helpful for the complete machine reasoning of ship behavior knowledge in the future.

Investigation of ship responses in regular head waves through a Fully Nonlinear Potential Flow approach

In this study, the hydrodynamic performance of a ship in terms of motions and resistance responses in calm water and in regular head waves is investigated for two loading conditions using a Fully Nonlinear Potential Flow (FNPF) panel method. The main focus is understanding the ship responses in a broad range of operational conditions. Comprehensive analyses of the motions and their correlation with the wave making resistance including their harmonics in waves are presented and compared against experimental data. The predicted motions compare well with experimental data but the resistance prediction is not quite as good. The natural frequencies for heave and pitch are estimated from a set of free decay motion simulations in calm water to provide a better insight into the ship behavior near resonance conditions in waves. Interestingly, in addition to the well known peak in the added wave resistance coefficient around wave lengths close to one ship length, a secondary peak is detected in the vicinity of wave lengths with half the ship length.

Review of Ship Behavior Characteristics in Mixed Waterborne Traffic

Through the continuous development of intellectualization, considering the lifecycle of ships, the future of a waterborne traffic system is bound to be a mixed scenario where intelligent ships of different autonomy levels co-exist, i.e., mixed waterborne traffic. According to the three modules of ships’ perception, decision-making, and execution, the roles of humans and machines under different autonomy levels are analyzed. This paper analyzes and summarizes the intelligent algorithms related to the three modules proposed in the last five years. Starting from the characteristics of the algorithms, the behavior characteristics of ships with different autonomous levels are analyzed. The results show that in terms of information perception, relying on the information perception techniques and risk analysis methods, the ship situation can be judged, and the collision risk is evaluated. The risk can be expressed in two forms, being graphical and numerical. The graphical images intuitively present the risk level, while the numerical results are easier to apply into the control link of ships. In the future, it could be considered to establish a risk perception system with digital and visual integration, which will be more efficient and accurate in risk identification. With respect to intelligent decision-making, currently, unmanned ships mostly use intelligent algorithms to make decisions and tend to achieve both safe and efficient collision avoidance goals in a high-complexity manner. Finally, regarding execution, the advanced power control devices could improve the ship’s maneuverability, and the motion control algorithms help to achieve the real-time control of the ship’s motion state, so as to further improve the speed and accuracy of ship motion control. With the upgrading of the autonomy level, the ship’s behavior develops in a safer, more efficient, and more environment-friendly manner.

Mining rules of decision-making for fleet composition under market uncertainty using a genetic algorithm

This study proposes a method for determining decision-making rules on fleet composition that are effective from a perspective of profitability in the shipping industry, where there are several market uncertainties such as fuel prices, freight rates, exchange rate, transportation demand, world transportation capacity, and ship price. A simulator is used to calculate the revenue of the fleet composition based on the market scenario. Using this to optimize the buying and selling behavior of ships, decision-making rules regarding fleet composition can be determined. The rules are expressed as a vector, and a genetic algorithm (GA) is used for optimization. As a case study, the method was applied to container ships operating between Asia and Europe. The simulation revealed optimal decision-making rules. Moreover, a controlled experiment was conducted to validate the effectiveness of the rules. Participants were randomly divided into two groups: those with rules and those without rules, and they were asked to perform buying and selling behavior in a simulated environment. By comparing these groups’ profits, it is validated that the rules discovered by the method are useful because they encourage decision-making from a long-term perspective.

Evaluation Model of Ship Berthing Behavior Based on AIS Data

In recent years, the research on ship behavior and ship berthing behavior is a hot topic in the navigation theory research, but the research on ship berthing behavior evaluation is relatively less. Based on the navigation theory, the characteristics of ship berthing behavior (including course, course changes, speed, speed changes and ship position) are extracted, and the berthing behavior evaluation index system is established. According to the characteristics of each behavior, the mathematical description is given for quantitative analysis. Based on the principle of “safety, stability and efficiency”, the evaluation standard is determined for each evaluation index, and the evaluation model is established. The Z-score method is used to standardize the evaluation index data, and the critical method is used to calculate the objective weight of each evaluation index; finally, the model is used to get the evaluation results of each berthing behavior. In this paper, the evaluation model is tested by using the one month’s AIS (Automatic Identification System) berthing data of Tianjin port, and the evaluation results are in line with the actual navigation.

桟橋と係留船の連成運動を考慮した津波来襲時の大型石炭船の挙動再現

桟橋と係留船の連成運動を考慮した津波来襲時の大型石炭船の挙動再現

Development of Fuzzy Observer Gain Design Algorithm for Ship Path Estimation Based on AIS Data

This paper develops a Takagi-Sugeno fuzzy observer gain design algorithm to estimate ship motion based on Automatic Identification System (AIS) data. Nowadays, AIS data is widely applied in the maritime field. To solve the problem of safety, it is necessary to accurately estimate the trajectory of ships. Firstly, a nonlinear ship dynamic system is considered to represent the dynamic behaviors of ships. In the literature, nonlinear observer design methods have been studied to estimate the ship path based on AIS data. However, the nonlinear observer design method is challenging to create directly since some dynamic ship systems are more complex. This paper represents nonlinear ship dynamic systems by the Takagi-Sugeno fuzzy model. Based on the Takagi-Sugeno fuzzy model, a fuzzy observer design method is developed to solve the problem of estimating using AIS data. Moreover, the observer gains of the fuzzy observer can be adjusted systemically by a novel algorithm. Via the proposed algorithm, a more suitable or better observer can be obtained to achieve the objectives of estimation. Corresponding to different AIS data, the better results can also be obtained individually. Finally, the simulation results are presented to show the effectiveness and applicability of the proposed fuzzy observer design method. Some comparisons with the previous nonlinear observer design method are also given in the simulations.

HISTORICAL TRAILS OF SHIP BROACHING-TO

The article intends to bring back to light old perceptions about the “broaching-to” behaviour of ships. The signature of broaching-to is the sudden loss of controllability. The phenomenon sometimes ends with vessel capsize. The findings of an investigation into old bibliographical sources are reported, spanning more than 300 years of use of the term. Several citations have been identified in texts of nautical or related content, including voyagers’ records, nautical journals, training manuals, old encyclopaedias and even literary sources and leisure magazines. At a time when broaching-to is considered in the currently formulated new ship stability criteria at IMO, this paper provides a historical perspective on a problem that has maintained relevance despite the changes in ship technology and design.

A COMPARISON OF EXPERIMENTAL AND NUMERICAL BEHAVIOUR CHARACTERISTICS OF A SHIP ENTERING A LOCK USING BENCHMARK TEST DATA

This paper discusses several papers that were presented at the 3rd International Conference on Ship Manoeuvring in Shallow and Confined Water, which had a non-exclusive focus on Ship Behaviour in Locks. For this conference, experimental model test data obtained at Flanders Hydraulics Research had been made public and researchers were encouraged to compare numerical with experimental results [1]. Data of benchmark tests carried out both with self- propelled and captive models were used by researchers for comparison with various numerical tools. The objective of this paper is to give a selected overview of how accurately numerical tools are presently able to predict the hydrodynamic forces that occur on ships approaching locks. Based on this, the paper concludes that experiments and numerical tools complement each other.

CFD-BASED HYDRODYNAMIC ANALYSIS FOR A SHIP SAILING ALONG A BANK IN RESTRICTED WATERS


 
 
 The paper is interesting, good structured and deals with an important problem concerning ship behaviour in restricted water. The use of a CFD method as FLUENT (code also used at Ghent University) shows the possibilities of numerical methods for the calculation of ship-bank interaction. The content could still be improved as some topics in the paper miss some depth.
 
 

Reducing emissions of atmospheric pollutants along major dry bulk and tanker routes through autonomous shipping

The present study investigates the environmental benefits of phasing-in autonomous ships in global maritime transportation along major dry bulk and tanker routes using Bayesian probabilistic forecasting algorithm. The focus is on the simulations and calibrations on the navigational behavior of autonomous ships at both port and high-sea, as well as the potential emission abatement of atmospheric pollutants compared to the conventional fleet along the sailing routes. We use historical data on major international tanker and dry bulk trade routes to characterize the ship movements and trends in ship emission. Different scenarios are evaluated with a combination of autonomous ship phase-in rates (25, 75, 100%) and cleaner fuel choices in Years 2030 and 2050 (from the baseline Year, 2020). The results show that the magnitude of the emission reduction generally increases with a higher level of autonomous ships in the fleet as expected, and the magnitude ranges from small increments to major reductions of 37–64% along the different routes. Overall, we hope that our findings can contribute towards the realization of environmental benefits with the adoption of autonomous shipping along the major shipping routes in the future.

A Multi-Feature Ensemble Learning Classification Method for Ship Classification with Space-Based AIS Data

AIS (Automatic Identification System) is an effective navigation aid system aimed to realize ship monitoring and collision avoidance. Space-based AIS data, which are received by satellites, have become a popular and promising approach for providing ship information around the world. To recognize the types of ships from the massive space-based AIS data, we propose a multi-feature ensemble learning classification model (MFELCM). The method consists of three steps. Firstly, the static and dynamic information of the original data is preprocessed and features are then extracted in order to obtain static feature samples, dynamic feature distribution samples, time-series samples, and time-series feature samples. Secondly, four base classifiers, namely Random Forest, 1D-CNN (one-dimensional convolutional neural network), Bi-GRU (bidirectional gated recurrent unit), and XGBoost (extreme gradient boosting), are trained by the above four types of samples, respectively. Finally, the base classifiers are integrated by another Random Forest, and the final ship classification is outputted. In this paper, we use the global space-based AIS data of passenger ships, cargo ships, fishing boats, and tankers. The model gets a total accuracy of 0.9010 and an F1 score of 0.9019. The experiments prove that MFELCM is better than the base classifiers. In addition, MFELCM can achieve near real-time online classification, which has important applications in ship behavior anomaly detection and maritime supervision.

MVFFNet: Multi-view feature fusion network for imbalanced ship classification

The accurate classification of moving ships is of fundamental importance to maritime authorities for ensuring the safety and security of shipping operations. With the wide use of automatic identification systems (AISs), which allow ships to receive identification/location information from nearby ships, it is feasible to classify the types of ships by analysing ship behaviour from AIS-based trajectories. However, the imbalanced features of AIS data make it difficult to achieve satisfactory classification results in the presence of several different types of ships. To overcome these potential limitations, we propose a multi-view feature fusion network (MVFFNet) to achieve accurate ship classification with imbalanced data. To guarantee the powerful representation and generalization abilities of MVFFNet, we first extract several multi-view features (i.e., motion features and morphological features) from AIS-based ship trajectories. Several kinematic variables related to ship behaviour are empirically adopted as motion features. The morphological features are automatically extracted via convolutional auto-encoder (CAE) networks. CAE networks are capable of optimally learning the features from informative trajectory images, which are strictly related to the original ship trajectories. The bidirectional gated recurrent unit (BiGRU) network is then proposed to combine multi-view features to generate the ship classification results. In addition, a hybrid loss function is presented to handle the imbalance problem of ship types, potentially leading to enhanced robustness and accuracy of ship classification. Comprehensive experiments on two realistic datasets have demonstrated that our proposed MVFFNet consistently outperforms other competing methods in terms of classification accuracy and robustness.

Numerical investigation on the cavity behavior and hydrodynamic performance of a planing air cavity ship

Air lubrication is an effective way to improve the hydrodynamic performance of ships. This study focuses on the cavity behaviors and hydrodynamic performance of air cavity ship (ACS) across a wide range of volumetric Froude number (Fr▽) and ventilation coefficient (Cq) via the computational fluid dynamics (CFD) method. The drag reduction and trim of the ACS are found to first increase with the Fr▽ and then decrease, while the sinkage increases monotonously. For the constant Fr▽, the drag reduction first increases quickly with the Cq and then remains unchanged, while the trim and sinkage roughly keep increasing. The drag reduction and motion attitude of the ACS are affected by the air cavity under the hull. By further looking into the cavity behavior, the air coverage and the pressure distribution of the cavity are considered as the key influence factors for the drag reduction and motion attitude of the ACS, while the quantitative cavity thickness and internal airflow indicate the influence of Fr▽ and Cq on the air layer distribution and the dynamic flow inside the air cavity, respectively. Different internal airflows are found in the closed-form cavity and the open-form cavity. Moreover, once the air supply is stopped, the air cavity forms are crucial for the cavity behavior, the corresponding drag and motion of the ACS. For the closed-form cavity, the closure moves upstream slowly after the air ventilation stopped. However, the open-form air cavity breaks into two parts due to the upstream necking process of the cavity.

Study on the behavior of benchmark container ships in regular waves

The study of the behaviour of ships in the real sea has become a real challenge in recent years due to climate change, especially in the European sea basin. One of the main categories of types of ships that cross these waters are transport ships. The development of the economy and trade have a major influence on this type of ships, which must be studied and improved in order to be fully exploited. Investigating the ship’s behavior is not a new topic, but the changing environment of the transport ship’s specifications requires continuous study. An alternative to model testing is the use of numerical simulation through which performance can be fully evaluated using only computers, without the need to produce a scale model for testing. Due to improved computer performance, but also the disadvantages of towing testing, numerical simulations have become increasingly popular for determining ship characteristics. The shorter time in which results can be obtained, as well as the ease of controlling and changing the input parameters, contributes to the preference to use numerical simulations, to the detriment of basin tests. In this paper, the behavior of a Post-Panamax benchmark container ship in regular waves was studied. Numerical simulations were performed using SHIPFLOW MOTIONS, a solver that treats potential nonlinear flows for regular waves and provides accurate results by the free surface potential flow panel method. For our case, the simulations were performed for a range of six speeds corresponding to Froude numbers ranged between 0.174 and 0.218, for five nondimensional wavelengths (λ/Lpp) and for four wave heights. Because body discretization is one of the main factors for obtaining accurate results, an additional study was conducted in calm waters on body refinement and the influence that the mesh has on results, for a range of ten grids with different densities.

A Novel Metric for Detecting Anomalous Ship Behavior Using a Variation of the DBSCAN Clustering Algorithm

A Novel Metric for Detecting Anomalous Ship Behavior Using a Variation of the DBSCAN Clustering Algorithm