Collision Risk Index Calculation Based on an Improved Ship Domain Model

Liu, Weifeng; Zhong, Lufeng; Yang, Xu; Shi, Guangming

doi:10.3390/jmse10122016

Cited by 11 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A dynamic elliptical ship domain based on AIS data combines the relative motion between ships in different encounter situations to assess the level of ship intrusion in the domain. However, during the movement, the size of the ship domain is static, not changing with speed [25].…”

Section: Related Workmentioning

confidence: 99%

A Study on A Novel Collision Risk Prediction Map for Maritime Traffic Surveillance Based on Ship Domain

Quang Nguyen,

Nam Luong,

Luong Tran

2024

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Recently, a regional model for assessing the risk of multi-ship collision has been developed to reduce the risk of ship collision in territorial sea areas such as trade ports and entry waterways and improve the safety and efficiency of ship traffic. The focus is on marine traffic in the visualized waters with the risk of ship collision. However, due to the lack of information from experts with sufficient knowledge and experience in a given area, they also have some limitations in adequately and comprehensively representing the risk of collision, especially in busy waterways where encounters of more than two ships often appear. In addition, they could not visualize the location of the proximity collision and the exact risk value in real time. Therefore, to overcome the limitations of previous studies, this paper proposes a new regional collision risk visualization system, which combines density-based spatial clustering of applications with noise (DBSCAN) and analysis and knowledge-based ship domains and uses AIS data to intuitively and accurately map the dynamic collision risk of water areas at successive moments, predict areas where collisions can happen by dynamic risk index and warn the ships. Identifying high-risk collision areas between multi-ships can be enhanced using the developed system, which allows for reliable and accurate analysis to help implement safety measures.

show abstract

Section: Related Workmentioning

confidence: 99%

A Study on A Novel Collision Risk Prediction Map for Maritime Traffic Surveillance Based on Ship Domain

Quang Nguyen,

Nam Luong,

Luong Tran

2024

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

show abstract

“…In other words, D pca is defined as the margin distance required for collision avoidance (here, the intended TCPA is multiplied by the ship's speed) and the turning delay. The intended TCPA, ∆t, was set as 15 min, as applied multiple times in a number of past studies and cases [42][43][44]. In this study, as described above, reach is 1 to 2 times the length of the ship, meaning R OS , the median value of the reach point range, was set to 1.5.…”

Section: Proper Time For Collision Avoidancementioning

confidence: 99%

Determining the Proper Times and Sufficient Actions for the Collision Avoidance of Navigator-Centered Ships in the Open Sea Using Artificial Neural Networks

Kim

Park

2023

JMSE

View full text Add to dashboard Cite

Ship collisions are a major maritime accident; various systems have been proposed to prevent them. Through investigating and analyzing the causes of maritime accidents, it has been established that ship collisions can either caused by delaying actions or not taking the sufficient actions to avoid them. Recognizing the limitations in providing quantitative numerical values for avoiding ship collisions, this study aimed to use Bayesian regularized artificial neural networks (BRANNs) to suggest the proper time and sufficient actions required for ship collision avoidance consistent with the Convention on the International Regulations for Preventing Collisions at Sea. We prepared the data by calculating the proper times and sufficient actions based on precedent research and used them to train, validate, and assess the BRANNs. Subsequently, an artificial neural network controller was designed and proposed. The data of the proposed neural network controller were verified via simulation, validating the controller. This study is limited in cases such as overtaking a ship in front. However, it is expected that this controller can be improved by establishing the criteria for an appropriate overtaking distance after further examining the closest point of approach (CPA) and time to the CPA (TCPA) for overtaking a ship in front and using the method presented herein.

show abstract

“…In [9], such a comprehensive approach to assessing the risk of capital investment of ships is proposed, including parameters of use such as the closest point of approach (DCPA), the time to the closest point of approach (TCPA), and the capital increase risk index (CRI). However, despite the thoroughness of these methods, the cited article does not take into account the human factor, in particular, the states and actions of the shipmaster during the navigation watch.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Devising an approach to safety management of vessel control through the identification of navigator’s state

Nosov,

Koretsky,

Zinchenko

et al. 2023

EEJET

View full text Add to dashboard Cite

The object of this study is the processes of automated management of maritime safety by analyzing the manifestations of the human factor of sea navigators. The task solved is justified by the need for formal and logical analysis and intelligent identification of mental motivational states (MMS) of marine navigators whose actions can cause dangerous situations during the control of the ship’s movement. High accident rates due to the fault of the navigators, in the absence of automated means of monitoring their condition, cause a contradiction between the existing means of safety control in controlling the movement of the vessel and the modern requirements of navigation, which needs to be resolved. A safety management approach was devised that takes into account the specificity of navigational tasks and the p-adic classification of dangerous MMS for navigators. This has made it possible to create three security modes that are activated depending on the detected state of the navigator’s MMS. Features of the results are the combination of analysis by means of p-adic systems and intelligent methods of data processing. As a result, sufficient identification accuracy was obtained for more than 75 % of MMS through neural network training. Experimental data collected during the navigation watch, as well as on the Navi Trainer 5000 navigation simulator (Wärtsilä Corporation, Finland), became the basis for simulation by means of neural networks. In turn, the training of neural networks made it possible to obtain sufficient identification accuracy by performing up to 3000 iterations. Overall, the learning rate of the neural network was 0.98, which indicates a high level of identification. From a practical point of view, the results could be used for the automated management of shipping safety, as well as for evaluating the level of adaptation of the navigator to dynamically changing conditions. The proposed approach provides opportunities for the application of modern intelligent technologies in the field of maritime transport safety, namely artificial neural network tools that determine notification modes or activation of automatic ship traffic control modules. The specified contradiction requires the design of specialized systems for automated safety management of ship traffic control based on the identified states of navigators

show abstract

Collision Risk Index Calculation Based on an Improved Ship Domain Model

Cited by 11 publications

References 28 publications

A Study on A Novel Collision Risk Prediction Map for Maritime Traffic Surveillance Based on Ship Domain

A Study on A Novel Collision Risk Prediction Map for Maritime Traffic Surveillance Based on Ship Domain

Determining the Proper Times and Sufficient Actions for the Collision Avoidance of Navigator-Centered Ships in the Open Sea Using Artificial Neural Networks

Devising an approach to safety management of vessel control through the identification of navigator’s state

Contact Info

Product

Resources

About