Abstract
In order to gain a deep understanding of the operation of different ships in different time states and understand the geographical distribution of the encounters of ships near Gulei Port and the maneuvering behavior patterns of ships in the port area, this essay is different from the traditional single ship versus multi-target ship research. Through the comprehensive processing and data regulation of Gulei Port AIS (Automatic Identification System) data, the ships with consistent temporal and spatial characteristics are found, and the time and geographical position of the voyage data are revised, which solves the problem of asynchronous data processing of multi-target ships at different times. By ship navigation data mining, obtaining the trajectory distribution of the ship under a certain time condition, the distribution of the encounter area, the geographical distribution of the speed, and the law of ship speed and heading changes triggered by the formation of the encounter, summing up the same behavioral characteristics of different ship maneuvering modes in the port area at low speed.
You have full access to this open access chapter, Download conference paper PDF
Similar content being viewed by others
Keywords
1 Introduction
Due to the complex characteristics of maritime transport itself, it is often necessary to comprehensively consider various aspects in the study of maritime transport, such as navigation waters, natural conditions, traffic conditions and other complex factors. In addition, the basic data collection and investigation of maritime transport also need to consider many data characteristics, such as ship density distribution, track distribution, traffic flow, traffic volume, speed distribution, ship arrival law, encounter rate and collision avoidance behavior. At the same time, due to the lack of AIS data, abnormal data, asynchronous broadcast time and large span, the availability and effectiveness of data are greatly reduced, and the subsequent data processing problem increasingly becoming the focus of research. The AIS data are used to realize ship behavior recognition based on multi-scale convolution [1]. The AIS data are mined, the complex and changeable ship routes are analyzed, and the behavior characteristics of ships are analyzed [2]. Research on ship behavior based on semantic level [3] and AIS data visualization [4] are exploring how to maximize the function of AIS data. Therefore, the use of AIS data mining for effective information on the regional distribution of multi-objective ships encountering and the characteristics of ship maneuvering behavior can help relevant personnel to understand the ship maneuvering law under realistic conditions and make corresponding adjustments according to the characteristics of ship maneuvering behavior. At the same time, it is of great significance for the deployment of maritime navigation aid facilities.
2 AIS Data Preprocessing
The data of ship automatic identification system includes the dynamic data and static data of the ship. Under realistic conditions, due to the influence of ship operation conditions and signal processing errors, AIS data are missing, repetitive and abnormal, which brings some difficulties to AIS data processing and analysis. The time asynchronous problem of AIS data between ships leads to further improvement of data processing difficulty. In order to improve the accuracy and reliability of the data, the missing value and abnormal value of the original AIS data are processed in advance. The data with the interval time span of data items greater than 30 min in the AIS data are deleted, and the data with abnormal speed are deleted. In order to facilitate the analysis of the actual navigation data with relatively large capacity, the ship navigation data with AIS data items greater than 300 are extracted, and the extracted 308 ship data are statistically analyzed. The data processing flow is show in Fig. 1.
3 Identification of Ship Encounter Area
3.1 Ship Distance Correction
Due to the asynchronous broadcast time of AIS data of different ships, there is a negative obstacle to the calculation of spherical distance between different ships. The spherical triangle sine theorem is used to correct the position of different ships. The distance between the target ship and the ship is corrected, and the navigation state of the two ships is compared at the same time. The spherical distance of the two ships is corrected to the same time. The distance between the two ships at the same time is used as the basis for detecting the occurrence of the encounter situation. At the same time, the distance between the two ships before and after the correction is recorded. When the distance between the two ships is small and less than a certain threshold, it is considered that the two ships have a potential encounter situation. The behavior mode of the ship before and after the time point is used to judge the steering and speed change measures after the encounter of the ship. The extracted AIS data of ships are shown in Table 1.
By selecting two different ships, the distance of the point with the closest time difference is calculated. Due to the phenomenon of time asynchronous, the position of the ship A in time T1 and the ship B in time T2 is shown in Fig. 2. Due to the T1 and T2 is inequality, there is a certain time difference. Assuming T1 is greater than T2, to compare the distance of the two ships at the same time T2, it is necessary to correct the position of the ship at the moment T2, and move in the opposite direction along the existing course and speed of the ship A. The motion time is δt, the distance between the ship A and the ship B is corrected to the distance at the same time T2, that is, the distance between the ship A and the ship B at the moment T2.
Spherical distance formula:
where \(R\) is the radius of the earth, and the geographical coordinates of the two ships are \(A(\alpha_1 ,\beta_1 )\), \(B(\alpha_2 ,\beta_2 )\). Where \(\alpha_1\) and \(\alpha_2\) is the longitude of the ship and the target respectively, \(\beta_1\) and \(\beta_2\) is the latitude of the two ships, \(\theta\) is the center angle of the large circle of the two points \(A\) and \(B\), and \(L\) is the spherical distance of the two ships.
Since the navigation state of the ship on the water surface is constantly changing, the applicable condition of the correction method is that the change of ship heading and speed is relatively small under the condition of small-time difference, and the distance between the ship and the target ship is approximately linear. Therefore, in this paper, the time difference of the correction method is controlled to be less than or equal to 30Â min, and the corrected distance is less than 3.8Â nm [5] as the condition for the occurrence of the ship encounter situation. Thus, in the range of the existing AIS data, different ships with the corrected distance lower than the threshold and the close position and time are obtained. These two ships are considered as potential encounter ships, and the navigation data of these two ships are analyzed. The statistics of some encounter ships are shown in Table 2:
3.2 Statistical Characteristics of AIS Data
Ship trajectory and velocity distribution in the region.
Through the AIS data obtained after data preprocessing, the trajectory distribution of the ship in the region can be obtained in different periods. As shown in Fig. 3, the ship trajectory is dense in the triangle area that identifies different latitudes and longitudes. At the same time, the speed feature extraction of the existing AIS data under different latitudes and longitudes is carried out. Through three fittings, the speed distribution map of ship navigation in the region is obtained. Compared with the left and right parts, it can be seen that in the triangle area, the ship navigation speed is slow and the ship trajectory is dense. In this range, the maritime traffic volume is large and the frequency of ship encounters is relatively high.
Ship encounter area mining.
Through the historical AIS data information, the ships with relatively close distance at the same time and less than the threshold are selected. The speed change and heading change of each ship before and after the formation of the encounter situation are analyzed, and the latitude and longitude coordinates of the nearest encounter distance between the two ships are analyzed. From the existing statistical data, the geographical coordinates of all ships in the data range can be obtained, and the ship encounter area distribution near Gulei Port is obtained. As shown in Fig. 4, the ship encounter area is basically concentrated in the triangle area shown in Fig. 3, and at longitude 117.5, latitude 23.74. The zonal area formed by longitude 117.6, latitude 23.65 and longitude 117.6, latitude 23.69 shows that the natural conditions, traffic conditions and hydrological conditions of the three nearby areas have great influence on the ship. At the same time, the area should also be the place where the relevant departments set up navigation aids and focus on monitoring navigation safety.
4 Feature Mining of Ship Maneuvering Behavior
The ship’s navigation behavior is affected by the water period and the current maritime traffic facilities and equipment conditions, showing the adaptive navigation law of the ship itself to the environmental conditions [6, 7]. After the encounter ship identification and navigation data extraction of the existing ship navigation data, the course change rate and speed change rate of the ship near the nearest encounter point are calculated through the information of the ship’s longitude and latitude, course and speed. The encounter ships whose course change rate and speed change rate fluctuate near zero are screened. It is considered that they are non-avoidance ships in the whole process of encounter, and their course and speed are basically unchanged. In addition, after in-depth analysis of the course and speed change rate of all encounter ship navigation data, it is concluded that the speed of most ships with a speed of less than 10 sections is basically unchanged in the avoidance process, but the course change is relatively large. Taking one of the avoidance ships as an example, as shown in Fig. 5, the fluctuation range of the course change rate of the ship is basically maintained in the range of [–15, + 15], and the speed change rate fluctuates near zero and close to zero, which indicates that the ship with low speed does not adjust the ship speed frequently in the actual navigation process, but the ship course control is more frequent in the operation process. The steering operation of some ships may be guided by the tug near the port, but in most cases, the ship in the low-speed state is more dependent on steering for ship control, which is not the same as the frequent change of the direction and the acceleration in the road driving.
5 Conclusions
By processing the AIS data of ships in Gulei Port, the distribution of the encounter area, the trajectory distribution and the velocity distribution of the ships are excavated, and the conflict area of ship navigation in reality is obtained. Due to the temporal and spatial uncertainty of ship maneuvering and the adaptability to hydrology and geographical environment in the real navigation state, the ship maneuvering mode does not only consider the maritime navigation rules and the interference of other ships. Therefore, this paper mainly analyzes and calculates the low-speed ships near the port. Through the comparison of data, it is found that the common ship maneuvering behavior mainly depends on a large number of steering movements to complete the avoidance between ships, and the speed change is small. This conclusion is the same as the daily observation results of ship maneuvering near the port in life. At the same time, under certain conditions, the relevant personnel can effectively predict the behavior characteristics of ships near the port and complete their daily port work.
References
Li-lin, W., Jun, L.: Ship behavior recognition method based on multi-scale convolution. J. Comput. Appl. 39(12), 3691–3696 (2019)
Wan Hui, X., Shan-shan, M.-Q.: A behavior analysis of ship characteristics in arctic Northeast Passage. J. Transp. Inf. Saf. 38(02), 89–95 (2020)
Wen, Y.-Q., Zhang, Y.-M., Huang, L., Zhou, C.-H., Xiao, C.-S., Zhang, F.: Mechanism of ship behavior dynamic reasoning based on semantics. Navig. China 42(03), 34–39 (2019)
Jia, L.: Research on Visualization of Inland Waterway Transportation Information Based on Massive AIS Data. Wuhan University Of Technology (2018)
Xiao, X., Qiang, Z., Zhe-peng, S., Xian-biao, J., Jia-cai, P.: Specific ship’s encounter live distribution based on AIS. Navig. China 37(03), 50–53 (2014)
Yang, T., Zhe, M., Ping, S., Bing, W.: A study of regularity of navigation patterns of cargo ships at the waterways near Wuhan Yangtze River Bridge based on ship manoeuvring behavior. J. Transport Inf. Safety 36(01), 49–56 (2018)
Huan-huan, G., Hai-guang, H., Si-ning, J.: Study on the division of fishing vessel behavior based on VMS trajectory data analysis. Chinese Fisheries Econ. 38(02), 119–126 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Open Access This chapter is licensed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
The images or other third party material in this chapter are included in the chapter's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the chapter's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
Copyright information
© 2022 The Author(s)
About this paper
Cite this paper
Zhao, Y., Suo, Y., Xian, B. (2022). Ship Encounter Scenario and Maneuvering Behavior Mining Based on AIS Data. In: Qian, Z., Jabbar, M., Li, X. (eds) Proceeding of 2021 International Conference on Wireless Communications, Networking and Applications. WCNA 2021. Lecture Notes in Electrical Engineering. Springer, Singapore. https://doi.org/10.1007/978-981-19-2456-9_7
Download citation
DOI: https://doi.org/10.1007/978-981-19-2456-9_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-2455-2
Online ISBN: 978-981-19-2456-9
eBook Packages: EngineeringEngineering (R0)