Port ship comprehensive analysis and entry and exit situation prediction method

Abstract

The invention discloses a port ship comprehensive analysis and entry and exit situation prediction method, which comprises the following steps of S1, drawing a port area, and obtaining real-time data and historical data of an AIS (Automatic Identification System) in the port area; s2, preprocessing the data in the S1 to obtain dynamic data and static data of each ship; s3, constructing a visual port model, generating a map containing a port area on a display screen, marking the position of each ship on the map in real time, and generating a corresponding mark; and S4, constructing a ship comprehensive analysis model, selecting a corresponding mark on the map, displaying the corresponding historical track and predicted track on the map, and generating an information table of the corresponding ship. According to the invention, data can be simplified and visually displayed in front of management personnel, the state of each ship is intelligently analyzed, and the working difficulty of the management personnel is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of port ship management, and in particular to a comprehensive analysis and entry / exit situation prediction method for port ships. Background Art

[0002] A port is a transportation hub located along the coasts of seas, rivers, lakes, reservoirs, etc., with water-land intermodal equipment and conditions for safe entry and berthing of ships. A port is a gathering point and hub of water-land transportation, a distribution center for industrial and agricultural products and foreign trade import and export goods, and also a place for ships to berth, load and unload goods, pick up and drop off passengers, and replenish supplies. The existing port management methods are diverse, and most of them obtain information of each ship through the AIS system and satellites. Due to the complex and huge ship data at sea, comprehensive management will overload the management system and consume a huge amount of energy. Therefore, how to perform regional data processing and ship management has become the focus of energy conservation and efficiency improvement, simplifying the data and visually displaying it in front of management personnel, and intelligently analyzing the status of each ship to reduce the work difficulty of management personnel. Summary of the Invention

[0003] The purpose of the present invention is to provide a comprehensive analysis and entry / exit situation prediction method for port ships. To achieve the above purpose, the present invention adopts the following technical solutions:

[0004] A comprehensive analysis and entry / exit situation prediction method for port ships includes the following steps:

[0005] S1. Delimit a port area and obtain real-time data and historical data of the AIS system within the port area;

[0006] S2. Preprocess the data in S1 to obtain dynamic data and static data of each ship;

[0007] S3. Construct a visual port model, generate a map including the port area on a display screen, and based on the dynamic data and static data in S2, mark the positions of each ship on the map in real time and generate corresponding marks, and distinguish the entry / exit status and types of each mark through various colors;

[0008] S4. Construct a comprehensive ship analysis model, generate historical tracks and predicted tracks of each ship according to the dynamic data and static data in S2, and import them into the map including the port area on the display screen. By selecting the corresponding mark on the map, display its corresponding historical track and predicted track on the map, and generate an information table for the corresponding ship.

[0009] Furthermore, the map is provided with a region delimitation module. By selecting a line through the region delimitation module, select a starting point and an ending point on the map to form a closed area, and use this closed area as the port area;

[0010] The area extraction module selects a starting point and an ending point within the port area to form a closed sub - area, and uses this closed sub - area as at least one of a port, a dock, an anchorage, a supervision area, or a berth;

[0011] The area extraction module adds, modifies, and deletes closed areas and closed sub - areas on the map.

[0012] Further, the specific steps of step S1 are as follows:

[0013] Obtain the real - time data and historical data of the AIS system within the port area, obtain the current ship information entering and leaving the port according to the real - time data, and extract the navigation data of the corresponding ship within the port area from the historical data according to the ship information.

[0014] Further, the ship information includes at least one of ship name, MMSI, IMO, call sign, ship type, ship length, ship width, position, speed, course, draft, origin port, and destination port, and the historical data includes the navigation trajectory of the ship within the port area.

[0015] Further, in step S2, the real - time data and historical data of S1 are sequentially cleaned according to the ship information, invalid or incorrect data fields are removed, and they are classified into dynamic data and static data. Among them, the dynamic data includes position, speed, course, and draft, and the static data includes ship name, MMSI, IMO, call sign, ship type, ship length, ship width, origin port, and destination port.

[0016] Further, the specific steps of step S3 are as follows:

[0017] Construct a visual port model, generate a map including the port area on the display screen, and distinguish and display the closed areas and closed sub - areas with different colors according to the lines;

[0018] According to the dynamic data and static data in S2, mark the positions of each ship on the map in real - time and generate corresponding marks. One ship type matches one color, and the in - port and out - port status and types of each mark are distinguished by multiple colors;

[0019] The mark adjusts the orientation of its arrow on the map according to the course of the ship. The position is the longitude and latitude position of the ship, and the entry and exit situation of each ship within the port area is displayed on the map of the display screen.

[0020] Further, the specific steps of step S4 are as follows:

[0021] Construct a ship comprehensive analysis model, generate the historical track and predicted track of each ship according to the dynamic data and static data of S2, and import them into the map including the port area on the display screen;

[0022] By selecting the corresponding markers on the map, the corresponding historical tracks and predicted tracks are displayed on the map. The end point of the predicted track is the destination port, and the historical track and the predicted track are distinguished by two colors;

[0023] Meanwhile, an information table of the ship corresponding to the marker is generated, which contains the static data of the ship;

[0024] According to the static data and the berthing time, the ship berthing points of the target ship to the destination port are extracted. According to the speed and heading of the dynamic data, the sailing route from the current position to the ship berthing points of the destination port is generated to obtain the predicted route.

[0025] Furthermore, the extraction method of the ship berthing points is to select at least one berthing point available for berthing in the destination port within the port area according to the type of the target ship, the destination port and the historical track.

[0026] Furthermore, the ship comprehensive analysis model is provided with a long short-term memory neural network and a temporal convolutional network. Combining the position, speed, historical track, destination port and berthing point of the ship, the long short-term memory neural network extracts the long-term dependencies in the sailing track of the ship, and the temporal convolutional network performs feature extraction through its receptive field and the long-time dependence information of the track sequence. The predicted track is generated according to the long-term dependencies and the long-time dependence information.

[0027] After adopting the above technical solutions, compared with the background technology, the present invention has the following advantages:

[0028] The present invention integrates, processes and analyzes the basic information, position and track data of the ships entering and leaving the port, uses advanced prediction algorithms to predict the next port and sailing track of the ships, and dynamically presents the entry and exit situation of the port ships at the same time, providing strong support for port management and maritime traffic safety, simplifying the data and visually displaying it in front of the management personnel, intelligently analyzing the status of each ship, and reducing the work difficulty of the management personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0030] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0031] It should be noted that in the present invention, the terms "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are all based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the devices or elements of the present invention must have a specific orientation. Therefore, it should not be construed as a limitation to the present invention.

[0032] Embodiment

[0033] Reference Figure 1 As shown, the present invention discloses a comprehensive analysis method for port ships and a prediction method for entering and leaving trends, including the following steps:

[0034] S1. Delimit the port area and obtain the real-time data and historical data of the AIS system within the port area.

[0035] S2. Preprocess the data in S1 to obtain the dynamic data and static data of each ship. An AIS field cleaning component is provided and divided into an AIS dynamic data cleaning component and an AIS static data cleaning component, which are used to process dynamic data and static data respectively.

[0036] AIS dynamic data cleaning component: mainly responsible for cleaning the real-time dynamic message fields. Dynamic messages refer to the dynamic data sent by AIS devices in real time, including information such as the position, course, and speed of ships. The main purpose of this cleaning component is to remove outliers, fill in missing values, correct error values, etc., to ensure the accuracy and integrity of the data. For example, if the speed of a certain ship suddenly appears abnormal, this component will identify and correct it.

[0037] AIS static data cleaning component: mainly responsible for cleaning the static message fields. Static messages refer to the basic information of AIS devices, including information such as ship name, ship length, ship width, and ship depth. The main purpose of this cleaning component is to check and correct the consistency of the data, such as whether the ship name is unique and whether the ship length is within a reasonable range.

[0038] S3. Build a visual port model, generate a map including the port area on the display screen, and mark the positions of each ship on the map in real time according to the dynamic data and static data in S2, and generate corresponding marks, and distinguish the entering and leaving port status and types of each mark through multiple colors.

[0039] S4. Build a comprehensive ship analysis model, generate the historical track and predicted track of each ship according to the dynamic data and static data in S2, and import them into the map including the port area on the display screen. By selecting the corresponding mark on the map, display its corresponding historical track and predicted track on the map, and generate an information table for the corresponding ship.

[0040] The map is provided with a region extraction module. By using the region extraction module to select lines, a starting point and an ending point are selected on the map to form a closed region, and this closed region is used as the port area.

[0041] By using the region extraction module to select a starting point and an ending point within the port area to form a closed sub-region, this closed sub-region is used as at least one of a port, a wharf, an anchorage, a supervision area, or a berth.

[0042] By using the region extraction module, closed regions and closed sub-regions are added, modified, and deleted on the map.

[0043] The specific steps of step S1 are as follows:

[0044] Obtain the real-time data and historical data of the AIS system within the port area, obtain the current ship information entering and leaving the port according to the real-time data, and extract the navigation data of the corresponding ship within the port area from the historical data according to the ship information.

[0045] The ship information includes at least one of ship name, MMSI, IMO, call sign, ship type, ship length, ship width, position, speed, course, draft, origin port, and destination port. The historical data includes the navigation trajectory of the ship within the port area.

[0046] The position in this embodiment is the longitude and latitude data corresponding to the ship, which is obtained through the AIS system or can also be obtained through GPS.

[0047] In step S2, the real-time data and historical data of S1 are sequentially cleaned according to the ship information, invalid or incorrect data fields are removed, and they are classified into dynamic data and static data. Among them, the dynamic data includes position, speed, course, and draft, and the static data includes ship name, MMSI, IMO, call sign, ship type, ship length, ship width, origin port, and destination port.

[0048] The specific steps of step S3 are as follows:

[0049] Construct a visual port model, generate a map including the port area on the display screen, and distinguish and display the closed regions and closed sub-regions by different colors according to the lines.

[0050] According to the dynamic data and static data in S2, the positions of each ship are marked in real time on the map, and corresponding marks are generated. One ship type is matched with one color, and the inbound and outbound status and type of each mark are distinguished by multiple colors.

[0051] The mark adjusts the orientation of its arrow on the map according to the course of the ship. The position is the longitude and latitude position of the ship, and the inbound and outbound trends of each ship within the port area are displayed on the map of the display screen.

[0052] The specific steps of step S4 are as follows.

[0053] Construct a comprehensive ship analysis model. Based on the dynamic data and static data in S2, generate the historical tracks and predicted tracks of each ship, and import them into the map containing the port area on the display screen.

[0054] By selecting the corresponding markers on the map, display their corresponding historical tracks and predicted tracks. The end point of the predicted track is the destination port, and the historical track and the predicted track are distinguished by two colors.

[0055] Meanwhile, generate an information table of the ship corresponding to the marker, which includes the static data of the ship.

[0056] Extract the ship berthing points of the target ship to the destination port according to the static data and the berthing time. Generate the navigation route from the current position to the ship berthing points of the destination port according to the ship speed and heading of the dynamic data, and obtain the predicted route.

[0057] The extraction method of the ship berthing points is to select at least one berthing point available for berthing in the destination port within the port area according to the type of the target ship, the destination port and the historical track.

[0058] The ship berthing point extraction function allows users to select ship tracks from AIS data and extract berthing point information according to the set segmentation method. These information include attributes such as ship identification number, IMO number, ship length, ship type, berthing point type and berthing timestamp. This function supports exporting data in the format of shapefiles (including spatial reference information) and csv (general tabular data format) for data processing and analysis in other applications. By using the ship berthing point function, users can better understand the static characteristics and dynamic behaviors of ships, thus improving the efficiency and accuracy of shipping management.

[0059] The comprehensive ship analysis model is equipped with a long short-term memory neural network and a temporal convolutional network. Combining the position, speed, historical track, destination port and berthing point of the ship, the long short-term memory neural network extracts the long-term dependencies in the ship's navigation track, and the temporal convolutional network extracts features through its receptive field and the long-time dependence information of the track sequence. The predicted track is generated according to the long-term dependencies and the long-time dependence information.

[0060] The AIS system collects a large amount of AIS data. Therefore, it is necessary to parse the AIS data. The AIS data parsing function comprehensively parses the content of the AIS data message and converts it into plaintext data that is highly readable and easy to analyze. The implementation of this function is based on the international standard of the International Telecommunication Union (ITU) regarding the AIS data exchange protocol, ensuring the standardization and compatibility of the data. The AIS data parsing function covers the entire process of processing, parsing, and converting AIS raw data. First, the message content is extracted from the received AIS raw data, and then, according to the parsing rules of the international standard, the message is parsed and translated field by field. During the parsing process, the AIS data parsing function will correctly parse each field in the message based on information such as the start character, length, and data type of the message. These fields include but are not limited to the static information of the ship (such as ship name, ship type, call sign, etc.) and dynamic information (such as position, course, speed, etc.). The parsed plaintext data is presented in a highly readable and structured format, facilitating subsequent data analysis and processing. Users can intuitively view and analyze various information of the ship, providing strong support for applications such as shipping management, navigation safety assessment, and ship behavior analysis.

[0061] In this embodiment, by integrating, processing, and analyzing the basic information, position, and trajectory data of inbound and outbound ships, advanced prediction algorithms are used to predict the next port and navigation trajectory of the ships. At the same time, the entry and exit situation of ships in the port is dynamically presented, providing strong support for port management and maritime traffic safety. The data is simplified and visually displayed in front of the management personnel, and the status of each ship is intelligently analyzed, reducing the work difficulty of the management personnel.

[0062] As described above, only the preferred specific embodiments of the present invention are provided, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for comprehensive analysis and prediction of port ship entry and exit situations, characterized in that: The following steps are involved: S1. Draw a port area and obtain the real-time data and historical data of the AIS system in the port area; S2, preprocessing the data of S1 to obtain dynamic data and static data of each ship; S3, construct a visual port model, generate a map containing the port area on the display screen, mark the position of each ship on the map in real time according to the dynamic data and static data in S2, and generate corresponding marks, and distinguish the entry and exit status and type of each mark by multiple colors; S4. Construct a comprehensive ship analysis model, generate the historical track and predicted track of each ship based on the dynamic data and static data of S2, and import the map containing the port area on the display screen. By selecting the corresponding mark on the map, the corresponding historical track and predicted track are displayed on the map, and an information table of the corresponding ship is generated.

2. A method for comprehensive analysis and entry and exit situation prediction of port ships as claimed in claim 1, characterized in that: The map is provided with an area drawing module, through which a line is selected, a starting point and an end point are selected on the map to form a closed area, and the closed area is used as the port area; The area selection module selects a starting point and an end point in the port area to form a closed sub-area, and the closed sub-area is used as at least one of a port, a wharf, an anchorage, a supervision area or a berth; Add, modify and delete closed areas and closed sub-areas on the map through the area extraction module.

3. A method for comprehensive analysis and entry and exit situation prediction of port ships as claimed in claim 2, characterized in that: The specific steps of step S1 are: Acquire the real-time and historical data of the AIS system in the port area, obtain the current information of ships entering and leaving the port based on the real-time data, and extract the navigation data of the corresponding ship in the port area from the historical data based on the ship information.

4. A method for comprehensive analysis and entry and exit situation prediction of port ships as claimed in claim 3, characterized in that: The ship information includes at least one of the ship name, MMSI, IMO, call sign, ship type, length, width, position, speed, heading, draft, departure port and destination port, and the historical data includes the navigation track of the ship in the port area.

5. A method for comprehensive analysis and entry and exit situation prediction of port ships as claimed in claim 4, characterized in that: The step S2 cleans the real-time data and historical data of S1 in sequence according to the ship information, removes invalid or erroneous data fields, and classifies them into dynamic data and static data, wherein the dynamic data includes position, speed, heading and draft, and the static data includes ship name, MMSI, IMO, call sign, ship type, length, ship width, departure port and destination port.

6. A method for comprehensive analysis and entry and exit situation prediction of port ships as claimed in claim 5, characterized in that: The specific steps of step S3 are: Construct a visual port model, generate a map of the port area on the display screen, and distinguish the closed area and closed sub-area by different colors according to the lines; According to the dynamic data and static data in S2, the position of each ship is marked on the map in real time, and corresponding marks are generated. One ship type matches one color, and multiple colors are used to distinguish the entry and exit status and type of each mark; The marker adjusts the direction of its arrow on the map according to the ship's heading, and the position is the latitude and longitude of the ship, showing the entry and exit status of each ship in the port area on the map on the display screen.

7. A method for comprehensive analysis and entry and exit situation prediction of port ships as claimed in claim 6, characterized in that: The specific steps of step S4 are: Build a comprehensive ship analysis model, generate the historical and predicted tracks of each ship based on the dynamic and static data of S2, and import them into the map of the port area on the display screen; By selecting the corresponding mark on the map, the corresponding historical track and predicted track are displayed on the map. The predicted track end point is the destination port. The historical track and predicted track are distinguished by two colors. At the same time, an information table of the corresponding marked ship is generated, which contains the static data of the ship; The ship berthing point from the target ship to the destination port is extracted according to the static data and the berthing time. According to the speed and heading of the dynamic data, the navigation route from the current position to the ship berthing point of the destination port is generated to obtain the predicted route.

8. A method for comprehensive analysis and entry and exit situation prediction of port ships as claimed in claim 7, characterized in that: The method for extracting the ship berthing point is to select at least one berthing point available for the target ship to berth in the destination port within the port area according to the type of the target ship, the destination port and the historical track.

9. A method for comprehensive analysis and entry and exit situation prediction of port ships as claimed in claim 7, characterized in that: The ship comprehensive analysis model is equipped with a long short-term memory neural network and a temporal convolutional network. The long short-term memory neural network is used to extract the long-term dependency in the ship's navigation trajectory by combining the ship's position, speed, historical track, destination port and berthing point. The temporal convolutional network extracts features and the long-term dependency information of the trajectory sequence through its receptive field, and generates a predicted track based on the long-term dependency and the long-term dependency information.

Images