System for creating sea route for ship and operating method thereof

Abstract

A system for creating a sea route for a ship according to one embodiment disclosed in the present document comprises: a database for storing a sea route network of a ship; and a sea route creation unit for creating an initial route connecting a starting point and a destination point of the ship in the sea route network, wherein the sea route generation unit generates the initial route by approximating a fuel consumption amount and a speed of the ship so that a cost function related to at least one of the fuel consumption amount and the speed of the ship is minimized.

Description

Ship route generation system and its operation method

[0001] Cross-citation with related applications

[0002] This invention claims the benefit of priority from Korean Patent Application No. 10-2024-0050244, filed on April 15, 2024, and all contents of the document in that Korean Patent Application are incorporated herein by reference.

[0003] Technology field

[0004] The embodiments disclosed in this document relate to a ship route generation system and its operating method.

[0005] Because ships travel at sea, there are many variables to consider when finding the optimal route, compared to other modes of transportation on land. The process of exploring and determining a ship's route is closely related to the optimization problem of finding the optimal route by considering various variables.

[0006] In particular, utilizing AIS (Automatic Identification System) data during vessel route creation allows for route generation based on the vessel's actual travel path, enabling safer navigation. However, the sheer volume of vessel location data collected through AIS technology complicates real-time optimal route finding. Furthermore, finding optimal routes requires considering not only the distance between the vessel's departure and arrival points, but also weather conditions, tidal currents, and other factors.

[0007] One purpose of the embodiments disclosed in this document is to provide a ship route generation system and its operating method that generates a valid route network based on ship location data acquired through AIS data.

[0008] The technical problems of the embodiments disclosed in this document are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which the present invention pertains from the description below.

[0009] A ship route generation system according to an embodiment disclosed in this document includes a database storing a ship route network; and a route generation unit generating an initial route connecting a departure point and a destination point of the ship among the route network; wherein the route generation unit can generate the initial route by approximating the fuel consumption and the speed of the ship so that a cost function related to at least one of the fuel consumption and the speed of the ship is minimized.

[0010] According to one embodiment, the route generation unit may generate the initial route so that an objective function related to the sum of fuel consumption consumed when the ship moves through the initial route is minimized, and a constraint related to the sum of the time required when the ship moves through the initial route is satisfied.

[0011] According to one embodiment, the objective function may correspond to the sum of the product of the fuel consumption per unit distance consumed when moving each edge of the initial route and the length of each edge, and the constraint may correspond to a condition that the sum of the values ​​obtained by dividing the length of each edge by the speed per unit distance when the ship moves is less than the total sum of the required time for the ship.

[0012] According to one embodiment, the route generation unit may polynomially approximate a product of the fuel consumption per unit distance of each edge and the length of each edge, and a value obtained by dividing the length of each edge by the speed per unit distance at which the ship moves.

[0013] According to one embodiment, the route generation unit can input the initial route into a genetic algorithm to generate a route along which the ship will travel.

[0014] In one embodiment, the route network may be generated based on location data associated with the identified location of the vessel, which is identified based on AIS data of the vessel.

[0015] According to one embodiment, the ship route generation system may further include a data processing unit that preprocesses raw data-type location data related to the location of the ship identified at preset intervals based on the AIS location data to identify a plurality of characteristic points related to the density of the ship.

[0016] According to one embodiment, the data processing unit may preprocess the location data using at least one algorithm that identifies a feature point representing the location of the ship among the location data in the raw data form.

[0017] According to one embodiment, the data processing unit can identify the feature points using the Douglas Pecker algorithm.

[0018] According to one embodiment, the data processing unit may divide a two-dimensional space in which the position data in the raw data form is depicted into a plurality of spaces, and may repeat the operation of dividing the plurality of spaces until the number of the position data included in each of the divided spaces reaches a threshold value.

[0019] According to one embodiment, the data processing unit can identify a feature point corresponding to an average value of a plurality of location data included in each of the divided areas or a feature point closest to the feature point corresponding to the average value.

[0020] According to one embodiment, the route network may correspond to each side of a plurality of triangles generated as a result of dividing a plurality of feature points related to the density of the ships among the location data using the Delaunay triangulation method.

[0021] According to one embodiment, the route generation unit can generate a plurality of routes that satisfy the values ​​of the objective function and the constraints by changing the plurality of feature points.

[0022] According to one embodiment, the route generation unit may generate the initial route using a shortest distance algorithm that searches for the shortest distance connecting each of the feature points adjacent to the departure point and destination point of the ship among the plurality of feature points.

[0023] According to one embodiment, the shortest distance algorithm may include Dijkstra Algorithm or A* Algorithm.

[0024] According to an embodiment of the ship route generation system disclosed in this document, a valid route network can be generated based on the AIS data of a ship.

[0025] The effects according to the embodiments disclosed in this document are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art according to the disclosure of this document.

[0026] FIG. 1 is a drawing schematically illustrating a ship route generation system according to one embodiment disclosed in this document.

[0027] FIG. 2 is a diagram for explaining AIS data according to an embodiment disclosed in this document.

[0028] FIG. 3a is a diagram for explaining a preprocessing process of AIS data according to an embodiment disclosed in this document.

[0029] FIG. 3b is a diagram for explaining a preprocessing process of AIS data according to another embodiment disclosed in this document.

[0030] FIG. 4 is a diagram illustrating a process of verifying a group of route candidates and generating a valid route network according to one embodiment disclosed in this document.

[0031] FIG. 5 is a drawing for exemplarily explaining a route of a ship generated according to one embodiment disclosed in this document.

[0032] FIG. 6 is a diagram illustrating a process for generating an optimal route according to an embodiment disclosed in this document.

[0033] Figure 7 is a flowchart for explaining the operation of a ship route generation system according to an embodiment disclosed in this document.

[0034] Hereinafter, embodiments disclosed in this document will be described in detail with reference to exemplary drawings. When designating components in each drawing, it should be noted that, where possible, identical components are given identical reference numerals, even if they appear in different drawings. Furthermore, when describing embodiments disclosed in this document, detailed descriptions of related known structures or functions will be omitted if they are deemed to hinder understanding of the embodiments disclosed in this document.

[0035] In describing the components of the embodiments disclosed in this document, terms such as first, second, A, B, (a), (b), etc. may be used. These terms are only intended to distinguish the components from other components and do not limit the nature, order, or sequence of the components. In addition, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiments disclosed in this document belong. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning they have in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this application.

[0036] FIG. 1 is a drawing schematically illustrating a ship route generation system according to one embodiment disclosed in this document.

[0037] Referring to FIG. 1, the ship route generation system (100) may include a data acquisition unit (110), a data processing unit (120), a route generation unit (130), and a database (140).

[0038] A ship route generation system (100) may be configured to generate a route and / or route network for a ship (10) to move. The ship route generation system (100) may generate a route for a ship (10) to move in real time and / or generate a route for a ship (10) using a previously stored route network and provide the route to the ship (10).

[0039] The data acquisition unit (110) may be configured to receive various data provided by the ship (10). The data acquisition unit (110) may be configured to wirelessly communicate with the ship (10) in two directions to receive data provided by the ship (10) and / or provide data to the ship (10). To this end, the data acquisition unit (110) may include various communication interfaces or communication modules, etc., not shown in FIG. 1.

[0040] According to one embodiment, the data acquisition unit (110) may be configured to acquire AIS data provided by the vessel (10). Here, the AIS data may refer to all data acquired from an Automatic Identification System (AIS) mounted on the vessel (10), and may include, for example, location data including latitude and longitude of the vessel (10), data related to the speed of the vessel, etc., but is not limited thereto. The vessel automatic identification device may refer to any device installed on the vessel (10) to automatically track the vessel and transmit and receive data with the outside world via a transceiver. The vessel automatic identification device may be used in vessel traffic services, etc.

[0041] According to one embodiment, the data acquisition unit (110) may acquire AIS data from the vessel (10) at preset intervals. For example, if the AIS data includes location data of the vessel (10), the data acquisition unit (110) may acquire location data related to the location of the vessel (10) at preset intervals. As described above, the location data may include, but is not limited to, data related to the current latitude and longitude of the vessel (10).

[0042] The data processing unit (120) may be configured to calculate and / or process data acquired by the data acquisition unit (110) and / or various data generated during the operation of the ship route generation system (100).

[0043] According to one embodiment, the data processing unit (120) can preprocess the data of the ship (10) acquired by the data acquisition unit (110). Specifically, the data processing unit (120) can preprocess AIS data in the form of raw data and perform processes such as data calculation / processing.

[0044] If the location of the identified vessel (10) is displayed on a map at preset intervals, the locations of the vessels (10) will be depicted very densely on the map. In addition, if AIS data of all vessels moving at sea must be processed in addition to the location of the vessel (10) illustrated in FIG. 1, a massive amount of data will be depicted on the map. Referring to FIG. 2, a diagram is shown indicating the identified locations of all vessels sailing at sea at preset intervals. Each point illustrated in FIG. 2 may correspond to the actual location of the vessel identified at preset intervals. The location of the vessel may be identified based on, but is not limited to, vessel location data related to the latitude and longitude of the vessel collected through the AIS device mounted on each vessel.

[0045] Since each point depicted in Figure 2 corresponds to the location of an actually identified vessel, a straight line connecting the locations of the identified vessels can correspond to the actual vessel's route. Furthermore, areas with a high density of identified vessel locations can correspond to major routes frequently traveled by vessels. In other words, by connecting each point depicted in Figure 2, a route along which an actual vessel is moving and / or can move can be created.

[0046] However, as illustrated in Figure 2, the volume of vessel-identified location data is excessively large, and the routes these vessels navigate tend to be concentrated in specific areas. Generating vessel routes by considering all of the identified vessel location data can be inefficient. Therefore, preprocessing the vessel-identified location data is necessary to identify features that indicate vessel location or density, and then create a vessel route network based on these features.

[0047] According to one embodiment described with reference to FIG. 1 again, the data processing unit (120) can preprocess AIS data in raw data form using various algorithms. For example, the data processing unit (120) can preprocess AIS data using at least one of the Douglas Pecker algorithm or the Quad Tree algorithm for polygon approximation, but is not limited thereto.

[0048] Here, the Douglas Packer algorithm is an algorithm that simplifies data, and may be an algorithm that removes unnecessary data by approximating the boundaries of existing data with polygons that sufficiently resemble them, and the quad tree algorithm may be an algorithm that recursively divides a two-dimensional space to create a tree-shaped data structure.

[0049] That is, the data processing unit (120) may be configured to preprocess the ship's location data illustrated in FIG. 2 using at least one of the Douglas Packer algorithm and the quad tree algorithm to identify a plurality of feature points related to the ship's location and density.

[0050] The route generation unit (130) can generate a route network of a vessel (10) based on preprocessed AIS data. Specifically, the route generation unit (130) can generate a route network based on a plurality of feature points related to the location and density of the vessel (10) identified by the data processing unit (120). Here, the route network can correspond to an effective route along which the vessel (10) can travel.

[0051] According to one embodiment, the route generation unit (130) may generate a plurality of edges related to the movement path of the vessel (10) based on a plurality of feature points. Here, the edges may correspond to line segments connecting each of the plurality of feature points, and may correspond to a group of route candidates for the actual movement of the vessel (10).

[0052] According to one embodiment, the route generation unit (130) may divide the plurality of feature points identified by the data processing unit (120) using the Delaunay triangulation method. Here, the Delaunay triangulation may be a method of dividing space by creating continuous triangles based on the plurality of feature points on a plane, but dividing the space such that no point other than the vertices of the triangles is included within the circumcircle of each triangle. In this case, the created triangles may be close to the shape of equilateral triangles. Here, each of the plurality of edges may correspond to each side of the triangles created through the Delaunay triangulation method.

[0053] When segmenting multiple feature points depicted on a map using the Delaunay triangulation method, both valid and invalid edges may be generated. Here, whether an edge is valid may be related to, but is not limited to, whether a ship (10) can actually travel along the route depicted as the edge. For example, if an edge created on the map is created to cross land, the ship (10) cannot travel along the route depicted as the edge crossing land, and thus the edge may be identified as an invalid edge. However, this is merely exemplary, and the criteria for a valid edge may be set and changed in various ways.

[0054] The route generation unit (130) may be configured to verify a group of route candidates and generate a valid route network. The route generation unit (130) may verify each of a plurality of edges generated through Delaunay triangulation based on a plurality of feature points to generate a valid route network. For example, the route generation unit (130) may perform a verification operation to identify, based on the above-described criteria, an edge crossing land among a plurality of edges depicted on a map as an invalid edge, and to identify, based on the above-described criteria, an edge depicted on the sea among a plurality of edges depicted on the map as a valid edge.

[0055] According to one embodiment, the route generation unit (130) can verify valid edges using pre-stored water depth data. Here, the pre-stored water depth data may include, but is not limited to, data related to a map showing the water depth of a sea or lake, such as a bathymetric map data. The route generation unit (130) can verify edges depicted in the sea as valid edges using the water depth data, and delete invalid edges from among a plurality of edges depicted on the map to create a route network.

[0056] The route generation unit (130) can generate a route along which the ship (10) will actually travel based on the generated route network.

[0057] According to one embodiment, the route generation unit (130) may generate a route of the vessel (10) based on the location data of the departure point from which the vessel (10) departs and the destination point of the vessel (10). Specifically, the route generation unit (130) may identify at least one of the feature point closest to the departure point of the vessel (10) and the feature point closest to the destination point of the vessel (10) among the plurality of feature points identified by the data processing unit (120).

[0058] According to one embodiment, the route generation unit (130) may generate a route of the vessel (10) based on a plurality of edges connecting the departure point of the vessel (10) and the most adjacent feature point and the destination point and the most adjacent feature point. That is, the route generation unit (130) may identify a plurality of edges connecting the departure point of the vessel (10) and the most adjacent feature point and the destination point and the most adjacent feature point among the generated route networks, and may generate a route of the vessel (10) by connecting each of the plurality of edges to each other. Here, the route generation unit (130) may generate a route such that the distance between the departure point and the destination point of the vessel (10) is the shortest distance, but is not limited thereto. The route generation unit (130) may generate a route of the vessel (10) by taking into account not only the distance between the departure point and the destination point but also various other variables.

[0059] According to one embodiment, the route generation unit (130) may generate a route of the ship (10) based on various internal algorithms. For example, the route generation unit (130) may generate a route of the ship (10) based on an optimization algorithm such as Dijkstra's Algorithm or A* Algorithm, but is not limited thereto. Here, the Dijkstra's Algorithm may be an algorithm that finds all paths that minimize a cost function between one vertex and all other vertices, and the A* Algorithm may be an algorithm that finds a path that minimizes a cost function between one vertex and a target vertex. Here, the cost function may be set so that various variables are applied. For example, if the cost function is set to distance, the route generated through Dijkstra's algorithm and / or A-star algorithm may correspond to the route with the shortest distance, and if the cost function is set to fuel oil consumption (FOC), the route generated through Dijkstra's algorithm and / or A-star algorithm may correspond to the route that minimizes fuel consumption. However, this is merely an example, and the cost function may reflect various variables in addition to the examples described above.

[0060] Data related to these routes can be stored in a database (140).

[0061] The database (140) may be configured to store various data for the operation of the ship route generation system (100). According to one embodiment, the database (140) may be configured to store not only system data for the operation of the ship route generation system (100), but also data related to various algorithms, AIS data, generated route networks, etc., but is not limited to these examples.

[0062] According to one embodiment, the data processing unit (120) and the route generation unit (130) may be implemented as a single processor or as separate processors. Here, the processor may execute software to control at least one other component (e.g., hardware or software) of the ship route generation system (100), or perform operations such as processing and / or calculating various data.

[0063] According to one embodiment, the ship route generation system (100) may be implemented through a control server, etc. that communicates with the ship (10) and controls the passage of the ship (10), etc. In this case, the ship route generation system (100) may provide the user terminal with data related to the generated route network and the route for the ship (10) to move. For example, the ship route generation system (100) may display the generated route network and / or the route of the ship (10) generated based on the route network on a map UI (User Interface) and provide it to the user terminal, but is not limited thereto.

[0064] The ship route generation system (100) can generate an optimal route for the ship (10) to move based on the generated route network. The ship route generation system (100) can generate an optimal route that takes various variables into account by using the initial route identified based on the route network as the initial route. For example, the ship route generation system (100) can consider the fuel consumption of the ship (10), which is a dependent variable depending on weather conditions, assuming that the ship (10) moves along the initial route. As another example, the ship route generation system (100) can consider the minimum time required for the ship (10) to reach the destination (Required Time Arrival; RTA).

[0065] In such cases, a route that minimizes fuel consumption and allows the vessel to reach the destination within the required minimum time may correspond to an optimal route. In addition to the examples described above, the ship route generation system (100) may search for and / or generate an optimal route using various optimization algorithms.

[0066] According to one embodiment, the route generation unit (130) may be configured to generate an optimal route using a genetic algorithm. Here, the genetic algorithm is a global optimization technique based on the evolutionary process of genetics, and may be a search algorithm that finds a solution that optimizes a specific objective function.

[0067] Specifically, a genetic algorithm may involve a process of computing the fitness of a solution expressed in the form of a gene. A genetic algorithm may be an algorithm that searches for optimal fitness by varying the solution expressed in the form of a gene through operations such as selection, crossover, mutation, and replacement.

[0068] According to one embodiment, the route generation unit (130) may generate an initial route based on a route network. Here, the initial route may correspond to a route generated through the Dijkstra algorithm or the A-Star algorithm described above, but is not limited to these examples, and initial routes generated by various methods may all be input into the genetic algorithm.

[0069] The route generation unit (130) can set multiple feature points included in the initial route as mutation targets. That is, the route generation unit (130) can search for an optimal route by varying multiple feature points included in the initial route.

[0070] FIG. 3a and FIG. 3b are diagrams for explaining a preprocessing process of AIS data according to an embodiment disclosed in this document.

[0071] As described above in the description of FIG. 1, the ship route generation system (100, see FIG. 1) may be configured to preprocess raw data type AIS data acquired from the ship (10, see FIG. 1). According to one embodiment, the ship route generation system (100) may preprocess raw data type AIS data using at least one of the Douglas Pecker algorithm and the Quad Tree algorithm.

[0072] First, referring to Fig. 3a, the process of preprocessing AIS data using the Douglas Pecker algorithm is illustrated. The solid lines (1) displayed on the sea in the map (a) shown on the left may be a set of points indicating the identified locations of actual ships (10) on the map.

[0073] Since the position of the vessel (10) is transmitted to the vessel route generation system (100) at preset intervals through the AIS device mounted on the vessel (10), it is inefficient to generate a route by considering all the position data of the vessel (10) indicated on the map (a) shown on the left. Accordingly, the vessel route generation system (100) can identify feature points related to the position and density of the vessel (10) among the raw data type AIS data. For convenience of explanation, it is assumed that the vessel (10) moved along the real route generated from a point approximately 105 degrees east longitude on the equator to a point approximately 120 degrees east longitude on 38 degrees north latitude on the map (a) shown on the left.

[0074] First, there may be cases where the location of the vessel (10) is incorrectly identified for various reasons. Since the vessel (10) moved along the solid line route (1), the vessel (10) would not have been identified at the locations of multiple solid lines (2) extending in the direction of 140 degrees east longitude from the point of 120 degrees east longitude near 30 degrees north latitude on the map (a) shown on the left. The vessel route generation system (100) can delete the data (2) related to the location of the vessel (10) that has been abnormally identified as described above, and extract only the location data (1) related to the location where the vessel (10) was actually identified. It can be confirmed that the data (2) indicating the location where the vessel (10) was abnormally identified has been deleted on the map (b) shown on the right.

[0075] According to one embodiment, the vessel route generation system (100) may preprocess raw AIS data using the Douglas Pecker algorithm. As described above in the description of FIG. 1, the Douglas Pecker algorithm is an algorithm that simplifies data and may be an algorithm that removes unnecessary data by approximating the boundaries of existing data with polygons that sufficiently resemble them.

[0076] That is, the ship route generation system (100) can identify a plurality of points (3a to 3i) indicated on the map (b) shown on the right using the Douglas Packer algorithm. Here, the plurality of points (3a to 3i) identified and indicated on the map (b) shown on the right may correspond to feature points for indicating the route (3) along which the ship (10) actually moved. Since the ship route generation system (100) can generate the ship route network based only on the plurality of feature points (3a to 3i) indicated on the map (b) shown on the right, the amount of data to be processed is reduced, enabling faster route network and route generation.

[0077] Referring to Fig. 3b, a process of preprocessing AIS data using a Quad Tree algorithm is illustrated. Each point shown in Fig. 3b may correspond to an identified location of an actual vessel (10) on the map.

[0078] Here, the quad tree algorithm may be an algorithm that recursively divides a two-dimensional space to create a tree-shaped data structure. The ship route generation system (100) can hierarchically divide a two-dimensional space, i.e., the map illustrated in FIG. 3b, to create a data structure that expresses the density of the locations where ships (10) are actually identified.

[0079] According to one embodiment, the ship route generation system (100) can divide a two-dimensional map into multiple spaces using a quad tree algorithm. The ship route generation system (100) can compare the number of points included in each of the multiple divided spaces, i.e., the number of points indicating the location of a vessel identified on the map, with a preset reference value. Here, the reference value is not limited to a specific value and can be variously set and changed by design.

[0080] According to one embodiment, the ship route generation system (100) may further divide the space into multiple spaces if the number of points indicating the location of an identified ship in each of the divided spaces is greater than a preset reference value. The ship route generation system (100) may further divide the two-dimensional map until the number of points indicating the location of a ship included in the divided spaces reaches the preset reference value.

[0081] For example, the ship route generation system (100) can apply a Quad Tree algorithm to a two-dimensional map showing AIS data in the form of raw data as shown in Fig. 2. In this case, the ship route generation system (100) can divide the two-dimensional map shown in Fig. 2 into a plurality of spaces (e.g., four), and this process can be performed until the number of points indicating the ship's location reaches a preset reference value.

[0082] As another example, the ship route generation system (100) may apply a Quad Tree algorithm to a two-dimensional map (b) in which raw data type AIS data is preprocessed by applying the Douglas Packer algorithm as illustrated in FIG. 3A. In this case, the ship route generation system (100) may divide the two-dimensional map (b) illustrated in FIG. 3A into a plurality of spaces (e.g., four), and this process may be performed until the number of points indicating the ship's location reaches a preset reference value.

[0083] Referring back to FIG. 3b, a two-dimensional map in which the AIS data in the form of raw data is depicted by applying the quad tree algorithm or a two-dimensional map in which the AIS data in the form of raw data is preprocessed by applying the Douglas-Packer algorithm is divided into a plurality of spaces. According to one embodiment, each of the rectangular areas illustrated in FIG. 3b corresponds to each of the divided spaces, and points illustrated within each of the rectangular areas may correspond to the location of an identified vessel. According to one embodiment, the vessel route generation system (100) may be configured to identify a feature point among points indicating the location of an identified vessel included in each of the plurality of divided spaces. Here, the feature point may be at least one point related to the location and density of the identified vessel in each of the plurality of sections, and may be determined based on, for example, an average value or a median value between location data related to the location of each vessel, but is not limited thereto.

[0084] In one embodiment, the distance between feature points within each of the identified rectangular areas may be related to the density of vessels. A smaller size of a defined rectangular area indicates that the area contains a large number of points indicating the locations of identified vessels, which may correspond to a higher density of identified vessels within that area on the map. Specifically, the size of each rectangular area and the distance between feature points may be inversely proportional to the density.

[0085] FIG. 4 is a diagram illustrating a process of verifying a group of route candidates and generating a valid route network according to one embodiment disclosed in this document.

[0086] As described above in the description of FIG. 1, the ship route generation system (100, see FIG. 1) can generate a route network of a ship (10, see FIG. 1) based on preprocessed AIS data. Here, the route network can correspond to an effective route along which the ship (10) can travel.

[0087] According to one embodiment, the ship route generation system (100) may generate a ship route network based on a plurality of identified feature points. The ship route generation system (100) may generate a plurality of edges connecting the plurality of feature points by dividing the plurality of identified feature points using the Delaunay triangulation method, but is not limited thereto.

[0088] First, referring to the map (a) illustrated in Fig. 4, a plurality of triangles are depicted connecting a plurality of feature points identified on the map (a). Each side of the plurality of triangles created may correspond to an edge created by the ship route creation system (100).

[0089] Here, each of the multiple edges may correspond to a candidate route along which the vessel can travel. According to one embodiment, the vessel route generation system (100) mechanically connects each of the multiple feature points through Delaunay triangulation, thus requiring the identification of a valid route on which the vessel can actually navigate among the multiple edges included in the candidate route.

[0090] The ship route generation system (100) may be configured to verify valid edges among a plurality of edges included in the generated route candidate set. Here, whether an edge is valid may relate to, but is not limited to, whether a vessel can actually navigate along the route indicated by the edge. For example, if an edge generated on the map (a) is generated to cross land, the vessel (10) cannot navigate along the route indicated by the edge crossing land, and thus the edge may be identified as an invalid edge. However, this is merely exemplary, and the criteria for a valid edge may be set and modified in various ways.

[0091] According to one embodiment, the ship route generation system (100) can verify a valid edge among a plurality of edges based on previously stored water depth data. Here, the previously stored water depth data may include, but is not limited to, data related to a map indicating the water depth of a sea or lake, such as a bathymetric map data. The ship route generation system (100) can verify edges depicted in the sea as valid edges using the water depth data, and delete invalid edges among the plurality of edges depicted on the map to create a route network.

[0092] According to one embodiment, the ship route generation system (100) can use water depth data to identify edges crossing land as invalid edges and edges depicted at sea as valid edges. The ship route generation system (100) can delete edges crossing land among the multiple edges depicted in the map (a) shown above.

[0093] According to one embodiment, the ship route generation system (100) can generate a route network by verifying a plurality of edges. Here, the route network can be defined as a set of valid edges among a plurality of edges depicted on a map. Referring to the map (b) illustrated below, a map is illustrated in which edges created to cross land are deleted and only edges located at sea are depicted. Each of the plurality of edges shown in the map (b) illustrated below can correspond to a verified valid edge, and a ship can navigate using each edge as a travel path.

[0094] In one embodiment, a route network can be utilized as an initial route for generating a route for a vessel's movement. The vessel route generation system (100) can generate a route for a vessel's actual movement by connecting each of the multiple edges included in the route network depicted on the map.

[0095] FIG. 5 is a drawing for exemplarily explaining a route of a ship generated according to one embodiment disclosed in this document.

[0096] The ship route generation system (100, see FIG. 1) can generate a ship route based on a route network. Specifically, the ship route generation system (100) can identify feature points adjacent to each of the ship's departure and destination points. According to one embodiment, the ship route generation system (100) can identify the feature point closest to the departure and destination points among a plurality of feature points depicted on a map.

[0097] As illustrated in FIG. 5, the departure points of the ship may correspond to PHU MY (107, 10), ALGECIRAS (-5, 36), and BUSAN NEW PORT (128, 35), respectively, and the destination points of the ship may correspond to YANTIAN (114, 22), SOUTHAMPTON (-1, 50), and TIANJIN XIN GANG (117, 39). Here, each departure point and destination point may be expressed in the form of location data related to latitude and longitude.

[0098] The ship route generation system (100) can identify the feature points that are closest to the departure points of PHU MY (107, 10), ALGECIRAS (-5, 36), and BUSAN NEW PORT (128, 35), respectively. Here, the feature points that are closest to the departure points will correspond to the departure points of the actual ship. In addition, the ship route generation system (100) can identify the feature points that are closest to the destination points of YANTIAN (114, 22), SOUTHAMPTON (-1, 50), and TIANJIN XIN GANG (117, 39), respectively. Here, the feature points that are closest to the destination points may correspond to the destination points of the actual ship.

[0099] The ship route generation system (100) can identify multiple edges connecting the departure point and the most adjacent feature point and the destination point and the most adjacent feature point based on the route network. The ship route generation system (100) can create a ship route by connecting the multiple identified edges. Here, the ship route generation system (100) can create the ship route using a shortest distance algorithm. According to one embodiment, the shortest distance algorithm may be an algorithm that creates the shortest distance connecting the departure point and the most adjacent feature point of the ship and the most adjacent feature point of the destination point of the ship. For example, the shortest distance algorithm may include, but is not limited to, the Dijkstra algorithm or the A* algorithm.

[0100] In one embodiment, a ship's route generated using a shortest path algorithm may be used as an initial solution for finding the ship's optimal route using an optimization algorithm. The optimization algorithm may include, but is not limited to, a genetic algorithm.

[0101] FIG. 6 is a diagram illustrating a process for generating an optimal route according to an embodiment disclosed in this document.

[0102] Referring to Figure 6, the initial route (a) generated based on the route network and the optimal route (b) searched using a genetic algorithm are shown.

[0103] First, the initial route (a) may include a plurality of feature points (W1, W2, W3, W4, W5) identified by the data processing unit (120, see FIG. 1) and a plurality of edges (d1, d2, d3, d4) connecting the feature points. Each of the plurality of feature points may be referred to as a waypoint and may be expressed in the form of position data including data related to the latitude and longitude of the ship. Here, the initial route (a) may correspond to the ship route described with reference to FIG. 5. For example, the initial route (a) may be a ship route generated using a shortest path algorithm, such as Dijkstra's algorithm or A-star algorithm, but is not limited thereto.

[0104] The route generation unit (130, see FIG. 1) can determine at least one variable to be reflected in determining the optimal route. Here, the variables reflected in determining the optimal route may include, but are not limited to, weather conditions, fuel consumption of the vessel based on weather conditions, required time, etc.

[0105] According to one embodiment, the route generation unit (130) may be configured to generate a route that optimally reflects the above-described variables throughout the route along which the vessel will travel. For example, when determining an optimal route using fuel consumption as a variable, the route generation unit (130) may be configured to determine a route that minimizes fuel consumption throughout the route being generated. As another example, when determining an optimal route using fuel consumption and required time as variables, the route generation unit (130) may be configured to determine a route that minimizes fuel consumption and required time throughout the route being generated.

[0106] To this end, the route generation unit (130) can approximate various variables for determining the optimal route in the form of a general solution. The route generation unit (130) can approximate the variables for determining the optimal route in the form of a general solution through various methods, and input the approximated general solution into various optimization algorithms to generate the optimal route.

[0107] According to one embodiment, the route generation unit (130) may generate an optimal route using, but is not limited to, the fuel consumption of the ship and the minimum time required for the ship to reach the destination (Required Time Arrival; RTA), which are dependent variables depending on weather conditions. In this case, the route generation unit (130) may search for an optimal route by changing a plurality of feature points (W1, W2, W3, W4, W5) to generate a route that minimizes fuel consumption and the minimum time required throughout the generated route.

[0108] According to one embodiment, the route generation unit (130) can search for an optimal route using a genetic algorithm, which is an example of an optimization algorithm.

[0109] In one embodiment, the objective function of the genetic algorithm may be related to the sum of fuel consumption per unit distance when the ship moves along each of the multiple edges (d1, d2, d3, d4). Specifically, the objective function of the genetic algorithm may satisfy the following mathematical expression (1).

[0110]

[0111] (Here, N corresponds to the number of edges included in the initial route, corresponds to the fuel consumption per unit distance at the i-th edge, can correspond to the length of the i-th edge.)

[0112] According to one embodiment, since it is most economical to travel along a route that minimizes fuel consumption of a ship, a route where the value of the objective function expressed through mathematical expression 1 is minimized may correspond to an optimal route.

[0113] Here, additional constraints may exist to determine the optimal route. Since the vessel must arrive within the required time, the sum of the time required to travel along the route must be considered. In one embodiment, the route generation unit (130) may further consider constraints that satisfy the following mathematical equation (2).

[0114]

[0115] (Here, N corresponds to the number of edges included in the initial route, corresponds to the velocity per unit distance at the i-th edge, corresponds to the length of the i-th edge, and RTA can correspond to the total sum of required times.)

[0116] In one embodiment, the fuel consumption per unit distance and the speed per unit distance of the vessel may be dependent variables affected by weather conditions.

[0117] The route generation unit (130) can approximate the fuel consumption per unit distance and the speed per unit distance of the vessel as shown in mathematical equations 1 and 2. According to one embodiment, the route generation unit (130) can approximate the fuel consumption per unit distance and the speed per unit distance of the vessel in the form of polynomials (posynomial fitting). The approximated fuel consumption per unit distance and the speed can satisfy mathematical equations 3 and 4 below, respectively.

[0118]

[0119]

[0120] (Here, and is a coefficient of the relationship that indicates the tendency between the ship's output and fuel consumption. and can correspond to the coefficient of the relationship that represents the tendency between the ship's output and speed.)

[0121] According to one embodiment, the coefficients of the relationship representing the tendency between the output of the ship and the fuel consumption and the coefficients of the relationship representing the tendency between the output of the ship and the speed of the ship are not limited to specific values ​​and can be set and applied in various ways.

[0122] The route generation unit (130) can search for a route that minimizes the value of the following mathematical expression 5, which is generated by substituting the above-described mathematical expression 3 into the above-described mathematical expression 1. Here, mathematical expression 5 can correspond to an objective function.

[0123]

[0124] In addition, the route generation unit (130) can search for a route that satisfies the condition of the following mathematical expression 6, which is generated by substituting the above-described mathematical expression 4 into the above-described mathematical expression 2. Here, the mathematical expression 6 can correspond to a constraint condition.

[0125]

[0126] The route generation unit (130) will search for a route that satisfies the conditions of the above-described mathematical expressions 5 and 6 by changing a plurality of feature points (W1, W2, W3, W4, W5) included in the initial route. For example, the route generation unit (130) can calculate fuel consumption and speed conditions corresponding to a route that uses a feature point (W2') adjacent to the second feature point (W2) and a feature point (W4') adjacent to the fourth feature point (W4) as new feature points. The route generation unit (130) can search for an optimal route by changing the feature points and calculating the fuel consumption and speed when moving each edge.

[0127] Here, mathematical expressions 5 and 6 are polynomial approximations of the fuel consumption per unit distance and the speed per unit distance described above, and a route satisfying mathematical expressions 5 and 6 may be a route that has the minimum fuel consumption per unit distance in the entire region and satisfies the required time. According to one embodiment, the route generation unit (130) may search for an optimal route by applying a plurality of feature points in the form of general solutions satisfying mathematical expressions 5 and 6 to a genetic algorithm.

[0128] Figure 7 is a flowchart for explaining the operation of a ship route generation system according to an embodiment disclosed in this document.

[0129] In step S101, the ship route generation system (100, see FIG. 1) can extract the position data of the vessel received at preset intervals. According to one embodiment, the ship route generation system (100) can extract the position data of the vessel from the AIS data received via the AIS device mounted on the vessel, wherein the position data may include, but is not limited to, data related to the latitude and longitude of the identified vessel.

[0130] In step S102, the ship route generation system (100) can identify a plurality of feature points related to the density of ships based on the ship location data.

[0131] According to one embodiment, the ship route generation system (100) may identify feature points using at least one of the Douglas Pecker algorithm and the Quad Tree algorithm, but is not limited thereto. Here, the distance between multiple feature points may be inversely proportional to the density of actually identified ships. According to one embodiment, the ship route generation system (100) may identify multiple feature points based on AIS data in raw data form using the Douglas Pecker algorithm.

[0132] According to one embodiment, the ship route generation system (100) can identify a plurality of feature points based on AIS data in raw data form using a quad tree algorithm.

[0133] According to one embodiment, the ship route generation system (100) can identify a plurality of feature points based on AIS data in raw data form using the Douglas Packer algorithm and the quad tree algorithm.

[0134] Additionally, according to one embodiment, the ship route generation system (100) can identify a plurality of feature points based on AIS data in raw data form without using the above-described algorithm.

[0135] In step S103, the ship route generation system (100) may generate a group of vessel route candidates based on a plurality of feature points. According to one embodiment, the ship route generation system (100) may generate a plurality of triangles by segmenting the identified plurality of feature points using the Delaunay triangulation method, but is not limited thereto. Here, each side of the plurality of triangles may correspond to an edge.

[0136] According to one embodiment, the identified plurality of feature points may correspond to the plurality of feature points described in step S102. That is, the ship route generation system (100) may generate a group of candidate ship routes using at least one of the Douglas Packer algorithm and the quad tree algorithm and / or based on the plurality of feature points identified from AIS data in raw data form.

[0137] In step S104, the ship route generation system (100) can verify the generated route candidate group to generate a valid route network. According to one embodiment, the ship route generation system (100) can identify edges shown at sea among a plurality of edges shown on a map, and delete edges other than edges shown at sea among a plurality of edges shown on the map. Here, the ship route generation system (100) can verify valid edges using pre-stored water depth data. The pre-stored water depth data may include, but is not limited to, data related to a map showing the water depth of a sea or lake, such as a bathymetric map data. The ship route generation system (100) can verify edges shown at sea as valid edges using the water depth data, and delete invalid edges among a plurality of edges shown on the map to generate a route network.

[0138] In step S105, the ship route generation system (100) can generate an initial route based on a valid route network.

[0139] According to one embodiment, the ship route generation system (100) may generate an initial route using a shortest path algorithm. Here, the shortest path algorithm may include, but is not limited to, Dijkstra's algorithm or A-Star algorithm.

[0140] At step S106, the ship route generation system (100) can generate an optimal route based on the initial route.

[0141] According to one embodiment, the ship route generation system (100) can generate an optimal route by applying the generated initial route to an optimization algorithm. The ship route generation system (100) can set various variables for determining the optimal route and generate an optimal route reflecting these variables. For example, the ship route generation system (100) can utilize a genetic algorithm, but is not limited thereto.

[0142] In one embodiment, step S106 may be omitted.

[0143] In the above, all components constituting the embodiments have been described as being combined or operating in combination as one. However, this is not necessarily limited to such embodiments, and within the scope of the purpose, all components may be selectively combined and operated in one or more combinations. Furthermore, terms such as "include," "comprise," or "have" described above, unless specifically stated to the contrary, imply that the corresponding component may be inherent, and therefore should be interpreted to include other components rather than excluding other components.

[0144] The above description is merely an example of the technical idea disclosed in this document, and those skilled in the art to which the embodiments disclosed in this document pertain may make various modifications and variations without departing from the essential characteristics of the embodiments disclosed in this document.

[0145] Accordingly, the embodiments disclosed in this document are intended to illustrate, rather than limit, the technical concepts disclosed in this document, and the scope of the technical concepts disclosed in this document is not limited by these embodiments. The scope of protection of the technical concepts disclosed in this document should be interpreted by the claims below, and all technical concepts within the equivalent scope should be interpreted as being included within the scope of the rights of this document.

Claims

1. A database storing the ship's route network; and A route generation unit for generating an initial route connecting the departure point and destination point of the vessel among the route network; The above route generation unit, A ship route generation system that generates the initial route by approximating the fuel consumption and the speed of the ship so that a cost function related to at least one of the fuel consumption and the speed of the ship is minimized.

2. In the first paragraph, the route generation unit, The objective function related to the sum of fuel consumption consumed when the above ship moves through the above initial route is minimized, A ship route generation system that generates the initial route so as to satisfy a constraint related to the sum of the time required for the ship to move through the initial route.

3. In paragraph 2, The above objective function is, It corresponds to the sum of the product of the fuel consumption per unit distance consumed when moving each edge of the initial route and the length of each edge, The above constraints are, A ship route generation system corresponding to a condition in which the sum of the length of each edge divided by the speed per unit distance when the ship moves is less than the total sum of the required time for the ship.

4. In the third paragraph, the route generation unit, A ship route generation system that polynomially approximates the product of the fuel consumption per unit distance of each edge and the length of each edge, and the product of the length of each edge and the speed per unit distance when the ship moves.

5. In the fourth paragraph, the route generation unit, A ship route generation system that inputs the initial route into a genetic algorithm to generate a route for the ship to travel.

6. In the second paragraph, the route network, A ship route generation system in which the ship is identified based on AIS data of the ship and the location data related to the identified location is generated.

7. In paragraph 6, A ship route generation system further comprising a data processing unit that preprocesses raw data-type location data related to the location of the ship identified at preset intervals based on the AIS data to identify a plurality of characteristic points related to the density of the ship.

8. In the 7th paragraph, the data processing unit, A ship route generation system that preprocesses the location data using at least one algorithm that identifies a feature point representing the location of the ship among the location data in the form of the raw data.

9. In the 8th paragraph, the data processing unit, A ship route generation system that identifies the above-mentioned feature points using the Douglas Pecker algorithm.

10. In the 8th paragraph, the data processing unit, A ship route generation system that divides a two-dimensional space in which the position data in the form of the above raw data is depicted into a plurality of spaces, and repeats the operation of dividing the plurality of spaces until the number of the position data included in each of the divided spaces reaches a threshold value.

11. In the 10th paragraph, the data processing unit, A ship route generation system that identifies a feature point corresponding to an average value of multiple location data included in each of the above-described areas or a feature point closest to the feature point corresponding to the average value.

12. In paragraph 6, the route network, A system for generating a ship route corresponding to each side of a plurality of triangles generated as a result of dividing a plurality of feature points related to the density of the ships among the above location data using the Delaunay triangulation method.

13. In the 12th paragraph, the route generation unit, A ship route generation system that generates multiple routes that satisfy the values ​​of the objective function and the constraints by changing the multiple feature points.

14. In the 13th paragraph, the route generation unit, A ship route generation system that generates the initial route using a shortest distance algorithm that searches for the shortest distance connecting each of the feature points adjacent to the ship's departure point and destination point among the above plurality of feature points.

15. In the 14th paragraph, the shortest distance algorithm, A ship route generation system including Dijkstra Algorithm or A* Algorithm.

Images