A ship route planning method based on meteorological data

Abstract

The present specification provides a kind of ship route planning method based on meteorological data, the invention relates to route planning technical field, when ship navigation environment changes, obtain the meteorological data and operating state data of the navigation area of ship, dynamically adapt the change of meteorological condition, based on meteorological data and operating state data, using the resistance coefficient calculation model constructed in advance, determine the additional resistance coefficient corresponding to each coordinate point, and construct as resistance coefficient matrix, based on resistance coefficient matrix and navigation area, construct 1-NKP based on ship route planning model, based on ship route planning model, using greedy algorithm, determine the potential route of ship. By combining ship route planning with 1-NKP, the potential route of ship is quickly solved using greedy algorithm, precise avoidance and navigation efficiency improvement in severe weather are realized, have strong scene adaptability, provide safe and economic balance route planning scheme for shipping enterprise.

Description

Technical Field

[0001] This specification relates to the field of route planning technology, and in particular to a method for ship route planning based on meteorological data. Background Technology

[0002] Ship route planning, as a core technology of intelligent shipping systems, supports the safety and efficiency of over 80% of global international cargo transportation and plays an irreplaceable role in areas such as the promotion of new energy vessels and ocean logistics scheduling. Ships navigate in complex marine environments, and the dynamic changes in meteorological elements such as wind, waves, and currents directly affect their navigation stability, leading to an increase in ship accidents caused by severe weather. Furthermore, extreme weather events such as typhoons and sudden severe convective weather, due to delayed warnings or inaccurate path predictions, can easily cause significant losses such as ship groundings and equipment damage. Therefore, there is an urgent need to integrate accurate meteorological data for ship route planning.

[0003] Currently, traditional route planning methods mainly rely on static path planning algorithms such as Dijkstra and A*, or on manual route planning based on crew experience. However, these methods are difficult to dynamically adapt to changes in weather conditions. Furthermore, these methods rely on a single data source, such as shore-based weather forecasts or shipborne sensors, which lacks real-time performance and is limited by spatial coverage, resulting in insufficient accuracy in risk assessment and a significant decrease in planning reliability.

[0004] Based on this, this specification provides a method for ship route planning based on meteorological data. Summary of the Invention

[0005] To address the problems of existing technologies, such as difficulty in dynamically adapting to changes in weather conditions, low real-time performance, and low planning reliability, this specification provides a ship route planning method based on meteorological data to solve the aforementioned problems in the existing technologies.

[0006] The following technical solution is adopted in this specification:

[0007] This specification provides a method for ship route planning based on meteorological data. The method includes:

[0008] S1: Data Acquisition: When the ship's navigation environment changes, acquire meteorological data and operational status data of the ship's navigation area; the navigation area is an undirected connected graph composed of multiple coordinate points, and the multiple coordinate points are between the ship's current position coordinates and target position coordinates;

[0009] S2: Constructing the drag coefficient matrix: Based on the meteorological data and the operational status data, a pre-constructed drag coefficient calculation model is used to determine the additional drag coefficient corresponding to each coordinate point and construct a drag coefficient matrix.

[0010] S3: Constructing a Ship Route Planning Model: Based on the resistance coefficient matrix and the navigation area, construct a ship route planning model based on 1-NKP. The optimization objective of the ship route planning model is: under given constraints, solve for the sum of the products of the navigation resistance of all coordinate points in the undirected connected graph and the state of the corresponding coordinate points as the total resistance, and find the minimum value of the total resistance. The minimum value is:

[0011] (1)

[0012] Among them, the The number of coordinate points, the Represents coordinate points The navigation resistance, the Represents the coordinate point The state;

[0013] S4: Route planning: Based on the ship route planning model, a greedy algorithm is used to determine the potential route of the ship.

[0014] Optionally, the meteorological data includes wind speed and wave height; the operational status data includes basic parameters, drag-related parameters, and operational parameters. The drag-related parameters include seawater density, air density, seawater drag coefficient, and air drag coefficient. The basic parameters include the resistance of the vessel when sailing in still water, the characteristic length of the vessel, its projected area above the waterline, and its width. The operational parameters include the vessel's speed in still water.

[0015] Optionally, the drag coefficient calculation model in S2 is as follows:

[0016] (2)

[0017] (3)

[0018] (4)

[0019] Among them, the The additional drag coefficient, the The resistance of the vessel when it is sailing in still water, the Let t be the additional resistance of the wave on the ship at time t. The additional resistance of the wind to the ship at time t is... The feature length is the length of the feature. The height of the wave at time t represents the height of the wave at that time. Represents gravitational acceleration, the The density of the seawater, For the air density, the and stated These are the projected area and width of the vessel above the waterline, respectively. and stated These are the seawater drag coefficient and the air drag coefficient, respectively. Let be the wavelength of the wave at time t. Let be the angle between the wave and the ship at time t. This indicates that the seawater drag coefficient is affected by both the wavelength and the incident direction. Let t be the speed of the ship in still water at time t. Let be the wind speed at time t.

[0020] Optionally, the method for constructing the ship route planning model based on 1-NKP in S3 is as follows:

[0021] Each coordinate point is taken as a vertex of the graph structure corresponding to 1-NKP. The navigation resistance of each coordinate point is set as the vertex cost of 1-NKP. The navigation distance between adjacent coordinate points is set as the vertex weight of 1-NKP. The maximum navigation distance of the ship is limited to the total backpack capacity of 1-NKP. The problem of minimizing the sum of the products of the navigation resistance and the state of the coordinate point is transformed into the optimal solution problem of 1-NKP with capacity constraints. The navigation resistance is positively correlated with the additional resistance coefficient.

[0022] Optionally, the predetermined constraints of the 1-NKP-based route planning model in S3 include:

[0023] (5)

[0024] Among them, the Indicates to coordinate point The sailing distance, the This indicates the maximum sailing distance, the Represents coordinate points The state of the coordinate point The coordinate point The neighborhood coordinates of the points, Indicates the coordinate point The set of directly connected adjacent coordinate points, Describes the knapsack set, the Indicates the With the The intersection, the Represents the set of coordinate points, the This indicates the current position coordinates of the vessel.

[0025] Optionally, S4 specifically includes:

[0026] S41: Use the current position coordinates of the ship as the initial coordinate point and store them in the knapsack set to obtain the initial knapsack set;

[0027] S42: Determine the total sailing distance and total sailing resistance of all coordinate points in the initial knapsack set, and determine the remaining capacity of the initial knapsack set based on the maximum sailing distance and the total sailing distance;

[0028] S43: Based on the undirected connected graph, determine the neighborhood coordinates of all coordinate points in the initial knapsack set and store them in the candidate set;

[0029] S44: Calculate the resistance-to-distance ratio of each coordinate point in the candidate set, and determine whether there are any coordinate points that meet the preset screening conditions; the screening conditions are that the resistance-to-distance ratio is the smallest and the sailing distance does not exceed the remaining capacity;

[0030] S45: If they exist, the coordinate points that meet the filtering conditions are taken as candidate coordinate points and stored in the initial knapsack set to obtain the first knapsack set;

[0031] S46: Determine whether the remaining capacity of the first knapsack set meets the preset termination condition;

[0032] S47: If the termination condition is not met, the first knapsack set is used as the initial knapsack set again, and S42~S47 are repeated until the remaining capacity of the first knapsack set meets the termination condition. Based on the coordinate points in the first knapsack set, the potential route of the ship is generated.

[0033] Optionally, S45 specifically includes:

[0034] If there is only one coordinate point that satisfies the filtering conditions, then the coordinate point that satisfies the filtering conditions is taken as a candidate coordinate point and stored in the initial knapsack set to obtain the first knapsack set.

[0035] If there are multiple coordinate points that meet the filtering conditions, the coordinate point with the least sailing resistance among the multiple coordinate points that meet the filtering conditions is selected as the candidate coordinate point and stored in the initial backpack set to obtain the first backpack set.

[0036] If no coordinate point meets the filtering criteria, then the potential route of the ship is generated based on the coordinate points in the initial knapsack set.

[0037] Optionally, the method further includes:

[0038] If the termination condition is met, the total sailing distance and total sailing resistance of all coordinate points in the first backpack set are determined, and the potential route of the ship is generated based on the coordinate points in the first backpack set.

[0039] Optionally, the method for determining the potential route in S4 is as follows:

[0040] Based on the ship route planning model, a greedy algorithm is used to solve for routes that satisfy the given constraints, which are then used as candidate routes.

[0041] Based on the drag coefficient matrix, the cumulative additional drag coefficient of the candidate route is calculated;

[0042] The candidate route with the lowest cumulative additional resistance coefficient is selected as the potential route of the vessel.

[0043] Optionally, the method for obtaining the meteorological data in step S1 is as follows:

[0044] When the ship's navigation environment changes, environmental data of the ship's navigation area is collected;

[0045] When the environmental data includes only one meteorological factor, the wind speed and wave height of the navigation area are determined as meteorological data based on the Beaufort scale and the meteorological factor. The Beaufort scale includes the correspondence between Beaufort wind level, wind speed, wave height and sea state information. The meteorological factor is the wind speed, the wave height or the sea state information.

[0046] Optionally, the method further includes:

[0047] During the navigation along the potential route, the meteorological data corresponding to the coordinates of the points not reached along the potential route are monitored in real time.

[0048] When changes in the meteorological data of the coordinate points are detected, the meteorological data of all coordinate points between the current position coordinates of the ship and the target position coordinates are reacquired, and the ship's route is replanned based on the acquired meteorological data.

[0049] Optionally, the termination condition in S46 is: the remaining capacity of the first knapsack set is not less than the minimum travel distance corresponding to the neighboring coordinates of the candidate coordinate point.

[0050] The above-mentioned technical solutions adopted in this specification can achieve the following beneficial effects:

[0051] This specification provides a ship route planning method based on meteorological data. When the ship's navigation environment changes, it acquires meteorological and operational status data of the ship's navigation area to dynamically adapt to changes in weather conditions and provide data support for subsequent route planning. The navigation area is an undirected connected graph composed of multiple coordinate points located between the ship's current and target positions. Furthermore, considering the impact of wind and waves on the ship's navigation at sea, which increases resistance and affects speed, a pre-constructed resistance coefficient calculation model is used based on meteorological and operational status data to determine the additional resistance coefficient corresponding to each coordinate point and construct a resistance coefficient matrix, providing a basis for subsequent route planning.

[0052] Then, based on the resistance coefficient matrix and the navigation area, a ship route planning model based on 1-NKP is constructed. The optimization objective of this ship navigation planning model is to solve for the sum of the products of the navigation resistance of all coordinate points in the undirected connected graph (i.e., the navigation area) and the state of the corresponding coordinate points, under given constraints, as the total resistance, and to find the minimum value of the total resistance. Based on the ship route planning model, a greedy algorithm is used to determine the ship's potential route. By introducing 1-NKP (i.e., the 1-neighbor knapsack problem), ship route planning is combined with 1-NKP, allowing the greedy algorithm to quickly solve for the ship's potential route. Compared to traditional route planning methods, this allows for faster route planning when environmental changes necessitate replanning, achieving precise avoidance of severe weather and improved navigation efficiency. Furthermore, solving the ship route planning model using a greedy algorithm for replanning routes demonstrates strong scenario adaptability, providing shipping companies with a route planning solution that balances safety and economy.

[0053] In this invention, when constructing the ship route planning model based on 1-NKP, each coordinate point can be treated as a vertex of the graph structure corresponding to 1-NKP. The navigation resistance of each coordinate point is set as the vertex cost of 1-NKP, the navigation distance between adjacent coordinate points is set as the vertex weight of 1-NKP, and the maximum navigation distance of the ship is limited to the total capacity of the knapsack in 1-NKP. The problem of minimizing the sum of the products of the navigation resistance and the state of each coordinate point is transformed into a 1-NKP optimal solution problem with capacity constraints. This allows for mapping and transformation of variables in 1-NKP and route planning, providing data support for subsequent use of a greedy algorithm to solve the ship route, thereby improving the speed and real-time performance of ship route planning.

[0054] In this invention, environmental data of the ship's navigation area is collected when the navigation environment changes. However, the environmental data may only include one meteorological factor, resulting in incomplete data. Therefore, when the environmental data only includes one meteorological factor, the wind speed and wave height of the navigation area can be determined as meteorological data based on the Beaufort scale and the meteorological factor. The Beaufort scale includes the correspondence between Beaufort scale, wind speed, wave height and sea state information. The meteorological factor is the wind speed, wave height or sea state information. By mapping and integrating multiple meteorological factors through the Beaufort scale, meteorological data including multiple meteorological factors can be obtained, so as to realize the collaborative use of heterogeneous meteorological factors in route planning.

[0055] In determining potential routes, this invention, in addition to solving for candidate routes that meet the given constraints based on the ship route planning model and greedy algorithm, can further calculate the cumulative additional resistance coefficient of the candidate routes based on the resistance coefficient matrix, and select the candidate route with the smallest cumulative additional resistance coefficient as the ship's potential route, thereby optimizing the candidate routes to generate potential routes with low resistance and short sailing distance. Attached Figure Description

[0056] The accompanying drawings, which are included to provide a further understanding of this specification and form part of this specification, illustrate exemplary embodiments and are used to explain this specification, but do not constitute an undue limitation thereof. In the drawings:

[0057] Figure 1 This is a flowchart illustrating a ship route planning method based on meteorological data provided in this specification.

[0058] Figure 2 This is a schematic diagram illustrating the process of solving a ship route planning model based on 1-NKP using a greedy algorithm, as provided in this specification.

[0059] Figure 3 This is a route planning diagram based on a greedy algorithm provided in this specification. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0061] This specification provides a method for ship route planning based on meteorological data. The technical solutions provided by the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0062] Figure 1 This is a flowchart illustrating a ship route planning method based on meteorological data provided in this specification, which specifically includes the following steps:

[0063] S1: Data Acquisition: When the ship's navigation environment changes, acquire meteorological data and operational status data of the ship's navigation area; the navigation area is an undirected connected graph composed of multiple coordinate points, which are located between the ship's current position coordinates and target position coordinates.

[0064] In this manual, the equipment used for route planning can first acquire data, specifically meteorological and operational status data of the ship's navigation area when the ship's navigation environment changes. This equipment can be a server, a system, one or more modules within a system, or electronic devices such as desktop or laptop computers. For ease of description, the following explanation focuses on a server as the primary execution entity, illustrating a meteorological data-based ship route planning method provided in this manual. The aforementioned environmental changes refer to sudden changes in sea state or temporary obstacles during ship navigation, such as sudden gusts of wind or temporary no-navigation zones. In such cases, a rapid replanning of the route is necessary. The area for replanning the route is the candidate navigable sea area between the ship's current position and the target position, i.e., the navigation area. This is transformed into a set of vertices and edges in a graph model using a gridding approach. The navigation area can be an undirected connected graph composed of multiple coordinate points (grid points), located between the ship's current and target positions. The edges in this undirected connected graph represent the reachability between coordinate points, and each edge has a navigation distance set, i.e., the navigation distance between adjacent grid points (i.e., coordinate points), or the navigation distance between two coordinate points connected by an edge. This navigation distance is pre-determined known data and does not require real-time collection or prediction. The ship can be of any type.

[0065] The aforementioned meteorological data may include wind speed and wave height. This meteorological data can be collected in real time. Specifically, when acquiring meteorological data, if the ship's navigation environment changes, the server can collect environmental data of the ship's navigation area and use the meteorological factors in the environmental data as meteorological data. The environmental data may include meteorological factors, which may be wind speed, wave height, or sea state information. However, when the environmental data only includes one meteorological factor, the server can also determine the wind speed and wave height of the navigation area as meteorological data based on the Beaufort scale and the meteorological factors. The Beaufort scale includes the correspondence between Beaufort scale, wind speed, wave height, and sea state information, as detailed in Table 1 below.

[0066] Table 1

[0067] Beaufort scale wind speed High waves Sea conditions 0 <l knots 0m calm 1 1-3 knots 0.1~0.3m No ripples 2 4-6 knots 0.3~0.5m Xiao Bo 3 7-10 knots 0.5~0.9m big wave 4 11-16 knots 0.9~1.25m Xiaolang 5 17-21 knots 1.25~2.5m Mid-wave 6 22-27 knots 2.5~3m Long Wave

[0068] The above Beaufort Scale is an empirical scale that estimates the sea state through wind speed and wave height, and the sea state affects the additional resistance of all-electric ships. Moreover, in the "long wave" sea state, the additional resistance can reach up to 40% of the resistance on calm water. For the sake of illustration, it is assumed in this specification that the above ship avoids dangerous sea states, so only some levels of the Beaufort Scale are adopted. That is, only the wind speed, wave height and sea state corresponding to Beaufort Scale levels 0 to 6 in Table 1 are shown. Specifically, when the Beaufort Scale is level 0, the wind speed is < 1 knot, the wave height is 0 m, and the sea state is calm (i.e., Flat). When the Beaufort Scale is level 1, the wind speed is in the range of 1 - 3 knots, the wave height is in the range of 0.1 - 0.3 m, and the sea state is ripple without crest (i.e., Ripple without Crest). When the Beaufort Scale is level 2, the wind speed is in the range of 4 - 6 knots, the wave height is in the range of 0.3 - 0.5 m, and the sea state is small wavelet (i.e., Small Wavelet). When the Beaufort Scale is level 3, the wind speed is in the range of 7 - 10 knots, the wave height is in the range of 0.5 - 0.9 m, and the sea state is large wavelet (i.e., Large Wavelet). When the Beaufort Scale is level 4, the wind speed is in the range of 11 - 16 knots, the wave height is in the range of 0.9 - 1.25 m, and the sea state is small wave (i.e., Small Wave). When the Beaufort Scale is level 5, the wind speed is in the range of 17 - 21 knots, the wave height is in the range of 1.25 - 2.5 m, and the sea state is moderate wave (i.e., Moderate Wave). When the Beaufort Scale is level 6, the wind speed is in the range of 22 - 27 knots, the wave height is in the range of 2.5 - 3 m, and the sea state is long wave (i.e., Long Wave).

[0069] Furthermore, meteorological factors may be dynamically changing. Therefore, the aforementioned environmental data can also represent meteorological factors for the navigation area over a future period. In other words, besides collecting environmental data for the navigation area at the current moment, it is also possible to predict environmental data for a future period. Specific prediction methods can be employed using any existing algorithm or model. The aforementioned future period can be a preset timeframe, such as 7 days; the specific length is not specifically limited in this specification. Based on this, when the ship's navigation environment changes, the server can also collect first environmental data for the ship's navigation area at the current moment and predict second environmental data for the navigation area over a specified time period. The meteorological factors in the first and second environmental data are used as meteorological data, which includes wind speed and wave height for the navigation area at the current moment and at all moments within the specified time period. The specified time period is preset, and the starting time is the current moment. For ease of explanation, the following example assumes that the meteorological factors at all coordinate points within the navigation area remain unchanged from the current moment for a future specified time period.

[0070] In addition to wind speed and wave height, the meteorological data mentioned above may also include wavelength and angle.

[0071] S2: Constructing the drag coefficient matrix: Based on the meteorological data and the operational status data, a pre-constructed drag coefficient calculation model is used to determine the additional drag coefficient corresponding to each coordinate point and construct a drag coefficient matrix.

[0072] In this specification, the server can construct a drag coefficient matrix. Based on meteorological and operational status data, a pre-built drag coefficient calculation model is used to determine the additional drag coefficient corresponding to each coordinate point and construct a drag coefficient matrix. Since ships are affected by wind and waves during navigation at sea, leading to increased ship resistance and consequently speed loss or gain, the effect of wind and waves on ship speed needs to be considered. The aforementioned operational status data includes basic parameters, drag-related parameters, and operational parameters. The drag-related parameters include seawater density, air density, seawater drag coefficient, and air drag coefficient. The basic parameters include the ship's resistance in still water, the ship's characteristic length (which can be set as ship length or waterline length for normalizing wind and wave resistance), and its projected area and width above the waterline. The operational parameters include the ship's speed in still water. The aforementioned basic parameters and resistance-related parameters are known inherent ship parameters. However, the meteorological factors included in the meteorological data—wind speed, wave height, wavelength, and angle—require real-time or near-real-time updates (i.e., real-time or predicted meteorological factors) and are collected or predicted via S1. Furthermore, the aforementioned operational parameters are navigation state parameters and can also be updated in real-time, specifically by the shipborne navigation system and meteorological / sea state forecast data. Therefore, the additional resistance coefficient is calculated using the ship's inherent parameters, real-time / predicted meteorological factors, and navigation state parameters.

[0073] In determining the additional drag coefficient for each coordinate point, the server can use the drag coefficient calculation model described above, based on the meteorological data and operational parameters corresponding to that coordinate point, to determine the additional drag coefficient for that coordinate point. Then, a drag coefficient matrix including the additional drag coefficients for each coordinate point is constructed.

[0074] S3: Construct a ship route planning model: Based on the resistance coefficient matrix and the navigation area, construct a ship route planning model based on 1-NKP. The optimization objective of the ship route planning model is: under the constraints of the given constraints, solve for the sum of the products of the navigation resistance of all coordinate points in the undirected connected graph and the state of the corresponding coordinate points as the total resistance, and find the minimum value of the total resistance.

[0075] In this specification, the server can construct a ship route planning model, that is, based on the resistance coefficient matrix and the navigation area, construct a ship route planning model based on 1-NKP. The optimization objective of the ship route planning model is, under the constraints of the given conditions, to solve for the sum of the products of the navigation resistance of all coordinate points in the undirected connected graph and the state of the corresponding coordinate points as the total resistance, and to find the minimum value of the total resistance. This minimum value can be expressed by the following formula (1):

[0076] (1)

[0077] Among them, the above The number of coordinate points. Represents coordinate points The sailing resistance, Represents coordinate points The state.

[0078] Specifically, when constructing a ship route planning model based on 1-NKP, the server can use each coordinate point as a vertex of the graph structure corresponding to 1-NKP, set the navigation resistance of each coordinate point as the vertex cost of 1-NKP, set the navigation distance between adjacent coordinate points as the vertex weight of 1-NKP, and limit the maximum navigation distance of the ship to the total capacity of the knapsack in 1-NKP. The pre-defined problem is transformed into a problem of solving 1-NKP, that is, the problem of minimizing the sum of the products of the navigation resistance of the coordinate points and the state of the coordinate points is transformed into a 1-NKP optimal solution problem with capacity constraints. The above navigation resistance is positively correlated with the additional resistance coefficient, that is, the navigation resistance can be the product of the additional resistance coefficient and the ship mass.

[0079] S4: Route Planning: Based on the ship route planning model, a greedy algorithm is used to determine the ship's potential route.

[0080] In this specification, the server can perform route planning, that is, based on the ship route planning model, it uses a greedy algorithm to determine the ship's potential route, which can be achieved through the following steps:

[0081] S41: Use the ship's current position coordinates as the initial coordinate points and store them in the knapsack set to obtain the initial knapsack set, where the initial knapsack set can be... The above initial coordinate points can be: ,at this time .

[0082] S42: Determine the total sailing distance and total sailing resistance of all coordinate points in the initial knapsack set, and determine the remaining capacity of the initial knapsack set based on the maximum sailing distance and the total sailing distance. The total sailing distance can be calculated using the following formula (14), i.e. The total navigation resistance mentioned above can be calculated using the following formula (13), that is... The remaining capacity mentioned above can be calculated using the following formula (15), that is... .

[0083] S43: Based on undirected connected graphs (i.e.) (or navigation area), determine the neighboring coordinates (neighboring coordinates, i.e., those with edges to any coordinate in the initial knapsack set) of all coordinates in the initial knapsack set, and store them in the candidate set. The candidate set can be: .

[0084] S44: Calculate the resistance-to-distance ratio of each coordinate point in the candidate set to determine whether there are any coordinate points that meet the preset screening conditions. The resistance-to-distance ratio can be calculated using the following formula (12), i.e. The above screening criteria can be the minimum resistance-to-range ratio and the sailing distance not exceeding the remaining capacity (i.e., ), Represents the candidate set coordinates in The travel distance, i.e., the distance from the coordinate point in the initial knapsack set to the coordinate point mentioned above. The sailing distance.

[0085] S45: If they exist, the coordinate points that meet the filtering criteria are taken as candidate coordinate points and stored in the initial knapsack set to obtain the first knapsack set. Here, it is assumed that the coordinate points... If the coordinates are candidate points, then the first knapsack set is... .

[0086] S46: Determine whether the remaining capacity of the first knapsack set meets the preset termination condition. The termination condition can be that the remaining capacity of the first knapsack set is not less than the minimum sailing distance corresponding to the neighboring coordinates of the candidate coordinates. That is, first determine the neighboring coordinates of the candidate coordinates, then determine the sailing distance corresponding to the neighboring coordinates, that is, the sailing distance from the candidate coordinates to the neighboring coordinates, and then determine the minimum value of the sailing distance, that is, the minimum sailing distance. The remaining capacity of the first knapsack set can also be calculated using the following formula (15).

[0087] S47: If the termination condition is not met, the first knapsack set is used as the initial knapsack set again, and S42~S47 are repeated until the remaining capacity of the first knapsack set meets the termination condition. Based on the coordinate points in the first knapsack set, a potential route for the ship is generated. Specifically, when generating the potential route based on the coordinate points in the first knapsack set, the route sequence composed of the coordinate points in the first knapsack set can be generated according to the order in which the coordinate points were added to the first knapsack set, serving as the potential route for the ship.

[0088] Furthermore, in S44 above, when determining whether there are coordinate points that meet the preset filtering conditions, multiple results can be obtained: only one exists, multiple exist, or none exist. Different results correspond to different processing methods. Therefore, in S45 above, if only one coordinate point meets the filtering conditions, the coordinate point that meets the filtering conditions is taken as a candidate coordinate point and stored in the initial knapsack set to obtain the first knapsack set. If multiple coordinate points meet the filtering conditions, it means that multiple... Equal coordinate points can be used to compare the navigation resistance (i.e., ...) among multiple coordinate points that meet the screening criteria. The smallest coordinate point is selected as a candidate coordinate point and stored in the initial knapsack set to obtain the first knapsack set. However, if no coordinate point meets the selection criteria, the potential route of the ship is generated directly based on the coordinate points in the initial knapsack set.

[0089] In addition, if the termination condition is met, the potential route of the ship can be generated based on the coordinates in the first knapsack set.

[0090] Furthermore, when the termination conditions are met, in addition to generating the potential route of the ship, the total sailing distance and total sailing resistance of all coordinate points in the first backpack set can also be determined. Specifically, the total sailing distance can be calculated using the following formula (14), and the total sailing resistance can be calculated using the following formula (13).

[0091] In some embodiments of this specification, the above-mentioned drag coefficient calculation model is a model composed of the following formulas (2) to (4), namely:

[0092] (2)

[0093] (3)

[0094] (4)

[0095] in, For the additional drag coefficient, The resistance of a ship when it is sailing in still water. Let t be the additional resistance of the wave on the ship at time t. Let t be the additional resistance of the wind to the ship. For characteristic length, This represents the height of the wave at time t (i.e., wave height). Represents gravitational acceleration. The density of seawater, This refers to air density. and These are the projected area and width of the ship above the waterline, respectively. and stated These are the seawater drag coefficient and the air drag coefficient, respectively. Let be the wavelength of the wave at time t. Let t be the angle between the wave and the ship at time t (assuming the wind and wave are in the same direction). This indicates that the drag coefficient of seawater is affected by both wavelength and incident direction. Let be the speed of the ship in still water at time t. Let be the wind speed at time t. It should be noted that time t can refer to the current time, or it can refer to any time within the specified time period mentioned above; this specification does not impose any specific limitation.

[0096] In some embodiments of this specification, the predetermined constraints of the 1-NKP-based route planning model in S3 above (i.e. ) may include:

[0097] (5)

[0098] in, The number of coordinate points. Represents coordinate points The sailing resistance, Indicates to coordinate point The sailing distance, i.e., the coordinates. Neighborhood coordinates to coordinates The sailing distance, Represents coordinate points state, Indicates the maximum sailing distance. Represents coordinate points The state, coordinates coordinate point The neighborhood coordinates of the points. Represents coordinate points The set of directly connected adjacent coordinate points, Represents the knapsack set. express With the The intersection, Represents the set of coordinate points. This indicates the ship's current position coordinates. The above " " indicates that if the coordinates of the point Selected into the knapsack set (i.e. ), then its neighborhood (i.e. There is at least one coordinate point in the () It's already in the backpack collection.

[0099] In some embodiments of this specification, the 1-NKP mentioned above refers to the 1-neighbor knapsack problem. Assume that... Given relatively independent items and a knapsack with a capacity of C, each item has two attributes: weight W and price P. The ordinary knapsack problem is to select some items from these items to put into the knapsack, maximizing their profit while ensuring that the sum of their weights does not exceed the knapsack's capacity. Building upon this, if we consider vertices in a connected undirected simple graph as items, and a vertex is selected for the knapsack if at least one of its directly connected vertices has already been placed in the knapsack, then this type of problem is called 1-NKP. When the simple undirected connected graph is a complete graph, 1-NKP is equivalent to the ordinary knapsack problem, so the ordinary knapsack problem can be seen as a special case of 1-NKP. The 1-NKP problem includes the following parameters:

[0100] This represents a simple undirected connected graph, hereinafter simply referred to as a graph. , The set of vertices (items) is The set of edges is ;

[0101] for A subset of represents the set of vertices that have been packed into the knapsack (i.e., the knapsack set).

[0102] This represents the initial vertex to be placed in the knapsack. ;

[0103] Represents vertices The vertex cost (i.e., price). ;

[0104] Represents vertices Vertex weights (i.e., weights). ;

[0105] Represents vertices The cost-weight ratio (i.e., price-weight ratio) and the number of vertices are Specifically, the following formula (6) can be used for calculation:

[0106] (6);

[0107] This represents the sum of the prices (i.e., vertex costs) of all vertices in the current knapsack, which can be calculated using the following formula (7):

[0108] (7);

[0109] This represents the sum of the weights (i.e., vertex weights) of all vertices in the current knapsack, which can be calculated using the following formula (8):

[0110] (8);

[0111] This indicates the total capacity of the backpack, while The remaining capacity of the backpack can be calculated using the following formula (9):

[0112] (9).

[0113] In the figure In the context of the 1-neighborhood knapsack problem, the goal is to find a neighborhood that contains at least the initial vertex. vertex set , making The problem of finding the maximum sum of prices (i.e., vertex costs) of all vertices in the system is the 1-NKP optimal solution problem with capacity constraints, which can be represented by the following formula (10):

[0114] (10)

[0115] in, Represents vertices The state.

[0116] Furthermore, the aforementioned capacity constraint can be satisfied. The sum of the weights of all vertices in the knapsack is no greater than the knapsack capacity. And the concept of 1-neighborhood mentioned above is the vertex. The selection of a vertex into the knapsack satisfies a necessary condition, which is that the vertex is selected as a vertex. At least one vertex in the neighborhood of has already been selected into the knapsack. Therefore, the constraint of the 1-neighborhood knapsack problem is:

[0117] (11)

[0118] Among them, When it is 1, it represents a vertex. Selected into the backpack, in When the value is 0, it represents a vertex. Not in the backpack.

[0119] Based on the aforementioned 1-neighborhood knapsack problem, a ship route planning model can be constructed through variable mapping to achieve the core objective of "minimizing total resistance" (i.e., the aforementioned optimization objective). Specifically, the ship's current position coordinates are used as the initial vertices. The coordinates of each point within the navigation area are considered as shown in the above figure. Vertex in The vertex cost in the above 1-NKP Replace with the navigation resistance at each coordinate point The navigation resistance can be calculated based on the aforementioned additional resistance coefficient, and the navigation resistance of obstacles or inaccessible coordinate points is set as... The vertex weights in the above 1-NKP Replace with the sailing distance between each coordinate point Total backpack capacity Replace with the maximum acceptable sailing distance for the vessel. The constraints in the 1-NKP framework are adjusted from "maximum total cost" to "minimum total resistance," while retaining the core constraint of 1-NKP, namely, that a vertex included in the route must satisfy "at least one vertex in its neighborhood is already within the route." Therefore, the following predetermined constraints are obtained. It should be noted that the sailing distances and maximum sailing distances between the coordinate points mentioned above are known data.

[0120] Based on this, the above-mentioned ship route planning model includes, in addition to the above... , , , , , , , , In addition to the above, it also includes the following parameters:

[0121] Represents coordinate points The drag-to-range ratio, at the apex (coordinate points), is... Specifically, the following formula (12) can be used for calculation:

[0122] (12);

[0123] This represents the sum of resistance (navigation resistance) at all coordinate points in the current backpack, which can be calculated using the following formula (13):

[0124] (13);

[0125] This represents the sum of the flight distances (travel distances) of all coordinate points in the current backpack, which can be calculated using the following formula (14):

[0126] (14);

[0127] This indicates the total capacity of the backpack, which is the maximum range of travel.

[0128] The remaining capacity of the backpack can be calculated using the following formula (15):

[0129] (15).

[0130] In some embodiments of this specification, the above-mentioned drag coefficient calculation model may further include the following formula (16), namely:

[0131] (16)

[0132] in, for .

[0133] In some embodiments of this specification, the above-mentioned drag coefficient matrix may be as shown in the following formula (17):

[0134] (17)

[0135] in, Indicates the ship's current position. This indicates the target position of the ship. For coordinates that are blocked by obstacles or cannot be reached from adjacent coordinates, the additional resistance coefficient is set to... .

[0136] In some embodiments of this specification, in step S4 above, when determining potential routes, the server may first use a greedy algorithm based on the ship route planning model to solve for routes that satisfy predetermined constraints, which are then considered as candidate routes. Afterwards, based on the drag coefficient matrix, the cumulative additional drag coefficient of the candidate routes is calculated, i.e. Specifically, the following formula (18) can be used for calculation, namely:

[0137] (18)

[0138] Among them, the above This represents the cumulative additional drag coefficient, as stated above. Indicates the coordinates of the ship passing through. Additional drag coefficient at that time This represents the total number of grid points, i.e., the total number of coordinate points on the candidate route.

[0139] Then, all candidate routes are iterated through, and the candidate route with the smallest cumulative additional resistance coefficient is selected as the potential route for the ship.

[0140] Furthermore, since the additional resistance can reach up to 40% of the still water resistance under "long wave" sea conditions, and assuming that the ship avoids dangerous sea conditions and only uses part of the Beaufort scale, it is possible to verify and analyze the above-mentioned drag coefficient calculation model to map different sea conditions (or Beaufort scale) to different additional drag coefficient ranges, namely 0-0.2, 0.2-0.3, and greater than 0.3. The above formula (18) Limited to the range of 0-0.4, that is .

[0141] In some embodiments of this specification, after obtaining the potential route, the ship can proceed according to the potential route. Subsequently, during navigation along the potential route, the server can also monitor in real time the meteorological data corresponding to coordinates at points not yet reached within the potential route. When a change in the meteorological data of a coordinate point is detected, the server reacquires the meteorological data for all coordinates between the ship's current position and the target position, and based on the acquired meteorological data, replans the ship's route. The specific process of replanning the ship's route is the same as described above. Figure 1 The process shown is similar, so I will not repeat it here.

[0142] In some embodiments of this specification, the greedy algorithm described above is an approximate algorithm for solving the 1-NKP problem. In each iteration, this greedy algorithm selects the coordinates of the neighborhood of the Z set that have the smallest resistance-to-distance ratio and satisfy the knapsack capacity constraint, and places them into the knapsack. Specifically, as follows... Figure 2 As shown, Figure 2 This is a schematic diagram of the process of solving a ship route planning model based on 1-NKP using a greedy algorithm, as provided in this specification. The specific process is as follows: (1) to (9):

[0143] (1) Use the ship's current position coordinates as the initial coordinate point. And store it in the backpack collection. If we obtain the initial knapsack set, then ,Right now Figure 2 The phrase "store the initial coordinates into the initial knapsack set" appears in the text.

[0144] (2) Based on the above formulas (13), (14), and (15), calculate the total navigation resistance, total navigation distance, and remaining capacity of the initial knapsack set for all coordinate points, respectively. , and ,Right now Figure 2 The text refers to "calculating the total resistance, total distance traveled, and remaining capacity of the initial knapsack set";

[0145] (3) Based on undirected connected graphs (i.e., the above) (or, the navigation area), determine the neighborhood coordinates of all coordinate points in the initial knapsack set and store them in the candidate set. ,Right now Figure 2 The phrase "search the neighborhood of the initial knapsack set and store the coordinates of the neighborhood points into the candidate set" is relevant.

[0146] (4) Calculate the candidate set Resistance to range ratio at each coordinate point ,Right now Figure 2 The phrase "Calculate the resistance-to-distance ratio of each coordinate point in the candidate set" is included.

[0147] (5) Determine whether there are coordinate points that meet the filtering conditions. If they do, continue to the following step (6). If they do not, proceed to the following step (8).

[0148] (6) If there exists only one coordinate point that satisfies the filtering criteria, then the coordinate point that satisfies the filtering criteria shall be taken as the candidate coordinate point. If multiple coordinate points satisfy the filtering criteria, it means that multiple [conditions exist]. Equal coordinate points can be used to compare the navigation resistance (i.e., ...) among multiple coordinate points that meet the screening criteria. The smallest coordinate point is selected as the candidate coordinate point. Candidate coordinate points Store the contents into the initial knapsack set to obtain the first knapsack set. ,Right now Figure 2 The phrase "store the candidate coordinates into the initial knapsack set to obtain the first knapsack set" is included.

[0149] (7) Determine whether the remaining capacity of the first knapsack set meets the termination condition. If the termination condition is not met, the first knapsack set is used as the initial knapsack set again, and the process returns to step (2) above. If the termination condition is met, the following step (8) is executed.

[0150] (8) Calculate the current knapsack set according to the above formulas (13) and (14). (The first knapsack set or the initial knapsack set) and ,Right now Figure 2 The function is to "calculate the total resistance and total distance traveled for the current backpack set".

[0151] (9) Exit the loop, current knapsack set The coordinates in the above step (8) are the coordinates selected by the greedy algorithm to be placed in the knapsack. and Knapsack sets The sum of the resistance and the sum of the flight distance at all coordinate points, i.e. Figure 2The function is to "exit the loop and output the current backpack set, total navigation resistance, and total navigation distance".

[0152] In some embodiments of this specification, taking a 19×19 grid navigation area as an example, based on the Beaufort scale (i.e., Table 1) and meteorological data used for testing, a drag coefficient matrix corresponding to the 19×19 grid navigation area can be constructed (the matrix shown in Formula 17 above). The additional drag coefficient for prohibited navigation areas or inaccessible paths across grids is set to ∞; the additional drag coefficient for calm waters (Beaufort scale 0-2) is 0-0.2; for medium wave areas (Beaufort scale 4-5) it is 0.2-0.3; and for long wave areas (Beaufort scale 6-7) it is greater than 0.3. The variables (parameters) in the 1-NKP and ship route planning models are mapped, and the ship route planning model is solved using a greedy algorithm to obtain the route planning based on the greedy algorithm, i.e., the potential route. A specific route planning diagram can be seen as follows: Figure 3 As shown, Figure 3 This is a route planning diagram based on a greedy algorithm provided in this specification. Figure 3 In this context, A and B represent the starting point and ending point of the route planning, i.e., the ship's current position and target position, respectively. Figure 3 The different colored grids in the diagram correspond to different sea states or different ranges of additional drag coefficients. Figure 3 In the diagram, green indicates an additional drag coefficient of 0-0.2, yellow indicates an additional drag coefficient of 0.2-0.3, red indicates an additional drag coefficient >0.3, and blue areas correspond to obstacles / restricted areas / inaccessible areas. The above potential routes can be considered as test results, as shown in Table 2 below. Table 2 shows the route planning results (i.e., test results).

[0153] Table 2

[0154]

[0155] In Table 2 above, Route A has a total drag of 0.68 and a range of 150.3 nm, accounting for 82% of its path in the low-drag Beaufort class 0-4 region. Route B's total drag increases to 1.23, and its range increases by 5.4 nm to 155.7 nm. Route C's total drag reaches 1.57, and its range increases to 159.5 nm. In summary, Route A saves 44.7% in total drag compared to Route B, and 56.1% compared to Route C, while shortening the range by 5.8%, achieving a triple optimization of "low drag, short distance, and rapid response," fully meeting the actual needs of ships to cope with sudden changes in sea state.

[0156] The above description is merely an embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for ship route planning based on meteorological data, characterized in that, The method includes: S1: Data Acquisition: When the ship's navigation environment changes, acquire meteorological data and operational status data of the ship's navigation area; the navigation area is an undirected connected graph composed of multiple coordinate points, and the multiple coordinate points are between the ship's current position coordinates and target position coordinates; S2: Constructing the drag coefficient matrix: Based on the meteorological data and the operational status data, a pre-constructed drag coefficient calculation model is used to determine the additional drag coefficient corresponding to each coordinate point and construct a drag coefficient matrix. S3: Constructing a Ship Route Planning Model: Based on the resistance coefficient matrix and the navigation area, construct a ship route planning model based on 1-NKP. The optimization objective of the ship route planning model is: under given constraints, solve for the sum of the products of the navigation resistance of all coordinate points in the undirected connected graph and the state of the corresponding coordinate points as the total resistance, and find the minimum value of the total resistance. The minimum value is: （1） Among them, the The number of coordinate points, the Represents coordinate points The navigation resistance, the Represents the coordinate point The state; S4: Route planning: Based on the ship route planning model, a greedy algorithm is used to determine the potential route of the ship.

2. The ship route planning method based on meteorological data as described in claim 1, characterized in that, The meteorological data includes wind speed and wave height; the operational status data includes basic parameters, drag-related parameters, and operational parameters. The drag-related parameters include seawater density, air density, seawater drag coefficient, and air drag coefficient. The basic parameters include the resistance of the vessel when sailing in still water, the characteristic length of the vessel, its projected area above the waterline, and its width. The operational parameters include the vessel's speed in still water.

3. The ship route planning method based on meteorological data as described in claim 2, characterized in that, The drag coefficient calculation model in S2 is as follows: （2） （3） （4） Among them, the The additional drag coefficient, the The resistance of the vessel when it is sailing in still water, the Let t be the additional resistance of the wave on the ship at time t. The additional resistance of the wind to the ship at time t is... The feature length is the length of the feature. The height of the wave at time t represents the height of the wave at that time. Represents gravitational acceleration, the The density of the seawater, For the air density, the and stated These are the projected area and width of the vessel above the waterline, respectively. and stated These are the seawater drag coefficient and the air drag coefficient, respectively. Let be the wavelength of the wave at time t. Let be the angle between the wave and the ship at time t. This indicates that the seawater drag coefficient is affected by both the wavelength and the incident direction. Let t be the speed of the ship in still water at time t. Let be the wind speed at time t.

4. The ship route planning method based on meteorological data as described in claim 1, characterized in that, The method for constructing the ship route planning model based on 1-NKP in S3 is as follows: Each coordinate point is taken as a vertex of the graph structure corresponding to 1-NKP. The navigation resistance of each coordinate point is set as the vertex cost of 1-NKP. The navigation distance between adjacent coordinate points is set as the vertex weight of 1-NKP. The maximum navigation distance of the ship is limited to the total backpack capacity of 1-NKP. The problem of minimizing the sum of the products of the navigation resistance and the state of the coordinate point is transformed into the optimal solution problem of 1-NKP with capacity constraints. The navigation resistance is positively correlated with the additional resistance coefficient.

5. The ship route planning method based on meteorological data as described in claim 4, characterized in that, The given constraints of the 1-NKP-based route planning model in S3 include: （5） Among them, the Indicates to coordinate point The sailing distance, the This indicates the maximum sailing distance, the Represents coordinate points The state of the coordinate point The coordinate point The neighborhood coordinates of the points, Indicates the coordinate point The set of directly connected adjacent coordinate points, Describes the knapsack set, the Indicates the With the The intersection, the Represents the set of coordinate points, the This indicates the current position coordinates of the vessel.

6. The ship route planning method based on meteorological data as described in claim 1, characterized in that, S4 specifically includes: S41: Use the current position coordinates of the ship as the initial coordinate point and store them in the knapsack set to obtain the initial knapsack set; S42: Determine the total sailing distance and total sailing resistance of all coordinate points in the initial knapsack set, and determine the remaining capacity of the initial knapsack set based on the maximum sailing distance and the total sailing distance; S43: Based on the undirected connected graph, determine the neighborhood coordinates of all coordinate points in the initial knapsack set and store them in the candidate set; S44: Calculate the resistance-to-distance ratio of each coordinate point in the candidate set, and determine whether there are any coordinate points that meet the preset screening conditions; the screening conditions are that the resistance-to-distance ratio is the smallest and the sailing distance does not exceed the remaining capacity; S45: If they exist, the coordinate points that meet the filtering conditions are taken as candidate coordinate points and stored in the initial knapsack set to obtain the first knapsack set; S46: Determine whether the remaining capacity of the first knapsack set meets the preset termination condition; S47: If the termination condition is not met, the first knapsack set is used as the initial knapsack set again, and S42~S47 are repeated until the remaining capacity of the first knapsack set meets the termination condition. Based on the coordinate points in the first knapsack set, the potential route of the ship is generated.

7. The ship route planning method based on meteorological data as described in claim 6, characterized in that, Specifically, S45 includes: If there is only one coordinate point that satisfies the filtering conditions, then the coordinate point that satisfies the filtering conditions is taken as a candidate coordinate point and stored in the initial knapsack set to obtain the first knapsack set. If there are multiple coordinate points that meet the filtering conditions, the coordinate point with the least sailing resistance among the multiple coordinate points that meet the filtering conditions is selected as the candidate coordinate point and stored in the initial backpack set to obtain the first backpack set. If no coordinate point meets the filtering criteria, then the potential route of the ship is generated based on the coordinate points in the initial knapsack set.

8. The ship route planning method based on meteorological data as described in claim 6, characterized in that, The method further includes: If the termination condition is met, the total sailing distance and total sailing resistance of all coordinate points in the first backpack set are determined, and the potential route of the ship is generated based on the coordinate points in the first backpack set.

9. The ship route planning method based on meteorological data as described in claim 1, characterized in that, The method for determining the potential route in S4 is as follows: Based on the ship route planning model, a greedy algorithm is used to solve for routes that satisfy the given constraints, which are then used as candidate routes. Based on the drag coefficient matrix, the cumulative additional drag coefficient of the candidate route is calculated; The candidate route with the lowest cumulative additional resistance coefficient is selected as the potential route of the vessel.

10. The ship route planning method based on meteorological data as described in claim 1, characterized in that, The method for obtaining the meteorological data in S1 is as follows: When the ship's navigation environment changes, environmental data of the ship's navigation area is collected; When the environmental data includes only one meteorological factor, the wind speed and wave height of the navigation area are determined as meteorological data based on the Beaufort scale and the meteorological factor. The Beaufort scale includes the correspondence between Beaufort wind level, wind speed, wave height and sea state information. The meteorological factor is the wind speed, the wave height or the sea state information.

11. The ship route planning method based on meteorological data as described in claim 1, characterized in that, The method further includes: During the navigation along the potential route, the meteorological data corresponding to the coordinates of the points not reached along the potential route are monitored in real time. When changes in the meteorological data of the coordinate points are detected, the meteorological data of all coordinate points between the current position coordinates of the ship and the target position coordinates are reacquired, and the ship's route is replanned based on the acquired meteorological data.

12. The ship route planning method based on meteorological data as described in claim 6, characterized in that, The termination condition in S46 is: the remaining capacity of the first backpack set is not less than the minimum travel distance corresponding to the neighboring coordinates of the candidate coordinate point.

Images