Ship route speed optimization method and system, ship navigation device and medium

Abstract

The invention discloses a ship route speed optimization method and system, a ship navigation device and a medium, and belongs to the technical field of ship intelligent sailing, and the method comprises the steps: obtaining multi-source data related to the sailing environment of a ship, and constructing an environment model at each sampling moment in the sailing process; initializing node attributes of a starting point and a terminal point of ship navigation based on preset navigation parameters; determining a current node of the ship at the current moment and a corresponding node attribute based on the environment model at the current moment and the node attribute of the starting point; constructing a target function based on the starting point, the ending point and the node attributes of the current node; and on the basis of the environment model at each sampling moment in the navigation process, carrying out route and navigational speed collaborative optimization on the target function, and determining an optimal route and an optimal navigational speed at each node on the optimal route. The algorithm searching efficiency can be greatly improved, and the planning result can better meet the actual operation requirement of the ship under the condition that meteorological data and navigational speed dynamic adjustment are considered in the whole process.

Description

Technical Field

[0001] This application relates to the field of intelligent navigation technology for ships, specifically to a method, system, navigation device, and medium for optimizing ship routes and speeds. Background Technology

[0002] Currently, in the field of route planning, the main methods applied to ship route planning include graph search algorithms, such as the traditional A* search algorithm, Dijkstra's algorithm, and Jump Point Search (JPS) algorithm, as well as swarm intelligence optimization algorithms, such as particle swarm optimization, ant colony optimization, and genetic algorithms. In comparison, graph search algorithms, because they do not rely on complex parameter adjustments and can perform deterministic searches based on preset objectives, demonstrate advantages in ship navigation path planning, namely clear theory and simple process.

[0003] The traditional A-Star search algorithm combines the completeness of the Dijkstra algorithm with the heuristics of best-priority search, and is considered an effective method for path optimization in static environments. However, in highly complex navigation environments and rapidly changing weather conditions, the global search strategy of the traditional A-Star search algorithm leads to a surge in computation, resulting in poor timeliness of route planning. Summary of the Invention

[0004] This invention provides a method, system, navigation device, and medium for optimizing ship routes and speeds, aiming to solve the problem of poor timeliness in related route planning.

[0005] Firstly, a method for optimizing ship route and speed is provided, including the following steps: Acquire multi-source data related to the ship's navigation environment and construct environmental models at various sampling times during the navigation process; Based on preset navigation parameters, initialize the node attributes of the starting point and ending point of the ship's navigation. The node attributes include at least position, speed, and time. Based on the environmental model at the current moment and the node attributes of the starting point, determine the current node and corresponding node attributes of the ship at the current moment; Based on the starting point, the ending point, and the node attributes of the current node, construct the objective function; Based on the environmental model at each sampling moment during the navigation process, the objective function is optimized by coordinating route and speed to determine the optimal route and the optimal speed at each node on the optimal route.

[0006] In some embodiments, acquiring multi-source data related to the ship's navigation environment and constructing an environmental model at each sampling time during the navigation process includes: The navigation area is determined based on the starting and ending points of the ship's voyage; Real-time acquisition of multi-source data related to the environment of the navigation area, including at least wind speed data and draft depth data; The multi-source data is preprocessed to obtain preprocessed multi-source data; Based on preset wind speed thresholds and preset draft depth thresholds, the preprocessed multi-source data is rasterized to construct an environmental model at each sampling time during the navigation process.

[0007] In some embodiments, the preprocessing of the multi-source data to obtain preprocessed multi-source data includes: The multi-source data is resampled, longitude copied, and binarized to obtain preprocessed multi-source data.

[0008] In some embodiments, determining the current node and corresponding node attributes of the ship at the current moment based on the environmental model at the current time and the node attributes of the starting point includes: Based on the grid in the environment model at the current moment, determine several neighboring nodes of the starting point; Based on the environmental model at the current moment, the neighboring nodes are filtered to determine the current node where the ship is located at the current moment and the corresponding node attributes.

[0009] In some embodiments, constructing the objective function based on the starting point, the ending point, and the node attributes of the current node includes: Based on the node attributes of the starting point, the ending point, and the current node, calculate the first cumulative fuel consumption and the first cumulative distance from the starting point to the current node, and the second cumulative fuel consumption and the second cumulative distance from the current node to the ending point; Based on the first cumulative fuel consumption and the first cumulative mileage, a cost function is constructed; Based on the second cumulative fuel consumption and the second cumulative range, a heuristic function is constructed; Based on the cost function and the heuristic function, construct the objective function.

[0010] In some embodiments, the step of performing route and speed co-optimization on the objective function based on the environmental model at each sampling time during the navigation process, and determining the optimal route and the optimal speed at each node on the optimal route, includes: Based on the environmental model at each sampling moment during the navigation process, the objective function is optimized by coordinating route and speed, and the position and direction of movement of the current node are updated. The collaborative optimization steps are repeated, and the position and movement direction of the current node are iteratively updated by dynamically adjusting the search area and pruning search direction until the preset termination condition is met, so as to determine the optimal route and the optimal speed at each node on the optimal route.

[0011] In some embodiments, the dynamic adjustment of the search area refers to gradually narrowing the search range as the navigation progresses. The search range is defined by a grid area based on the positional relationship between the current node and the destination.

[0012] In some embodiments, the step of determining the pruning search direction includes: Based on the current environment model and the current node, several possible directions of movement are determined. Calculate the angle difference between the angle corresponding to each movable direction and the angle from the current node to the endpoint; The movement direction of the current node is updated based on the fact that the absolute value of the angle difference is less than a preset angle.

[0013] In some embodiments, the navigation parameters include an optimized speed range and a desired travel time; The speed optimization range is the interval from the minimum speed to the maximum speed. The minimum speed is determined based on the estimated distance from the current node to the destination and the expected remaining time. The expected remaining time is determined based on the expected travel time and the travel time already traveled.

[0014] Secondly, a ship route and speed optimization system is also provided, including: The environment model building module is used to acquire multi-source data related to the ship's navigation environment and build an environment model at each sampling time during the navigation process. The node initialization module is used to initialize the node attributes of the starting point and ending point of the ship's navigation based on preset navigation parameters. The node attributes include at least position, speed, and time. The current node determination module is used to determine the current node and corresponding node attributes of the ship at the current moment based on the environmental model at the current moment and the node attributes of the starting point. The objective function construction module is used to construct an objective function based on the starting point, the ending point, and the node attributes of the current node; The optimization module is used to perform route and speed optimization on the objective function based on the environmental model at each sampling time during the navigation process, and to determine the optimal route and the optimal speed at each node on the optimal route.

[0015] Thirdly, a ship navigation device is also provided, including a memory and a processor, wherein the memory stores a computer program, which, when executed by the processor, implements the steps of any of the above methods.

[0016] Fourthly, a computer-readable storage medium is also provided, on which a computer program is stored, the computer program being loaded by a processor to perform the steps of any of the methods described above.

[0017] Beneficial effects: This application constructs a dynamic environment model by integrating multi-source meteorological and water depth data, accurately initializes node attributes and determines the current node state, and can adapt to the time-varying marine environment in real time, effectively improving the ship's ability to avoid adverse conditions such as large waves and shallow waters, and ensuring navigation safety. By iteratively optimizing the constructed objective function, the algorithm search efficiency can be greatly improved in complex environments, thereby improving the timeliness of route and speed planning. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a simplified flowchart of the ship route and speed optimization method provided by an exemplary embodiment of this disclosure; Figure 2 This is a schematic diagram of the overall process of the ship route and speed optimization method provided by the exemplary embodiments of this disclosure; Figure 3 This is a flowchart illustrating the environment model construction process provided in an exemplary embodiment of this disclosure; Figure 4 This is a schematic diagram of the meteorological data preprocessing process provided by an exemplary embodiment of this disclosure; Figure 5 This is an environmental model and navigation area adjustment diagram provided by an exemplary embodiment of this disclosure; Figure 6 This is a flowchart of the search direction pruning process provided in an exemplary embodiment of this disclosure; Figure 7 This is a flowchart of the movable direction selection process in the search direction pruning provided by an exemplary embodiment of this disclosure; Figure 8 This is a schematic diagram illustrating the search direction determination provided by an exemplary embodiment of this disclosure; Figure 9This is a graph showing the route optimization results provided by an exemplary embodiment of this disclosure; Figure 10 This is a graph showing the speed optimization results provided by an exemplary embodiment of this disclosure; Figure 11 This is a schematic diagram of the functional modules of the ship route and speed optimization system provided in an exemplary embodiment of this disclosure; Figure 12 This is a schematic diagram of the structure of a ship navigation device provided in an exemplary embodiment of this disclosure. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0022] "A and / or B" includes the following three combinations: A only, B only, and a combination of A and B.

[0023] The use of "applies to" or "configured to" in this application implies open and inclusive language, which does not exclude the applicability to or configuration to devices performing additional tasks or steps. Additionally, the use of "based on" implies openness and inclusivity, because processes, steps, calculations, or other actions "based on" one or more of the stated conditions or values ​​may in practice be based on additional conditions or values ​​beyond those stated.

[0024] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0025] In situations where the navigation environment is too complex and weather conditions change rapidly, the global search strategy of the traditional A-star search algorithm will lead to a surge in computational load, resulting in poor timeliness of route planning.

[0026] On the one hand, this embodiment provides a method for optimizing ship route and speed, such as Figure 1 and Figure 2 As shown, it includes the following steps: Step 100: Acquire multi-source data related to the ship's navigation environment and construct an environmental model at each sampling time during the navigation process.

[0027] Specifically, multi-source navigation environment data within the navigating sea area is acquired, including at least meteorological and hydrological forecast data and sea depth data. The meteorological and hydrological forecast data includes wind speed and wave height data for different areas. The navigating sea area is rasterized to obtain multiple environmental grids. Navigation thresholds for wind speed and draft are set based on the vessel's draft, maximum navigable wind speed, and search accuracy requirements. Based on these thresholds, the meteorological and hydrological forecast data and ocean depth data within each environmental grid are binarized to determine navigable and non-navigable areas. Finally, the navigable and non-navigable area data from different times are integrated chronologically to construct a three-dimensional rasterized environment model for each sampling time, accurately reflecting the meteorological and water depth conditions of the navigation area at each moment.

[0028] Step 200: Based on preset navigation parameters, initialize the node attributes of the starting point and ending point of the ship's navigation. The node attributes include at least position, speed, and time.

[0029] Specifically, navigation parameters are preset, including but not limited to the speed optimization range and the expected navigation time. The speed optimization range refers to the interval between the minimum and maximum navigation speeds of the ship; the minimum navigation speed is calculated using the estimated distance from the ship's current position (i.e., the current node) to the destination and the expected remaining time; the expected remaining time is the difference between the preset expected navigation time and the time the ship has already traveled.

[0030] Based on the above navigation parameters, the node attributes of the ship's starting and ending points are initialized. These node attributes include at least the position coordinates of the starting and ending points, the ship's speed, and the corresponding time, all attributes related to the navigation. In this embodiment, the starting time is set as the navigation start time, and the ending time is set as the desired arrival time.

[0031] Step 300: Based on the current environment model and the node attributes of the starting point, determine the current node and corresponding node attributes of the ship at the current moment.

[0032] Specifically, the environmental model corresponding to the current sampling time is dynamically retrieved to clarify the navigable status, meteorological conditions, and water depth data of each area at the current time. Combining the node attributes of the initial starting point, the ship's specific position at the current time is determined by tracking the ship's navigation process in real time, and this position is taken as the current node. Based on the environmental model at the current time, the environmental grid area that meets the navigation requirements such as wind speed and water depth at the current time is identified. Then, based on the ship's navigation status, the environmental grid that meets the navigation requirements is filtered to determine the ship's current node at the current time, as well as the node attributes corresponding to the current node, including the position coordinates of the current node, the actual speed at the current time, the cumulative navigation time from the starting point to the current node, and other navigation-related attributes, to ensure that the current node data matches the real-time navigation status and environmental conditions.

[0033] Step 400: Construct the objective function based on the starting point, ending point, and the node attributes of the current node.

[0034] Specifically, in the construction process, based on the node attributes of the starting point, current node, and ending point, and combined with navigation optimization requirements, a fuel consumption model is introduced into the traditional A-Star search algorithm. By adding fuel consumption-related attributes to the node attributes, the cumulative fuel consumption and cumulative distance from the starting point to the current node, and the estimated remaining fuel consumption and estimated remaining distance from the current node to the ending point are calculated. A cost function is constructed using the cumulative fuel consumption and cumulative distance, and a heuristic function is calculated using the estimated remaining fuel consumption and estimated remaining distance. This improves the traditional A-Star search algorithm, and the objective function is constructed by combining the cost function and the heuristic function. It is evident that the objective function constructed using the improved A-Star search algorithm in this embodiment can support a single optimization objective or a composite optimization objective. The single optimization objective is the lowest fuel consumption or the shortest distance, while the composite optimization objective is the optimal result of a weighted combination of fuel consumption and distance.

[0035] Step 500: Based on the environmental model at each sampling time during the navigation process, perform joint optimization of the objective function for route and speed to determine the optimal route and the optimal speed at each node on the optimal route.

[0036] Specifically, based on the improved A-satellite search algorithm and combined with the environmental model at each sampling moment during the flight process, the route and speed are optimized collaboratively. During the optimization process, the algorithm adapts to the changes in the environmental model at different times by expanding the speed and time attributes of the nodes. It uses the constructed objective function to calculate the cost value corresponding to each candidate node and prioritizes the node with the best cost as the next flight node. This optimization process is repeated throughout the entire flight process, iteratively updating the node attributes such as the position and direction of movement of the current node at different times, until the meteorological data traversal is completed, the current starting point coincides with the new starting point, or the destination is reached. Finally, the optimal route consisting of a series of nodes is determined, as well as the speed attribute bound to each node on the route, i.e., the optimal speed of each node.

[0037] In this embodiment, a dynamic environment model is constructed by integrating multi-source meteorological and water depth data. The node attributes are accurately initialized and the current node status is determined. This model can adapt to the time-varying marine environment in real time, effectively improving the ship's ability to avoid adverse conditions such as high winds and waves and shallow waters, thus ensuring navigation safety. By iteratively optimizing the constructed objective function, the algorithm's search efficiency can be greatly improved in complex environments, thereby improving the timeliness of route and speed planning. Furthermore, by taking into account both meteorological data and dynamic speed adjustment throughout the entire process, the planning results can better meet the actual operational needs of the ship.

[0038] In some embodiments, step 100 involves acquiring multi-source data related to the ship's navigation environment and constructing an environmental model at each sampling time point during the navigation process, including: Step 110: Determine the navigation area based on the starting and ending points of the ship's voyage.

[0039] Specifically, based on the coordinates of the ship's starting point and ending point, and combined with the ship's pre-planned navigation route, the navigation sea area covering the entire journey from the starting point to the ending point is delineated through coordinate positioning. This ensures that the navigation sea area includes all potential areas that the ship may pass through during its journey from the starting point to the ending point, while also taking into account the continuity of the sea area in the global navigation scenario. This allows environmental data collection and model building to fully cover the entire geographical range of the ship's navigation.

[0040] Step 120: Acquire multi-source data related to the environment of the navigation area in real time. The multi-source data shall include at least wind speed data and draft depth data.

[0041] Specifically, it collects multi-source data related to the ship's navigation environment in real time, including at least meteorological data such as wind speed data and water depth data, covering the environmental conditions at various key time points during the navigation process. Among them, wind speed data includes north-south wind speed, east-west wind speed at a preset height (e.g., 10 meters above the ship's height), and wave height data in different areas within the navigation area.

[0042] Step 130: Preprocess the multi-source data to obtain preprocessed multi-source data.

[0043] Specifically, the collected multi-source data undergoes resampling, longitude replication (east and west), and binarization sequentially to obtain preprocessed multi-source data. The resampling operation addresses the differences in grid precision among different data sources. For example, water depth data differs from wind speed and wave height data in initial grid precision; upsampling or downsampling is used to unify the grid precision of all data to a preset standard, ensuring data format consistency. The longitude replication operation addresses global navigation scenarios. Since 180°E and 180°W represent the same geographical location, to avoid coordinate breaks during route planning, the collected meteorological data is replicated and stitched along the east and west longitude directions, ensuring the ship's accessibility within the stitched coordinate area. The binarization process, combined with the ship's own performance parameters and based on preset navigability standards, marks areas meeting navigation requirements as navigable points and areas failing to meet navigation requirements (such as excessive wind speed or shallow water) as unnavigable points, thus differentiating the navigation feasibility of different areas.

[0044] Step 140: Based on the preset wind speed threshold and preset draft depth threshold, perform rasterization on the preprocessed multi-source data to construct an environmental model at each sampling time during the navigation process.

[0045] Specifically, based on the ship's design parameters and navigation safety requirements, as well as the ship's maximum supportable wind speed and draft, preset wind speed thresholds and preset water depth thresholds are established. Based on these preset thresholds, the pre-processed multi-source data is rasterized, dividing the navigation area into several raster cells with uniform grid precision. Each raster cell is labeled with its corresponding wind speed, water depth information, navigability status, and navigability or non-navigability indicators according to the pre-processed data. Then, according to each sampling moment during the navigation process, the rasterized data from each sampling moment are integrated to construct a three-dimensional environmental model for each sampling moment, accurately reflecting the environmental conditions of each raster within the navigation area at different time points, thus achieving dynamic updates of the environmental status.

[0046] As an exemplary example, such as Figure 3 As shown, the grid precision of the environmental model is set to C. The original meteorological data and water depth data are processed in parallel. For meteorological data with a grid precision lower than C, it is upsampled to C precision to obtain meteorological data _up. After copying to east and west longitudes, meteorological data _splice is obtained. Then, a preset wind speed threshold is used to filter the meteorological data _splice to obtain meteorological data _obstacles at different sampling times such as T, 2T, ..., pT, where p represents the total number of sampling times. For water depth data with an original precision of b (which may be higher or lower than C), if the original precision b is less than the grid precision C, it is upsampled to C precision to obtain water depth data _up. If the original precision b is greater than the grid precision C, it is downsampled to C precision to obtain water depth data _down. After copying to east and west longitudes, water depth data _splice is obtained. Then, a preset water depth threshold is used to filter the water depth data _splice to obtain water depth data _obstacles. Then, in a unified grid coordinate system, the dynamic meteorological conditions at each sampling moment are fused with the static water depth information in chronological order to generate a dynamic environment model consisting of a series of consecutive moments.

[0047] like Figure 4 The diagram shown illustrates the meteorological data preprocessing process. Figure 4 In the diagram, (a) represents a portion of the navigation area after binarization of the environmental grid, where grids A and F represent non-navigable points, and grids B-E and G-I represent navigable points. Figure 4 (b) in the image is the environmental grid obtained after upsampling the environmental grid in (a). The first grid A in the first row, counting from the left, represents the position 180° West longitude, the first grid B represents 0°, and the second grid C represents the position 180° East longitude. Figure 4(c) is the environmental grid obtained by copying the original environmental grid in (a) with east and west longitudes, so that 180° west longitude and 180° east longitude coincide, in order to ensure the continuity of the navigation area in the east-west longitude direction.

[0048] like Figure 5 The environmental model diagram shown has black and green irregular areas. The black irregular areas represent areas with shallow water, indicating the presence of water depth obstacles; the green irregular areas represent areas with excessive wind speed, indicating the presence of wind speed meteorological obstacles.

[0049] In this embodiment, by accurately delineating navigation areas, acquiring key environmental data in real time, preprocessing multi-source information, and constructing a rasterized dynamic environmental model, the system ensures the targeted nature of environmental data collection by clearly defining geographical boundaries, unifies data formats through resampling and longitude replication to guarantee global navigation accessibility, and clearly distinguishes navigable and non-navigable areas through binarization and rasterization processing, effectively avoiding navigation risks such as excessive wind speed and shallow water. At the same time, the dynamic model updates at each sampling time can adapt to changes in the marine environment in real time, which helps to significantly improve the accuracy and reliability of the subsequent optimization process.

[0050] In some embodiments, step 300, based on the environmental model at the current moment and the node attributes of the starting point, determines the current node and corresponding node attributes of the ship at the current moment, including: Step 310: Based on the grid in the environment model at the current moment, determine several neighboring nodes of the starting point.

[0051] Specifically, the system dynamically retrieves the current three-dimensional rasterized environment model and clarifies the raster position corresponding to the ship's starting point in the model. Based on the node movement rules of the improved A-Star search algorithm, it traverses all possible movement directions around the starting point raster, including horizontal, vertical, and diagonal directions, and filters out all raster adjacent to the starting point raster in each possible movement direction. Each adjacent raster is considered as a potential neighboring node of the starting point. At the same time, each potential neighboring node is initially assigned attributes such as position coordinates, preset candidate speeds, and estimated time from the starting point to the node.

[0052] Step 320: Based on the environmental model at the current moment, filter the neighboring nodes to determine the current node where the ship is located at the current moment and the corresponding node attributes.

[0053] Specifically, based on the grid attributes in the current environmental model, potential neighboring nodes are screened one by one. First, nodes in non-navigable areas are excluded, that is, neighboring nodes corresponding to grids with wind speeds exceeding a preset wind speed threshold or water depths below a preset water depth threshold are removed. Then, further screening is carried out through search direction pruning logic. The difference between the movement direction angle corresponding to each potential neighboring node and the angle from the starting point to the ending point is calculated. Nodes that meet the priority search direction requirements are retained as current nodes, and the position coordinates, speed, and cumulative travel time from the starting point to the current node are determined. These are used as the first intermediate node for constructing the route in the first round of navigation planning.

[0054] For example, longitude and latitude can be used to represent the current node. Position coordinates ,as follows: (1); in, This indicates the mesh accuracy of the environmental model. Indicates the longitude of the node. Indicates the latitude of the node.

[0055] In this embodiment, by first determining all potential neighboring nodes centered on the current node and then filtering effective nodes in combination with the environment model, the integrity of route optimization can be ensured by fully covering all feasible paths in the surrounding area, and the redundant computation can be reduced by eliminating nodes in unnavigable areas and pruning invalid movement directions, thereby improving the algorithm's search efficiency.

[0056] As a preferred example, considering that sailing speed is a key factor affecting fuel consumption and range during navigation, and under the premise of meeting navigation time requirements and safe navigation, this example sets the sailing speed at each node of the entire journey as follows: Within the range, that is: (2); in, Indicates from minimum sailing speed To maximum sailing speed , interval is The speed vector represents the speed of each node. The speed of each node falls within the speed range represented by this speed vector, where the minimum speed... The expression is as follows: (3); in, For the current node The estimated distance to the destination. This represents the expected remaining time. It's worth noting the minimum speed. It will be continuously adjusted and optimized during the objective function optimization process to better adapt to the environmental model at different times, and to meet the requirements of navigation time and safe navigation.

[0057] In some embodiments, step 400 involves constructing an objective function based on the node attributes of the start point, the end point, and the current node, including: Step 410: Based on the node attributes of the starting point, the ending point, and the current node, calculate the first cumulative fuel consumption and the first cumulative distance from the starting point to the current node, and the second cumulative fuel consumption and the second cumulative distance from the current node to the ending point.

[0058] Specifically, by combining the node attributes of the starting point, the ending point, and the current node, and referring to the current node's speed, travel time, and meteorological data such as wind speed and wave height, as well as water depth conditions in the environmental model at the current moment, the first cumulative fuel consumption and the first cumulative voyage from the starting point to the current node are calculated respectively. Based on the estimated voyage from the current node to the ending point, the ending point's location attributes, and the environmental model predictions at each sampling moment in the subsequent voyage process, the estimated total fuel consumption and estimated total voyage required for this remaining voyage are estimated, thus obtaining the second cumulative fuel consumption and the second cumulative voyage from the current node to the ending point.

[0059] Step 420: Construct a cost function based on the first cumulative fuel consumption and the first cumulative range.

[0060] Specifically, when the optimization objective is to minimize fuel consumption, the first cumulative fuel consumption is used as the evaluation index of the cost function; when the optimization objective is to minimize the flight distance, the first cumulative flight distance is used as the evaluation index of the cost function; when the optimization objective is the optimal result of the weighted combination of fuel consumption and flight distance, the maximum and minimum values ​​of the first cumulative fuel consumption and the first cumulative flight distance from the starting point to the current node are first found, and the two types of data are normalized respectively. Then, the normalized fuel consumption and flight distance data are weighted and summed according to the preset weight coefficients to serve as the composite evaluation index of the cost function, reflecting the actual cumulative cost from the starting point to the current node.

[0061] Step 430: Construct a heuristic function based on the second cumulative fuel consumption and the second cumulative range.

[0062] Specifically, based on the second cumulative fuel consumption and the second cumulative range, a heuristic function is constructed to match the optimization objective of the cost function, ensuring consistency in the evaluation logic of both. When the optimization objective is to minimize fuel consumption, the heuristic function uses the second cumulative fuel consumption as the estimated evaluation index; when the optimization objective is to minimize range, the heuristic function uses the second cumulative range as the estimated evaluation index; when the optimization objective is the optimal result of a weighted combination of fuel consumption and range, the second cumulative fuel consumption and the second cumulative range are first normalized, and then weighted and summed according to the same weight coefficients as the cost function to obtain the composite estimated index of the heuristic function, which is used to predict the estimated cost from the current node to the destination.

[0063] Step 440: Construct the objective function based on the cost function and the heuristic function.

[0064] Specifically, a complete objective function is constructed by combining the cost function and the heuristic function. The optimization degree of the current node and its corresponding navigation path is measured by calculating the weighted sum of the cost function value and the heuristic function value. The optimization direction of the objective function is to minimize this comprehensive result, that is, to find the path with the lowest comprehensive cost, thereby achieving coordinated optimization of the ship's route and speed to adapt to navigation needs in different scenarios.

[0065] As an exemplary example, the current node Corresponding cost function Heuristic function and objective function The expressions are as follows: (4); (5); (6); in, Starting point To the current node First cumulative fuel consumption; For the current node To the finish line The second cumulative fuel consumption; Starting point To the current node The first cumulative voyage; Current node To the finish line The second cumulative voyage; and This is a weighting coefficient for fuel consumption and distance, and its value is preferably any value between [1, 5]. and These are indicator bits for fuel consumption and range, respectively. When and When, it means that the optimization objective only considers fuel consumption, when and When, it means that the optimization objective does not consider fuel consumption; when and "At this time" indicates that the optimization objective takes into account both fuel consumption and range.

[0066] For optimization objectives that simultaneously consider fuel consumption and range, in order to eliminate dimensions and unify the comparison scale of fuel consumption and range at different nodes, fuel consumption and range are normalized separately to obtain the results from the starting point. To the current node First cumulative fuel consumption normalized value and the first cumulative range normalized value and from the current node To the finish line Second cumulative fuel consumption normalized value Second cumulative range normalized value ,Right now: (7); (8); (9); (10); in, Indicates starting from the origin To the current node Then go to the neighboring node Fuel consumption between; Indicates starting from the origin To the current node Then go to the neighboring node The distance between; Indicates starting from the origin To the current node Then go to the neighboring node Fuel consumption between; Indicates starting from the origin To the current node Then go to the neighboring node The distance between; , This indicates the number of neighboring nodes of the current node. Each neighboring node has a different navigation direction and speed.

[0067] As can be seen, in this example, the ratio between the difference between the current fuel consumption and the minimum fuel consumption and the total fluctuation range of fuel consumption is used to obtain the relative proportion of the current node's fuel consumption relative to the overall fuel consumption range, which is used to represent the normalized fuel consumption; the ratio between the difference between the current range and the minimum range and the total fluctuation range of range is used to obtain the relative proportion of the current node's range relative to the overall range of range, which is used to represent the normalized range.

[0068] Then, the normalized values ​​of cumulative fuel consumption and cumulative range are substituted into the cost function. Heuristic function Thus, the objective function for the coordinated optimization of fuel consumption and range can be obtained.

[0069] In this embodiment, by accurately calculating cumulative fuel consumption and range data, a cost function and a heuristic function adapted to multiple optimization objectives are constructed, and finally integrated to form a complete objective function. This effectively eliminates the difference in the dimensions of fuel consumption and range, ensures that different optimization objectives participate fairly in the weighted calculation, and avoids a single indicator dominating the optimization result. At the same time, the cost function reflects the actual cost from the starting point to the current node, and the heuristic function predicts the estimated cost from the current node to the destination. The collaboration of the two not only ensures the efficiency of the route and speed optimization process, but also flexibly meets different navigation needs such as minimum fuel consumption, shortest distance, or composite optimization, which can significantly improve the optimality and practicality of the final planning result.

[0070] In some embodiments, step 500, based on the environmental model at each sampling time point during the navigation process, performs joint optimization of the objective function for route and speed to determine the optimal route and the optimal speed at each node on the optimal route, including: Step 510: Based on the environmental model at each sampling moment during the navigation process, optimize the objective function by coordinating the route and speed, and update the position and direction of movement of the current node.

[0071] Specifically, such as Figure 2As shown, initialize the OPEN set and the CLOSE set. The OPEN set is the set of nodes to be visited, representing the nodes that may be explored during the search process and their different speeds. The CLOSE set represents the set of nodes that have been visited, and the neighboring nodes of the current node with the optimal direction and optimal speed will be added to it. The starting point is placed into the OPEN set. If the OPEN set is not empty, the environmental model at each sampling time during the navigation process is used. Based on the node attributes of the current node and the navigable status, weather, and water depth conditions of the grid in the environmental model at each sampling time, candidate speeds are matched for the current node within a preset speed optimization range. The objective function is used to calculate the comprehensive costs of the candidate speeds and potential routes corresponding to different neighboring nodes of the starting point, including fuel consumption and distance. Based on the grid coordinates of the environmental model, the nodes on the routes of each neighboring node at the previous time are found, the parent attributes of each neighboring node are updated, and each neighboring node is added to the OPEN set. The neighboring node with the lowest comprehensive cost is selected and placed into the CLOSE set as the current node. Simultaneously, based on the unobstructed and navigable grid distribution in the environmental model, the optimal movement direction of the current node is determined, and the position of the current node is updated, allowing the current node to migrate along the optimal movement direction to the next compliant grid, completing the node state update after a single collaborative optimization. It's easy to understand that the parent attribute represents the node position at the previous moment on the route where the neighboring node is located, while the current node represents the starting point at the corresponding moment.

[0072] Step 520: Repeat the collaborative optimization steps, dynamically adjust the search area and pruning search direction to iteratively update the position and movement direction of the current node until the preset termination condition is met, and determine the optimal route and the optimal speed at each node on the optimal route.

[0073] Specifically, the collaborative optimization operation in step 510 is repeated, the starting point is continuously updated, and the starting point at each time step is added to the OPEN set. In each iteration, the search area is dynamically adjusted and the search direction is pruned to optimize the optimization efficiency.

[0074] For dynamically adjusted search areas, the search range is defined based on the current node and endpoint after each update, according to a set grid width. As the current node gradually approaches the endpoint, the search area shrinks synchronously, focusing on the core navigation path. The search range is defined by a grid area determined based on the positional relationship between the current node and the endpoint. For example... Figure 5 The diagram shown illustrates the navigation area adjustment process. The starting point corresponding to the navigation node at time T is... The navigation area is We can obtain the route Path1; find the navigation node at time 2T as the new starting point. Based on the new starting point and ending point, the navigation area is obtained. This yields the route Path2. Repeat the above navigation area adjustment operation, gradually decreasing the search area as you approach the destination, until the new starting point stops updating or the starting point becomes the destination, at which point the area adjustment operation stops. Here, black irregular areas represent areas with shallow water, green irregular areas represent areas with excessive wind speed, green squares represent the starting point position at different times (i.e., the current node), and red squares represent the destination position. The navigation area at time T is... The expression is: (11); in, Indicates the starting point longitude index Indicates the end point longitude index Indicates the starting point The latitude index, Indicates the end point The latitude index, It represents the width of the voyage and is also an index value.

[0075] For the pruning search direction, such as Figure 6 As shown, two empty sets are initialized as the preferred set Nei and the candidate set Out; based on the environment model at the current moment and the current node, several movable directions motion are determined; movable directions that have not passed through obstacles in the environment model are taken as potential movable directions; the angle corresponding to each potential movable direction is calculated. Angle from the current node to the destination absolute value of the difference between Directions with an absolute angle difference less than a preset angle (preferably 90°) are added to the preferred set Nei; otherwise, they are added to the candidate set Out. Based on the number of elements in the preferred set Nei, the final movable direction is adaptively determined, and invalid detour directions are eliminated. For example, ... Figure 7 As shown, when the preferred set Nei is empty, the movable direction is selected from the candidate set Out; when the preferred set Nei has only one element, directions from both the preferred set Nei and the candidate set Out can be used as movable directions; when the preferred set Nei has two or more elements, the movable direction is selected from the preferred set Nei. Figure 8 The diagram illustrates the pruning process for the search direction. The two red arrows next to the green box indicate movable directions. The black area represents areas with shallow water. The green squares represent the starting point (i.e., the current node) at different times, and the red squares represent the ending point. If movable directions exist within the area to the upper right of the vertical line perpendicular to the yellow dashed line between the starting and ending points, those directions are prioritized. Figure 8In (a), the two red arrows next to the green box point in the direction of the destination; if there is no movable direction in the area to the upper right of the perpendicular line of the yellow dashed line between the start and end points, select a movable direction in the area to the lower left of the perpendicular line of the yellow dashed line between the start and end points, such as... Figure 8 In (b) of the diagram, the two red arrows next to the green box indicate the direction to detour.

[0076] Following the temporal sequence of sampling moments during the navigation process, the position and direction of movement of the current node are iteratively updated until the OPEN set is empty, the meteorological data has been traversed, the current node's position coincides with the previously updated node's position, or the current node reaches its destination. At this point, iteration stops, and the optimal node positions and corresponding speeds from all iterations are integrated. Finally, the optimal route consisting of a series of nodes is determined, along with the speed attributes bound to each node on this route, i.e., the optimal speed of each node. When the OPEN set is empty, the objective function has no solution, and no path can be found, indicating that all possible starting points have been explored.

[0077] In this embodiment, the improved A* algorithm is combined with a dynamic environment model at each sampling time to perform coordinated optimization of route and speed. By dynamically shrinking the search area and precisely pruning the search direction, the node status is continuously updated iteratively. This not only significantly improves the algorithm's search efficiency in complex marine environments and shortens the planning time to meet actual engineering requirements, but also ensures that the optimization process conforms to time-varying weather and water depth conditions, dynamically matching the optimal speed and navigation direction. The final determined optimal route and optimal speed at each node not only avoid navigation risks such as large waves and shallow waters, but also achieve the goals of minimum fuel consumption, shortest distance, or combined optimization, improving ship navigation efficiency and adapting to different actual operational needs.

[0078] The method described in this application is used to optimize the route speed, resulting in the route speed configuration. Figure 9 The diagram shown is a flight route diagram. The horizontal axis represents the longitude measurement value, and the vertical axis represents the latitude measurement value. Figure 10 As shown Figure 9 A schematic diagram showing the speeds corresponding to the six segments of the route is provided. The results show that the optimized route and speed are very close to the optimal route and speed configuration for each segment of the actual navigation, fully demonstrating the feasibility and effectiveness of the method proposed in this application.

[0079] On the other hand, this embodiment provides a ship route and speed optimization system, such as Figure 11 As shown, it includes: The environmental model building module 1101 is used to acquire multi-source data related to the ship's navigation environment and build environmental models at various sampling times during the navigation process. The node initialization module 1102 is used to initialize the node attributes of the starting point and ending point of the ship's navigation based on preset navigation parameters. The node attributes include at least position, speed and time. The current node determination module 1103 is used to determine the current node and corresponding node attributes of the ship at the current moment based on the environmental model and the node attributes of the starting point at the current moment. The objective function construction module 1104 is used to construct an objective function based on the node attributes of the start point, the end point, and the current node; The optimization module 1105 is used to perform route and speed optimization on the objective function based on the environmental model at each sampling time during the navigation process, and to determine the optimal route and the optimal speed at each node on the optimal route.

[0080] This embodiment also provides a ship navigation device, such as Figure 12 As shown, it includes a memory, a processor, and other hardware and software modules involved in implementing navigation. In a specific example, the memory stores a computer program, which, when executed by the processor, implements the method of any of the above embodiments.

[0081] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, the computer program being loaded by a processor to perform the steps of any of the methods in the above embodiments.

[0082] In the embodiments of this application, the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0083] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0084] The above provides a detailed description of a method, system, navigation device, and medium for optimizing ship routes and speeds, as provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this application. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for optimizing ship route and speed, characterized in that, include: Acquire multi-source data related to the ship's navigation environment and construct environmental models at various sampling times during the navigation process; Based on preset navigation parameters, initialize the node attributes of the starting point and ending point of the ship's navigation. The node attributes include at least position, speed, and time. Based on the environmental model at the current moment and the node attributes of the starting point, determine the current node and corresponding node attributes of the ship at the current moment; Based on the starting point, the ending point, and the node attributes of the current node, construct the objective function; Based on the environmental model at each sampling moment during the navigation process, the objective function is optimized by coordinating route and speed to determine the optimal route and the optimal speed at each node on the optimal route.

2. The method for optimizing ship route and speed according to claim 1, characterized in that, The acquisition of multi-source data related to the ship's navigation environment and the construction of environmental models at various sampling times during the navigation process include: The navigation area is determined based on the starting and ending points of the ship's voyage; Real-time acquisition of multi-source data related to the environment of the navigation area, including at least wind speed data and draft depth data; The multi-source data is preprocessed to obtain preprocessed multi-source data; Based on preset wind speed thresholds and preset draft depth thresholds, the preprocessed multi-source data is rasterized to construct an environmental model at each sampling time during the navigation process.

3. The method for optimizing ship route and speed according to claim 1, characterized in that, The preprocessing of the multi-source data to obtain preprocessed multi-source data includes: The multi-source data is resampled, longitude copied, and binarized to obtain preprocessed multi-source data.

4. The method for optimizing ship route and speed according to claim 2 or 3, characterized in that, The process of determining the current node and corresponding node attributes of the ship at the current moment based on the current environment model and the node attributes of the starting point includes: Based on the grid in the environment model at the current moment, determine several neighboring nodes of the starting point; Based on the environmental model at the current moment, the neighboring nodes are filtered to determine the current node where the ship is located at the current moment and the corresponding node attributes.

5. The method for optimizing ship route and speed according to claim 1, characterized in that, The step of constructing a target function based on the node attributes of the starting point, the ending point, and the current node includes: Based on the node attributes of the starting point, the ending point, and the current node, calculate the first cumulative fuel consumption and the first cumulative distance from the starting point to the current node, and the second cumulative fuel consumption and the second cumulative distance from the current node to the ending point; Based on the first cumulative fuel consumption and the first cumulative mileage, a cost function is constructed; Based on the second cumulative fuel consumption and the second cumulative range, a heuristic function is constructed; Based on the cost function and the heuristic function, construct the objective function.

6. The method for optimizing ship route and speed according to claim 1, characterized in that, The environmental model based on various sampling moments during the navigation process is used to perform coordinated optimization of the objective function for route and speed, determining the optimal route and the optimal speed at each node on the optimal route, including: Based on the environmental model at each sampling moment during the navigation process, the objective function is optimized by coordinating route and speed, and the position and direction of movement of the current node are updated. The collaborative optimization steps are repeated, and the position and movement direction of the current node are iteratively updated by dynamically adjusting the search area and pruning search direction until the preset termination condition is met, so as to determine the optimal route and the optimal speed at each node on the optimal route.

7. The method for optimizing ship route and speed according to claim 6, characterized in that, The dynamically adjusted search area refers to gradually narrowing the search range as the navigation progresses. The search range is defined by a grid area based on the positional relationship between the current node and the destination.

8. The method for optimizing ship route and speed according to claim 6, characterized in that, The steps for determining the pruning search direction include: Based on the current environment model and the current node, several possible directions of movement are determined. Calculate the angle difference between the angle corresponding to each movable direction and the angle from the current node to the endpoint; The movement direction of the current node is updated based on the fact that the absolute value of the angle difference is less than a preset angle.

9. The method for optimizing ship route and speed according to claim 1, characterized in that, The navigation parameters include the optimized speed range and the expected travel time; The speed optimization range is the interval from the minimum speed to the maximum speed. The minimum speed is determined based on the estimated distance from the current node to the destination and the expected remaining time. The expected remaining time is determined based on the expected travel time and the travel time already traveled.

10. A ship route and speed optimization system, characterized in that, include: The environment model building module is used to acquire multi-source data related to the ship's navigation environment and build an environment model at each sampling time during the navigation process. The node initialization module is used to initialize the node attributes of the starting point and ending point of the ship's navigation based on preset navigation parameters. The node attributes include at least position, speed, and time. The current node determination module is used to determine the current node and corresponding node attributes of the ship at the current moment based on the environmental model at the current moment and the node attributes of the starting point. The objective function construction module is used to construct an objective function based on the starting point, the ending point, and the node attributes of the current node; The optimization module is used to perform route and speed optimization on the objective function based on the environmental model at each sampling time during the navigation process, and to determine the optimal route and the optimal speed at each node on the optimal route.

11. A ship navigation device, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, implements the method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, It stores a computer program, which is loaded by a processor to perform the steps of the method according to any one of claims 1-9.

Images