A method and system for path planning of a marine new energy collection and power supply platform

Abstract

The application discloses a kind of ocean new energy collection and power supply platform path planning method and system considering energy collection, it is related to ocean new energy utilization technical field, the method is by grid processing to target sea area, based on wind speed, solar radiation intensity and temperature data Construction time-varying ocean energy distribution map;Subsequently, first by improving A* complete global collision-free path search, then with global path as center Construction dynamic width safety path corridor, local energy optimization is executed in corridor, obstacle avoidance safety and energy collection maximization in navigation are considered;Meanwhile, the dynamic route of target ship is used as search space using particle swarm optimization algorithm, and the maximum total energy storage when multiple platforms arrive at the convergence point is used as the fitness function, and the optimal convergence point is solved autonomously;Finally, the multi-platform cooperative path that meets the time window, obstacle avoidance constraint and total energy optimization is output.The application effectively solves the problems of single target, subjective weight setting and inability to dynamically determine the convergence point in traditional path planning.

Description

Technical Field

[0001] This invention relates to the field of marine new energy utilization technology, and in particular to a method and system for path planning of a marine new energy collection and power supply platform. Background Technology

[0002] With the growth of global energy demand and the increasing awareness of environmental protection, marine renewable energy has become a research hotspot in the energy field due to its abundant reserves and clean, renewable nature. Marine renewable energy collection and power supply platforms, as the core carriers of offshore energy extraction and supply, typically integrate multiple power generation devices such as solar and wind power to provide electricity to offshore equipment. When operating at sea, these platforms need to plan their routes and relocate according to sea conditions, energy distribution, and mission requirements to optimize energy collection efficiency and ensure power supply reliability.

[0003] Against this backdrop, how a power supply platform can plan its navigation path to collect as much renewable energy as possible from the environment as possible on its way to rendezvous with the target vessel (the vessel awaiting resupply), thereby maximizing the energy carried at the rendezvous point, becomes a critical technical problem. Existing path planning algorithms (such as Dijkstra's algorithm, A algorithm, RRT algorithm, and genetic algorithms) mostly focus on a single objective, such as finding the shortest path or achieving obstacle avoidance, while rarely incorporating "maximizing energy collection" as a core optimization objective into the planning process. For example, while the traditional A algorithm can guarantee finding the shortest path, its cost function typically only considers distance and obstacles, failing to guide the platform to areas with abundant energy. Simply adding energy gains as a weight to the cost function can lead to poor planning results due to inconsistent dimensions and subjective weight settings, potentially sacrificing path feasibility (such as the inability to avoid obstacles). Furthermore, most algorithms require a fixed destination, while maritime resupply scenarios require the power supply platform to autonomously calculate the optimal rendezvous point based on the dynamic route of the target vessel.

[0004] Therefore, existing technologies lack an intelligent path planning method and system suitable for marine new energy collection and power supply platforms that can comprehensively consider multiple constraints and objectives such as obstacle avoidance safety, convergence time window, and maximizing energy collection. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art, and proposes a path planning method and system for marine new energy collection and power supply platforms.

[0006] In a first aspect, embodiments of the present invention provide a path planning method for a marine new energy harvesting and power supply platform, comprising:

[0007] The target sea area is divided into grids, and a time-varying energy distribution field is constructed based on wind speed, solar irradiance, and temperature.

[0008] A global collision-free path is generated using a pre-defined algorithm. A dynamically wide and safe path corridor is constructed with the global collision-free path as the center. Multi-objective greedy optimization is performed within the path corridor to obtain a local path that balances obstacle avoidance and energy harvesting.

[0009] Using the target ship's route as the search space, the particle swarm optimization algorithm is employed, with the maximization of total energy storage across multiple platforms as the fitness function, to solve for the optimal rendezvous point.

[0010] The final path of the marine new energy collection and power supply platform is output with the optimal rendezvous point as the endpoint.

[0011] Furthermore, the time-varying energy distribution field includes the sum of wind energy and photovoltaic energy, wherein the method for calculating the wind energy includes:

[0012] Obtain the wind turbine parameters within the grid, including at least the turbine blade radius, turbine conversion efficiency, air density, and turbine power coefficient; then determine the energy output of the wind turbine within that grid. The calculation formula is:

[0013]

[0014] in, air density, Let be the radius of the wind turbine blade, and v be the wind speed at the center point of the grid region at the hour. This represents the power coefficient of the wind turbine.

[0015] Furthermore, the method for calculating photovoltaic energy includes:

[0016] Obtain the photovoltaic parameters within the grid, including at least the photovoltaic panel area, photovoltaic panel conversion efficiency, temperature coefficient, and temperature under standard testing conditions; then determine the energy that the photovoltaic panel can emit within that grid. The calculation formula is:

[0017]

[0018] Where A is the area of ​​the photovoltaic panel, and G is the solar irradiance. For photovoltaic panel conversion efficiency, Here, T is the temperature coefficient, and T is the temperature at the center point of the grid region at the hour. This refers to the temperature under standard testing conditions.

[0019] Furthermore, an improved A* algorithm is used to generate globally collision-free paths. A heuristic function is introduced into the A* algorithm to implement heuristic search. The definition of the heuristic function is:

[0020]

[0021] In the formula, The cost function represents the actual distance traveled from the starting point to the current node; The estimation function represents the estimated distance the current node is to the destination.

[0022] Furthermore, the evaluation function h(n) is the Euclidean distance to the rendezvous point, and the cost function g(n) comprehensively considers the travel distance and the obstacle approach penalty:

[0023]

[0024] In the formula, This represents the cumulative cost from the starting point to the parent node. This represents the Euclidean distance from the parent node to the current node. P(n) is the penalty coefficient, which controls the weight of the obstacle's influence; P(n) is the obstacle approach penalty term.

[0025]

[0026] In the formula, The coordinates of the current node n; As an indicator function, when coordinates The value is 1 when there is an obstacle, and 0 otherwise.

[0027] Furthermore, a local path that balances obstacle avoidance and energy harvesting is obtained, and the specific implementation steps include:

[0028] The A* algorithm is used for global path search. By expanding through neighbor nodes in multiple directions, the search proceeds from the starting point to the target point until a collision-free path connecting the two points is found, providing directional reference for subsequent local optimization.

[0029] Based on the global path generated by the A* algorithm, non-obstacle grid points are selected within a specified radius using each point on the global path as the center, forming a continuous sequence of safe search areas and constructing a safe search corridor area.

[0030] Multi-objective greedy optimization is performed within the generated path corridor, and candidate directions are comprehensively scored.

[0031] Choose the step with the highest overall score as the next move direction;

[0032] The generated discrete path points are increased by using arc length parameterization combined with PCHIP shape-preserving interpolation, and then local jitter is eliminated by moving average filtering, followed by post-processing smoothing optimization.

[0033] Furthermore, multi-objective greedy optimization is implemented within the generated path corridor to comprehensively score candidate directions. The multi-objective greedy optimization generates candidate movement steps in multiple directions based on the current ship position and under corridor constraints. The length of each step introduces random perturbation on the basis of the basic step size. Based on the current time and the latest allowed arrival time, the reachability of each candidate position is verified to ensure that the new candidate position can reach the vicinity of the target area within a specified time.

[0034] Furthermore, a dynamically weighted multi-objective evaluation function is used to comprehensively score the candidate steps; the score for candidate position i is:

[0035]

[0036] In the formula, Weighting for energy harvesting; Assign weight to progress rewards; For corridor compliance degree weighting, weight and It is inversely proportional to the remaining time. It is directly proportional to the remaining time; E is the energy gain, which is the energy density value at the candidate step path point; The progress reward is the difference between the Euclidean distance between the current point and the target point and the distance between the candidate point and the target point; C is the corridor compliance, which can be expressed by the formula:

[0037]

[0038] In the formula, Let be the Euclidean distance between the candidate point and the center line of the corridor.

[0039] Furthermore, a particle swarm optimization algorithm is employed, using the maximization of total energy storage across multiple platforms as the fitness function, to solve for the optimal merging point. Specific steps include:

[0040] Using the target ship's navigation line segment as the search space, initialize the particle swarm, with each particle representing a candidate merging point;

[0041] The fitness function is the maximum total energy storage when multiple platforms arrive at the convergence point.

[0042] The particle velocity and position are updated iteratively until the global optimal merging point is obtained.

[0043] Secondly, this invention also discloses a path planning system for a marine new energy collection and power supply platform, employing any one of the methods in claims 1-9, comprising: a time-varying energy distribution field construction unit, a local path generation unit, an optimal convergence point solution unit, and a final path output unit; wherein:

[0044] The time-varying energy distribution field construction unit is used to divide the target sea area into grids and construct the time-varying energy distribution field based on wind speed, solar irradiance and temperature.

[0045] The local path generation unit is used to generate a globally collision-free path using a preset algorithm, construct a dynamically wide and safe path corridor centered on the globally collision-free path, and perform multi-objective greedy optimization within the path corridor to obtain a local path that balances obstacle avoidance and energy harvesting.

[0046] The optimal rendezvous point solution unit is used to solve for the optimal rendezvous point by using the target ship's route as the search space, employing the particle swarm optimization algorithm, and using the maximization of the total energy storage of multiple platforms as the fitness function.

[0047] The final path output unit is used to output the final path of the marine new energy collection and power supply platform, with the optimal rendezvous point as the endpoint.

[0048] This invention discloses a path planning method and system for marine renewable energy collection and power supply platforms that considers energy harvesting. The method involves gridding the target sea area and constructing a time-varying marine energy distribution map based on wind speed, solar irradiance, and temperature data. First, a global collision-free path search is performed using an improved A* algorithm. Then, a dynamically wide safe path corridor is constructed centered on the global path, and local energy optimization is performed within the corridor, balancing obstacle avoidance safety with maximizing energy harvesting during navigation. Simultaneously, a particle swarm optimization algorithm is used, with the target vessel's dynamic route as the search space and the maximum total energy storage at the rendezvous point for multiple platforms as the fitness function, to autonomously solve for the optimal rendezvous point. Finally, a multi-platform collaborative path that satisfies time window, obstacle avoidance constraints, and optimal total energy is output. This invention effectively solves the problems of traditional path planning, such as a single objective, subjective weight setting, and inability to dynamically determine the rendezvous point. It significantly improves the efficiency of marine renewable energy collection while ensuring timely rendezvous and navigation safety. It is applicable to engineering scenarios such as multi-platform maritime replenishment and autonomous power supply for unmanned platforms, demonstrating strong practicality and high engineering adaptability. Attached Figure Description

[0049] Figure 1 A flowchart illustrating a path planning method for a marine new energy collection and power supply platform provided in an embodiment of the present invention;

[0050] Figure 2 This is the energy map of the path planning area at 12 o'clock in this embodiment of the invention;

[0051] Figure 3 This is a schematic diagram of the final planned paths and convergence points of the three power supply platforms in an accessible scenario according to an embodiment of the present invention.

[0052] Figure 4 This is a schematic diagram illustrating the path planning of three power supply platforms successfully avoiding obstacles and optimizing energy harvesting in an obstacle-prone scenario according to an embodiment of the present invention.

[0053] Figure 5 This is a schematic diagram of the test environment in an embodiment of the present invention;

[0054] Figure 6 The energy map of the path planning area in the test environment of this embodiment of the invention at 16:00.

[0055] Figure 7 This is a schematic diagram of the optimized energy harvesting path planning for three power supply platforms under a test environment in an embodiment of the present invention;

[0056] Figure 8 This is an actual path diagram of the first power supply platform optimizing energy harvesting under a test environment in an embodiment of the present invention;

[0057] Figure 9 This is an actual path diagram of the second power supply platform optimizing energy harvesting under a test environment in an embodiment of the present invention;

[0058] Figure 10 This is an actual path diagram of the third power supply platform optimizing energy harvesting under a test environment in an embodiment of the present invention;

[0059] Figure 11 This is a structural block diagram of a path planning system for a marine new energy collection and power supply platform, provided as an embodiment of the present invention. Detailed Implementation

[0060] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0061] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0062] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0063] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0064] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0065] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0066] To address at least one of the technical problems existing in the aforementioned related technologies, the present invention provides a path planning method and system for a marine new energy harvesting and power supply platform that considers energy harvesting.

[0067] This implementation discloses a path planning method for a marine new energy harvesting and power supply platform, such as... Figure 1 ,include:

[0068] S100. Divide the target sea area into grids and construct a time-varying energy distribution field based on wind speed, solar irradiance, and temperature.

[0069] In this embodiment, the time-varying energy distribution field includes the sum of wind energy and photovoltaic energy, wherein the method for calculating the wind energy includes:

[0070] Obtain the wind turbine parameters within the grid, including at least the turbine blade radius, turbine conversion efficiency, air density, and turbine power coefficient; then determine the energy output of the wind turbine within that grid. The calculation formula is:

[0071]

[0072] in, air density, Let be the radius of the wind turbine blade, and v be the wind speed at the center point of the grid region at the hour. This represents the power coefficient of the wind turbine.

[0073] In this embodiment, the method for calculating photovoltaic energy includes:

[0074] Obtain the photovoltaic parameters within the grid, including at least the photovoltaic panel area, photovoltaic panel conversion efficiency, temperature coefficient, and temperature under standard testing conditions; then determine the energy that the photovoltaic panel can emit within that grid. The calculation formula is:

[0075]

[0076] Where A is the area of ​​the photovoltaic panel, and G is the solar irradiance. For photovoltaic panel conversion efficiency, Here, T is the temperature coefficient, and T is the temperature at the center point of the grid region at the hour. This refers to the temperature under standard testing conditions.

[0077] For example, the selected target sea area is a square sea area with a projected area of ​​72km × 72km, and each grid is 1km × 1km in size; the energy (unit: kWh) of the grid area is calculated from the temperature, solar irradiance, and wind speed data at the center point of the grid area. The parameters for photovoltaic and wind turbines are shown in Table 1:

[0078] Table 1 Parameters of Photovoltaic and Wind Turbines

[0079]

[0080] For each grid cell at each integer time t:

[0081] Wind energy is:

[0082]

[0083] In the formula, v is the wind speed at the center point of the grid area at the hour.

[0084] The energy that the wind turbine can generate in this grid is:

[0085]

[0086] The photovoltaic panel conversion efficiency is:

[0087]

[0088] In the formula, T is the temperature at the center point of the grid region at the hour.

[0089] The energy that the photovoltaic panel can emit in this grid is:

[0090]

[0091] In the formula, G is the solar radiation intensity, with the unit W / m2.

[0092] Therefore, the total energy generated by wind turbines and photovoltaic power within this grid is:

[0093]

[0094] By visualizing the energy values ​​of all grids at a specific time, we can obtain, for example... Figure 2 The energy distribution diagram shown. Figure 2 In the diagram, different colors are used to represent new energy sources in different grids. The brighter the color, the higher the energy of that grid.

[0095] S200. A global collision-free path is generated using a preset algorithm. A dynamically wide and safe path corridor is constructed with the global collision-free path as the center. Multi-objective greedy optimization is performed within the path corridor to obtain a local path that balances obstacle avoidance and energy harvesting.

[0096] Specifically, compared to other scenarios, the path planning algorithm in this embodiment needs to consider not only obstacle avoidance and distance factors, but also energy harvesting factors and time constraints. Simply changing the cost function of A* to consider energy gains would result in a lack of verification of path feasibility for the A* search objective. If both distance and energy are considered in the cost function, a suitable weighting function needs to be designed due to their different dimensions, leading to a subjective and ambiguous determination of the weights. Therefore, a fusion algorithm combining the improved A* algorithm with a multi-objective greedy strategy is chosen. First, a global path search is performed based on the A* algorithm to ensure the path is basically feasible and meets obstacle avoidance requirements. Simultaneously, to maximize energy harvesting for the floating marine energy harvesting platform, a path corridor is constructed based on the aforementioned global path. Within the corridor, local optimization is performed using a greedy algorithm, dynamically adjusting the travel path to improve energy harvesting efficiency. This ensures path feasibility while effectively avoiding the problems of getting trapped in local high-energy areas and failing to reach the global optimum, as well as the lack of a global perspective, inherent in pure greedy strategies.

[0097] To ensure path feasibility and obstacle avoidance requirements, the evaluation function h(n) is chosen as the Euclidean distance to the rendezvous point, and the cost function g(n) comprehensively considers the travel distance and obstacle approach penalty.

[0098]

[0099] In the formula, This represents the cumulative cost from the starting point to the parent node. This represents the Euclidean distance from the parent node to the current node. P(n) is the penalty coefficient (typically 0.1), which controls the weight of the obstacle's influence; P(n) is the obstacle approach penalty term.

[0100]

[0101] In the formula, The coordinates of the current node n; As an indicator function, when coordinates The value is 1 when there is an obstacle, and 0 otherwise.

[0102] In this embodiment, the specific implementation steps of S200 include:

[0103] S201. The A* algorithm is used for global path search. It expands through multiple (8) directional neighbor nodes and searches step by step from the starting point to the target point until a collision-free path connecting the two points is found, providing directional reference for subsequent local optimization.

[0104] S202. Based on the global path generated by the A* algorithm, non-obstacle grid points are selected within a specified radius using each point on the global path as the center, forming a continuous sequence of safe search areas and constructing a safe search corridor area.

[0105] S203. Perform multi-objective greedy optimization within the generated path corridor and give a comprehensive score to the candidate directions;

[0106] S204. Select the step with the highest overall score as the next move direction;

[0107] S205. The generated discrete path points are increased by using arc length parameterization combined with PCHIP shape-preserving interpolation, and then local jitter is eliminated by moving average filtering, followed by post-processing smoothing optimization.

[0108] In this embodiment, multi-objective greedy optimization is implemented within the generated path corridor, and candidate directions are comprehensively scored. The multi-objective greedy optimization generates candidate movement steps in multiple directions based on the current ship position and under corridor constraints. The length of each step introduces random perturbation on the basis of the basic step size. Based on the current time and the latest allowed arrival time, the reachability of each candidate position is verified to ensure that the new candidate position can reach the vicinity of the target area within a specified time.

[0109] Specifically, the score for candidate position i is:

[0110]

[0111] In the formula, Weighting for energy harvesting; Assign weight to progress rewards; For corridor compliance degree weighting, weight and It is inversely proportional to the remaining time. It is directly proportional to the remaining time; E is the energy gain, which is the energy density value at the candidate step path point; The progress reward is the difference between the Euclidean distance between the current point and the target point and the distance between the candidate point and the target point; C is the corridor compliance, which can be expressed by the formula:

[0112]

[0113] In the formula, Let be the Euclidean distance between the candidate point and the center line of the corridor.

[0114] S300. Using the target ship's route as the search space, the particle swarm optimization algorithm is used, with the maximization of total energy storage across multiple platforms as the fitness function, to solve for the optimal rendezvous point;

[0115] Among them, the Particle Swarm Optimization (PSO) algorithm is an optimization algorithm based on swarm intelligence that finds the optimal solution by simulating the social behavior of flocks of birds or schools of fish. Each particle represents a possible solution (i.e., the coordinates of the meeting point). The particles move in the search space and adjust their positions based on their own experience and the experience of the group, eventually converging to the optimal solution.

[0116] In this embodiment, the particle swarm optimization algorithm is used, with the maximization of total energy storage across multiple platforms as the fitness function, to solve for the optimal merging point. Specific steps include:

[0117] Using the target ship's navigation line segment as the search space, initialize the particle swarm, with each particle representing a candidate merging point;

[0118] The fitness function is the maximum total energy storage when multiple platforms arrive at the convergence point.

[0119] The particle velocity and position are updated iteratively until the global optimal merging point is obtained.

[0120] For example, based on the particle swarm optimization algorithm, the optimal meeting point C on line segment AB can be searched using specific methods, including:

[0121] (1) Initialize the particle swarm: Randomly generate a group of particles (coordinate points) on line segment AB and randomly initialize their velocities.

[0122] (2) For each particle (merging point C), calculate the paths of the three ships from their respective starting points to point C, and calculate the total stored energy.

[0123] (3) Calculate the fitness (i.e. total energy storage) of each particle and update the individual optimum and global optimum.

[0124] (4) Update the particle's velocity and position.

[0125] (5) Repeat steps 2-4 until the fitness converges.

[0126] S400. Using the optimal rendezvous point as the endpoint, output the final path of the marine renewable energy collection and power supply platform. Specifically, combining the above steps, with the optimal rendezvous point as the final goal, output the optimal path for each platform.

[0127] This embodiment discloses a path planning method and system for marine renewable energy collection and power supply platforms that considers energy harvesting. The method involves gridding the target sea area and constructing a time-varying marine energy distribution map based on wind speed, solar irradiance, and temperature data. Then, an improved A* algorithm is used to complete a global collision-free path search. Next, a dynamically wide safe path corridor is constructed centered on the global path, and local energy optimization is performed within the corridor, balancing obstacle avoidance safety and maximizing energy harvesting during navigation. Simultaneously, a particle swarm optimization algorithm is used with the target vessel's dynamic route as the search space and the maximum total energy storage when multiple platforms arrive at the rendezvous point as the fitness function to autonomously solve for the optimal rendezvous point. Finally, a multi-platform collaborative path that satisfies time window, obstacle avoidance constraints, and optimal total energy is output. This invention effectively solves the problems of traditional path planning, such as a single objective, subjective weight setting, and inability to dynamically determine the rendezvous point. It significantly improves the efficiency of marine renewable energy collection while ensuring timely rendezvous and navigation safety. It is applicable to engineering scenarios such as multi-platform maritime replenishment and autonomous power supply for unmanned platforms, demonstrating strong practicality and high engineering adaptability.

[0128] To better understand this implementation, simulation experiments are used to evaluate the performance and application effects of the improved A* algorithm. The simulation experiment environment and specific steps include:

[0129] The CPU used is an AMD Ryzen 78745HSw / Radeon 780M Graphics, with 32GB of RAM. The operating system is Windows 11 (64-bit). The simulation was developed using Matlab, and the simulation program is a .m script within the Matlab environment. The aforementioned raster map was used as the simulation environment. Different colored dots and lines, the "X" symbol, red dashed lines, and pentagrams were used to represent the platform's starting point and path, obstacles, the target ship's path, and the rendezvous point, respectively.

[0130] The simulation environment is set as follows: Platform 1 starts at coordinates (14, 14), departs at 4:00 AM, and its path is marked by a blue solid line; Platform 2 starts at coordinates (61.8, 31.8), departs at 5:00 AM, and its path is marked by a red solid line; Platform 3 starts at coordinates (40.6, 60.2), departs at 4:00 AM, and its path is marked by a yellow solid line; the movement step of the three platforms is 1 km, and the time taken for one movement is 30 minutes; the initial weights of the multi-objective evaluation function are: The target vessel that needs to receive energy departs from coordinates (2, 2) at 4:00 PM, heading in a straight line at (70, 70), with a speed of 30 km / h. The path planning results are as follows: Figure 3 As shown.

[0131] Depend on Figure 3 It can be seen that, compared to the traditional A* algorithm, platforms 1 and 3, given sufficient time, will choose to veer to the lower left to a region with higher energy density in order to collect more energy, rather than heading straight for the rendezvous point.

[0132] Based on the path planning scenario in an accessible environment, an obstacle is added at point (50, 33) on the path of platform 2. The path planning result is as follows. Figure 4 As shown.

[0133] from Figure 4 It can be seen that the algorithm proposed in this invention can achieve energy collection and reach the rendezvous point while still ensuring obstacle avoidance capabilities.

[0134] To further verify the effectiveness of the proposed algorithm, a water tank experiment was conducted at a test pool located in Dongjiagou, Duzhuang Town, Haigang District, Qinhuangdao City, at 119.5797095 E, 40.0421503 N. By simulating weather and current power generation data in different areas, the remote control terminal automatically calculated the regional energy density changes. Within the test water area, the coordinates of the point with the maximum current power generation were calculated, and automatic path planning was performed for multiple platforms. The size and shape of the water tank are as follows... Figure 5 As shown, the simulated energy density data for different regions are as follows: Figure 6 As shown, the path obtained from platform path planning is as follows: Figure 7 As shown.

[0135] The waypoints obtained from the path planning simulation results were applied to the platform's lower-level computer, and the actual flight paths of platforms 1-3 were obtained as follows: Figure 8-10 As shown by the red, green, and blue line segments in the diagram, the platform's movement trajectory follows the sequence from Figure ① to Figure ④ in the sub-diagram. This is based on the test results from the water tank and... Figure 8The simulation results shown demonstrate that the pool experiment intuitively proves that the proposed path planning algorithm is not a rigid static planning simulator, but rather possesses high practical application value. The path planning algorithm deployed on the host computer can accurately calculate the optimal charging point coordinates for both the platform and the platform to be charged. After receiving commands from the remote control terminal, the platform can complete path planning from different areas and travel to the coordinates of maximum power generation according to the predetermined route. This proves that the route calculated by the proposed algorithm is practical and can effectively guide ship navigation.

[0136] Based on the same inventive concept, this invention also provides a path planning system for a marine new energy harvesting and power supply platform, employing the aforementioned path planning method for marine new energy harvesting and power supply platforms, comprising: a time-varying energy distribution field construction unit, a local path generation unit, an optimal convergence point solution unit, and a final path output unit; wherein:

[0137] The time-varying energy distribution field construction unit is used to divide the target sea area into grids and construct the time-varying energy distribution field based on wind speed, solar irradiance and temperature.

[0138] The local path generation unit is used to generate a globally collision-free path using a preset algorithm, construct a dynamically wide and safe path corridor centered on the globally collision-free path, and perform multi-objective greedy optimization within the path corridor to obtain a local path that balances obstacle avoidance and energy harvesting.

[0139] The optimal rendezvous point solution unit is used to solve for the optimal rendezvous point by using the target ship's route as the search space, employing the particle swarm optimization algorithm, and using the maximization of the total energy storage of multiple platforms as the fitness function.

[0140] The final path output unit is used to output the final path of the marine new energy collection and power supply platform, with the optimal rendezvous point as the endpoint.

[0141] The specific working methods of the time-varying energy distribution field construction unit, the local path generation unit, the optimal convergence point solution unit, and the final path output unit have been described in detail in the above methods, and will not be repeated here in this implementation.

[0142] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0143] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0144] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0145] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0146] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0147] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0148] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0149] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0150] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0151] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

Claims

1. A path planning method for a marine new energy harvesting and power supply platform, characterized in that, include: The target sea area is divided into grids, and a time-varying energy distribution field is constructed based on wind speed, solar irradiance, and temperature. A global collision-free path is generated using a pre-defined algorithm. A dynamically wide and safe path corridor is constructed with the global collision-free path as the center. Multi-objective greedy optimization is performed within the path corridor to obtain a local path that balances obstacle avoidance and energy harvesting. Using the target ship's route as the search space, the particle swarm optimization algorithm is employed, with the maximization of total energy storage across multiple platforms as the fitness function, to solve for the optimal rendezvous point. The final path of the marine new energy collection and power supply platform is output with the optimal rendezvous point as the endpoint.

2. The path planning method according to claim 1, characterized in that, The time-varying energy distribution field includes the sum of wind energy and photovoltaic energy, wherein the method for calculating the wind energy includes: Obtain the wind turbine parameters within the grid, including at least the turbine blade radius, turbine conversion efficiency, air density, and turbine power coefficient; then determine the energy output of the wind turbine within that grid. The calculation formula is: in, air density, Let be the radius of the wind turbine blade, and v be the wind speed at the center point of the grid region at the hour. This represents the power coefficient of the wind turbine.

3. The path planning method according to claim 1, characterized in that, The method for calculating photovoltaic energy includes: Obtain the photovoltaic parameters within the grid, including at least the photovoltaic panel area, photovoltaic panel conversion efficiency, temperature coefficient, and temperature under standard testing conditions; then determine the energy that the photovoltaic panel can emit within that grid. The calculation formula is: Where A is the area of ​​the photovoltaic panel, and G is the solar irradiance. For photovoltaic panel conversion efficiency, Here, T is the temperature coefficient, and T is the temperature at the center point of the grid region at the hour. This refers to the temperature under standard testing conditions.

4. The path planning method according to claim 1, characterized in that, An improved A* algorithm is used to generate globally collision-free paths. A heuristic function is introduced into the A* algorithm to implement heuristic search. The definition of the heuristic function is: In the formula, The cost function represents the actual distance traveled from the starting point to the current node; The estimation function represents the estimated distance the current node is to the destination.

5. The path planning method according to claim 4, characterized in that, The evaluation function h(n) is the Euclidean distance to the rendezvous point, and the cost function g(n) comprehensively considers the travel distance and the obstacle approach penalty: In the formula, This represents the cumulative cost from the starting point to the parent node. This represents the Euclidean distance from the parent node to the current node. This is the penalty coefficient, which controls the weight of the obstacle's influence. Penalty for approaching obstacles: In the formula, The coordinates of the current node n; As an indicator function, when coordinates The value is 1 when an obstacle is present, and 0 otherwise.

6. The path planning method according to claim 1, characterized in that, To obtain a local path that balances obstacle avoidance and energy harvesting, the specific steps include: The A* algorithm is used for global path search. By expanding through neighbor nodes in multiple directions, the search proceeds from the starting point to the target point until a collision-free path connecting the two points is found, providing directional reference for subsequent local optimization. Based on the global path generated by the A* algorithm, non-obstacle grid points are selected within a specified radius using each point on the global path as the center, forming a continuous sequence of safe search areas and constructing a safe search corridor area. Multi-objective greedy optimization is performed within the generated path corridor, and candidate directions are comprehensively scored. Choose the step with the highest overall score as the next move direction; The generated discrete path points are increased by using arc length parameterization combined with PCHIP shape-preserving interpolation, and then local jitter is eliminated by moving average filtering, followed by post-processing smoothing optimization.

7. The path planning method according to claim 6, characterized in that, Multi-objective greedy optimization is performed within the generated path corridor, and candidate directions are comprehensively scored. The multi-objective greedy optimization is based on the current ship position and generates candidate movement steps in multiple directions under corridor constraints. The length of each step introduces random perturbation on the basis of the basic step size. Based on the current time and the latest allowed arrival time, each candidate location is verified for accessibility to ensure that the new candidate location can reach the vicinity of the target area within the specified time.

8. The path planning method according to claim 7, characterized in that, A dynamically weighted multi-objective evaluation function is used to comprehensively score the candidate steps, and the score for candidate position i is: In the formula, Weighting for energy harvesting; Assign weight to progress rewards; For corridor compliance degree weighting, weight and It is inversely proportional to the remaining time. It is directly proportional to the remaining time; E is the energy gain, which is the energy density value at the candidate step path point; The progress reward is the difference between the Euclidean distance between the current point and the target point and the distance between the candidate point and the target point; C is the corridor compliance, which can be expressed by the formula: In the formula, Let be the Euclidean distance between the candidate point and the center line of the corridor.

9. The path planning method according to claim 1, characterized in that, The particle swarm optimization algorithm is used, with the maximization of total energy storage across multiple platforms as the fitness function, to solve for the optimal merging point. The specific steps include: Using the target ship's navigation line segment as the search space, initialize the particle swarm, with each particle representing a candidate merging point; The fitness function is the maximum total energy storage when multiple platforms arrive at the convergence point. The particle velocity and position are updated iteratively until the global optimal merging point is obtained.

10. A path planning system for a marine new energy harvesting and power supply platform, employing the method of any one of claims 1-9, characterized in that, include: The system comprises a time-varying energy distribution field construction unit, a local path generation unit, an optimal convergence point solution unit, and a final path output unit; wherein: The time-varying energy distribution field construction unit is used to divide the target sea area into grids and construct the time-varying energy distribution field based on wind speed, solar irradiance and temperature. The local path generation unit is used to generate a globally collision-free path using a preset algorithm, construct a dynamically wide and safe path corridor centered on the globally collision-free path, and perform multi-objective greedy optimization within the path corridor to obtain a local path that balances obstacle avoidance and energy harvesting. The optimal rendezvous point solution unit is used to solve for the optimal rendezvous point by using the target ship's route as the search space, employing the particle swarm optimization algorithm, and using the maximization of the total energy storage of multiple platforms as the fitness function. The final path output unit is used to output the final path of the marine new energy collection and power supply platform, with the optimal rendezvous point as the endpoint.

Images