Wind power plant emergency operation and maintenance method, equipment and medium

Abstract

The invention discloses a wind power plant emergency operation and maintenance method and device and a readable storage medium, and the method comprises the steps: obtaining the number of particles in a particle swarm, and setting the number of unmanned ships, the number K of unmanned planes carried by each unmanned ship, and the number of to-be-operated and to-be-maintained points; initializing the position of each particle in a particle swarm by taking the number of the to-be-operated and to-be-maintained points as the particle length; segmenting a position pseudo index and a tool pseudo index according to the position of the particle, and generating an operation and maintenance path corresponding to the current position of the particle according to the position pseudo index and the tool pseudo index; calculating the fitness of particles according to the running speed and running time of the unmanned ship and the unmanned aerial vehicle, obtaining a global optimal particle according to the fitness of the particles, and recording the global optimal particle and a corresponding operation and maintenance path; updating the position of each particle in the particle swarm; outputting the updated global optimal particle and the corresponding operation and maintenance path, and scheduling the unmanned ship and the unmanned aerial vehicle; therefore, the emergency operation and maintenance path planning of the wind power plant is realized, and the path planning time is shortened.

Description

Technical Field

[0001] The present invention relates to the technical field of offshore wind farms, and in particular to a wind farm emergency operation and maintenance method, equipment and medium. Background Art

[0002] In recent years, offshore wind power generation technology has continued to advance, and the scale of wind farm applications in actual sea areas has continued to expand. The challenges faced by offshore wind power operation and maintenance work have become increasingly complex and diverse. On the one hand, due to its special geographical environment and climatic conditions, offshore wind farms are difficult to operate and maintain, especially in emergency scenarios where it is difficult to control the inspection time. On the other hand, although existing technologies also use unmanned boats carrying drones to collaboratively inspect wind farms, this method lacks an efficient path planning method and cannot meet the emergency needs of offshore wind farms. The emergency time is long and the operation and maintenance efficiency in emergency scenarios is low. Summary of the invention

[0003] The embodiments of the present invention provide a wind farm emergency operation and maintenance method, device and medium to solve the problems of low path planning efficiency and long emergency time in the prior art when performing emergency operation and maintenance on a wind farm.

[0004] A wind farm emergency operation and maintenance method, the method comprising:

[0005] S1: Get the number of particles N in the particle swarm, set the number of unmanned boats M, the number of drones carried by each unmanned boat K, and the number of points to be operated and maintained P;

[0006] S2: Using the number of points to be operated and maintained P as the particle length, the position of each particle in the particle swarm is initialized;

[0007] S3: traverse each particle, divide the position pseudo index and the tool pseudo index according to the position of the particle, and generate the operation and maintenance path corresponding to the particle at the current position according to the position pseudo index and the tool pseudo index;

[0008] S4: Calculate the fitness of the particles according to the running speed and running time of the unmanned boat and the drone, obtain the global optimal particle according to the fitness of the particle, and record the global optimal particle and its corresponding operation and maintenance path;

[0009] S5: Use the MPSO algorithm to update the position of each particle in the particle swarm;

[0010] S6: Determine whether the number of iterations reaches a preset threshold. If so, output the updated global optimal particle and its corresponding operation and maintenance path to dispatch the unmanned boat and the unmanned aerial vehicle; if not, return to step S3.

[0011] Optionally, the initializing the position of each particle in the particle swarm using the number P of points to be operated and maintained as the particle length includes:

[0012] The particle length is set to the number P of the points to be operated and maintained;

[0013] Initialize each dimension value within the particle length according to the encoding value rule, and get the position of particle i as x i =(x i，1 , x i，2 , …, x i，P ), where the pth (1≤p≤P) dimension value x i，p The value range is [1,P), and the precision is 1 decimal place.

[0014] Optionally, dividing a position pseudo index and a tool pseudo index according to the position of the particle, and generating an operation and maintenance path corresponding to the particle at the current position according to the position pseudo index and the tool pseudo index comprises:

[0015] Divide each dimension value of the position of the particle into an integer part and a decimal part;

[0016] The integer part of each dimension value is combined to form a position pseudo index, and the decimal part of each dimension value is combined to form a tool pseudo index;

[0017] Acquire an operation and maintenance point sequence according to the position pseudo index;

[0018] Acquire an operation and maintenance tool sequence according to the tool pseudo index;

[0019] The operation and maintenance point sequence and the operation and maintenance tool sequence are combined to generate a temporary path, and the operation and maintenance path of the unmanned boat and the operation and maintenance path of the unmanned aerial vehicle are segmented according to the temporary path.

[0020] Optionally, acquiring the operation and maintenance point sequence according to the position pseudo index includes:

[0021] S331: Initialize a selected operation and maintenance point set SETA and an unselected operation and maintenance point set SETB, wherein the selected operation and maintenance point set SETA is an empty set, and the unselected operation and maintenance point set SETB includes all the points to be operated and maintained;

[0022] S332: Initialize the current operation and maintenance point PA to 0 and the dimension variable p to 1;

[0023] S333: Obtain the distance AM between the current operation and maintenance point PA and the points to be operated and maintained in the unselected operation and maintenance point set SETB, sort the distance AM from small to large, and generate an operation and maintenance point distance sequence SAM;

[0024] S334: Determine whether the unselected operation and maintenance point set SETB is an empty set, if not, execute S335, if yes, execute S337;

[0025] S335: According to the position pseudo-index and the operation and maintenance point distance sequence SAM, a new operation and maintenance point is selected to update the current operation and maintenance point PA, and the new operation and maintenance point is added to the selected operation and maintenance point set SETA, and the new operation and maintenance point is deleted from the unselected operation and maintenance point set SETB;

[0026] S336: increment the dimension variable p by 1, and return to step S333;

[0027] S337: End the iteration. When the unselected operation and maintenance point set SETB is an empty set, obtain the selected operation and maintenance point set SETA as the operation and maintenance point sequence.

[0028] Optionally, acquiring the operation and maintenance tool sequence according to the tool pseudo index includes:

[0029] According to the number of drones K carried by each unmanned boat and the number of points to be operated and maintained P, a generative group of operation and maintenance tools is constructed;

[0030] For each dimension value in the tool pseudo index, obtain the operation and maintenance tool coding information corresponding to the dimension through the generation formula group of the operation and maintenance tool;

[0031] Each dimension value in the tool pseudo index is traversed to generate an operation and maintenance tool sequence.

[0032] Optionally, the combining the operation and maintenance point sequence and the operation and maintenance tool sequence to generate a temporary path, and segmenting the operation and maintenance path of the unmanned boat and the operation and maintenance path of the drone according to the temporary path includes:

[0033] A node is formed by using the dimension values ​​on the same dimension in the operation and maintenance point sequence and the operation and maintenance tool sequence to generate a temporary path;

[0034] Acquire all nodes whose operation and maintenance tool coding information is the unmanned boat from the temporary path, and generate a first node sequence;

[0035] Adding a starting node consisting of the departure port and the operation and maintenance tool coding information of the unmanned boat to the front end and the rear end of the obtained first node sequence respectively, to generate an operation and maintenance path of the unmanned boat;

[0036] Dividing the temporary path into a plurality of segmented paths according to the operation and maintenance tool coding information of the unmanned boat;

[0037] For each segmented path, the corresponding operation and maintenance path is extracted for each UAV.

[0038] Optionally, for each segmented path, extracting a corresponding operation and maintenance path for each drone includes:

[0039] In a segmented path, traverse the operation and maintenance tool coding information of each drone, extract corresponding nodes from the segmented path, and generate a second node sequence;

[0040] The first node in the segmented path is added to the head of the second node sequence, and the tail node is added to the tail of the second node sequence to generate an operation and maintenance path for the drone.

[0041] Optionally, the step of calculating the fitness of particles according to the running speed and running time of the unmanned boat and the unmanned aerial vehicle includes:

[0042] According to the operation and maintenance path corresponding to the particle at the current position, the nodes passed by the unmanned boat, the distance between the nodes and the running speed of the unmanned boat are obtained respectively, and the running time of the unmanned boat is generated;

[0043] According to the operation and maintenance path corresponding to the particle at the current position, the nodes passed by the drone, the distance between nodes and the running speed of the drone are obtained respectively, and the running time of the drone is generated;

[0044] According to the operation and maintenance path corresponding to the particle at the current position, the nodes passed by the unmanned boat and the unit time of the unmanned boat for operating the wind turbine are obtained respectively, and the operation and maintenance time of the unmanned boat is generated;

[0045] According to the operation and maintenance path corresponding to the particle at the current position, the nodes passed by the drone and the unit time of the drone's operation and maintenance of the wind turbine are obtained respectively, and the operation and maintenance time of the drone is generated;

[0046] The sum of the operating time of the unmanned boat, the operating time of the drone, the operation and maintenance time of the unmanned boat, and the operation and maintenance time of the drone is calculated as the fitness of the particle.

[0047] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the wind farm emergency operation and maintenance method as described above when executing the computer program.

[0048] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the wind farm emergency operation and maintenance method as described above is implemented.

[0049] The embodiment of the present invention obtains the number of particles N in the particle swarm, respectively sets the number of unmanned boats M, the number of drones K carried by each unmanned boat, and the number of points to be operated and maintained P; uses the number of points to be operated and maintained P as the particle length, and initializes the position of each particle in the particle swarm; then traverses each particle, divides the position pseudo index and the tool pseudo index according to the position of the particle, and generates the operation and maintenance path corresponding to the particle at the current position according to the position pseudo index and the tool pseudo index; calculates the fitness of the particle according to the running speed and running time of the unmanned boat and the drone, obtains the global optimal particle according to the fitness of the particle, and records the global optimal particle and its corresponding operation and maintenance path; adopts the MPSO algorithm to update the position of each particle in the particle swarm; outputs the updated global optimal particle and its corresponding operation and maintenance path when judging that the number of iterations reaches a preset number threshold, and dispatches the unmanned boat and the drone; thereby realizing the emergency operation and maintenance path planning of the wind farm, and shortening the encoding length of the particle and introducing the position pseudo index to perform neighborhood search, shortening the path planning time, improving the path planning speed, effectively solving the problems of low path planning efficiency and long emergency time in the prior art when performing emergency operation and maintenance on the wind farm, and meeting the emergency operation and maintenance needs of the offshore wind farm. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0051] Figure 1 is a schematic diagram of a wind farm emergency operation and maintenance method provided by an embodiment of the present invention;

[0052] Figure 2 This is a schematic diagram of an emergency operation and maintenance path for an offshore wind farm provided by an embodiment of the present invention;

[0053] Figure 3 is a specific coding schematic diagram of particle positions provided by an embodiment of the present invention;

[0054] Figure 4 is a schematic diagram of a position pseudo index and a tool pseudo index provided by an embodiment of the present invention;

[0055] Figure 5 This is a flowchart of obtaining an operation and maintenance point sequence according to a position pseudo index provided by an embodiment of the present invention;

[0056] Figure 6 It is a schematic diagram of a process for obtaining an operation and maintenance path of a drone provided by an embodiment of the present invention;

[0057] Figure 7 is a schematic diagram of a wind farm emergency operation and maintenance device provided by an embodiment of the present invention;

[0058] Figure 8 is a schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] The wind farm emergency operation and maintenance method provided by the present invention is applied to offshore wind farms that use multiple drones to coordinate unmanned boats for operation and maintenance. The method optimizes the wind turbine operation and maintenance paths of unmanned boats and drones with the shortest time pseudo-target, and improves the operation and maintenance efficiency in emergency scenarios.

[0061] In the process of multiple drones cooperating with unmanned boats for operation and maintenance, facing multiple wind power operation and maintenance points, the port dispatches an unmanned boat carrying multiple drones to be responsible for operation and maintenance. The operation and maintenance time required for drones and unmanned boats to operate the same point is usually different. In this process, the unmanned boat will provide battery replacement services for the drone. After completing the operation and maintenance tasks of the operation and maintenance point, the drone can return to the unmanned boat to replace the battery. The drone's battery life will be restored to its maximum battery life, and then take off from the unmanned boat and continue to serve other operation and maintenance points. In addition, unmanned boats and drones can perform operation and maintenance services synchronously. Even when the drone goes out to perform operation and maintenance tasks, the unmanned boat can also serve other operation and maintenance points at the same time. The object of the present invention is to determine the hybrid operation and maintenance path of unmanned boats and drones during emergency operation and maintenance to achieve the shortest operation and maintenance time.

[0062] Figure 1 The wind farm emergency operation and maintenance method provided by the embodiment of the present invention. Figure 1 As shown, the wind farm emergency operation and maintenance method includes:

[0063] S1: Get the number of particles N in the particle swarm, set the number of unmanned boats M, the number of drones carried by each unmanned boat K, and the number of points to be operated and maintained P respectively;

[0064] S2: Using the number of points to be operated and maintained P as the particle length, the position of each particle in the particle swarm is initialized;

[0065] S3: traverse each particle, divide the position pseudo index and the tool pseudo index according to the position of the particle, and generate the operation and maintenance path corresponding to the particle at the current position according to the position pseudo index and the tool pseudo index;

[0066] S4: Calculate the fitness of the particles according to the running speed and running time of the unmanned boat and the drone, obtain the global optimal particle according to the fitness of the particle, and record the global optimal particle and its corresponding operation and maintenance path;

[0067] S5: Use the MPSO algorithm to update the position of each particle in the particle swarm;

[0068] S6: Determine whether the number of iterations reaches a preset threshold. If so, output the updated global optimal particle and its corresponding operation and maintenance path to dispatch the unmanned boat and the unmanned aerial vehicle; if not, return to step S3.

[0069] Here, the embodiment of the present invention starts from the goal of shortest emergency operation and maintenance time of wind farms. In the particle sequence encoding program, the number of points to be operated and maintained P is innovatively used as the particle length to initialize the position of each particle in the particle group. Compared with the particle length used in the prior art, it is shortened by at least half, which can realize the transformation of particle space to real physical scheme; combined with the use of position pseudo-index for neighborhood search in particle sequence decoding, the speed and effect of algorithm convergence are greatly improved. At the same time, the fitness optimization method of the particle is based on the operation and maintenance path corresponding to the particle at the current position and the driving speed and driving time of the drone and unmanned boat to obtain the global optimal particle and update the corresponding operation and maintenance path. Finally, the service path of the drone and unmanned boat is obtained according to the global optimal particle, and the drone and unmanned boat are dispatched accordingly, which effectively shortens the path planning time and improves the speed of path planning. It solves the problems of low path planning efficiency and long emergency time in the prior art when performing emergency operation and maintenance of wind farms, and can meet the emergency operation and maintenance needs of offshore wind farms.

[0070] According to one embodiment of the present invention, in step S1, the number of particles N in the particle swarm is randomly set by a user or a computer program. The number of unmanned boats M, the number of drones K carried by each unmanned boat, and the number of maintenance points P are set according to the actual offshore wind farm that needs maintenance. For ease of understanding, Figure 2 A schematic diagram of an emergency operation and maintenance path for an offshore wind farm provided by an embodiment of the present invention. Figure 2 In the example, the offshore wind farm includes a port base, 6 maintenance points (i.e. wind turbines), and uses an unmanned boat carrying 2 drones. Figure 2 In the emergency operation and maintenance path diagram shown, the unmanned boat is responsible for visiting operation and maintenance points 3, 2, and 1, drone 1 is responsible for visiting operation and maintenance points 6 and 5, and drone 2 is responsible for visiting operation and maintenance point 4.

[0071] According to an embodiment of the present invention, in step S2, the embodiment of the present invention initializes the position of each particle in the particle swarm according to the number of points to be operated and maintained P. The step S2 described in which the number of points to be operated and maintained P is used as the particle length to initialize the position of each particle in the particle swarm includes:

[0072] S21: setting the particle length to the number P of the points to be operated and maintained;

[0073] S22: Initialize each dimension value within the particle length according to the encoding value rule, and obtain the position of particle i as x i =(x i，1 , x i，2 , …, x i，P ), where the pth (1≤p≤P) dimension value x i，p The value range is [1, P), and the precision is 1 decimal place.

[0074] In this embodiment, assuming that the number of points to be operated and maintained is P, and one unmanned boat can be equipped with K drones, the position of the i-th particle in the particle swarm is x i =(x i，1 , x i，2 , …, x i，P ). It should be understood that the pth (1≤p≤P) dimension value x i，p The value range of cannot exceed P, that is, the value interval is [1, P), and one decimal place is retained to be used for segmenting the tool pseudo sequence in the subsequent particle sequence decoding process. Exemplarily, in order to better describe the encoding strategy of the present invention, assuming that P = 9, K = 2, and randomly obtain each dimension value of the particle according to the encoding value rule, the specific encoding of the particle position is as follows Figure 3 As shown, x i =(1.4, 2.4, 3.6, 32, 2.3, 1.8, 1.9, 2.6, 2.6).

[0075] After initializing the position of each particle, execute step S3, traverse each particle, run the particle sequence decoding program to decode the position of the particle, and obtain the operation and maintenance path corresponding to the particle at the current position, and the operation and maintenance path includes the operation and maintenance path of the unmanned boat and the unmanned aerial vehicle. It should be understood that particles correspond to operation and maintenance paths one by one, and different particles decode different operation and maintenance paths, that is, different operation and maintenance paths of unmanned boats and unmanned aerial vehicles can be obtained after decoding the positions of different particles.

[0076] According to an embodiment of the present invention, the step S3 of dividing the position pseudo index and the tool pseudo index according to the position of the particle, and generating the operation and maintenance path corresponding to the particle at the current position according to the position pseudo index and the tool pseudo index includes:

[0077] S31: Divide each dimension value of the position of the particle into an integer part and a decimal part;

[0078] S32: Combining the integer part of each dimension value to form a position pseudo index, and combining the decimal part of each dimension value to form a tool pseudo index;

[0079] S33: Acquire an operation and maintenance point sequence according to the position pseudo index;

[0080] S34: Acquire an operation and maintenance tool sequence according to the tool pseudo index;

[0081] S35: Combining the operation and maintenance point sequence and the operation and maintenance tool sequence to generate a temporary path, and segmenting the operation and maintenance path of the unmanned boat and the operation and maintenance path of the drone according to the temporary path.

[0082] Among them, in step S31, according to the particle position encoding rule of the previous step S2, each dimensional value in the position of particle i is composed of an integer part and a decimal part. Correspondingly, when decoding the particle sequence, the present invention divides each dimensional value in the position of particle i into an integer part and a decimal part.

[0083] In step S32, the present invention combines the integer part of each dimension value to form a pseudo index of the location of the maintenance point to be operated, and combines the decimal part of each dimension value to form a pseudo index of the tool used for operation and maintenance. It should be understood that the operation and maintenance tools mentioned here are unmanned boats and drones. Continuing with the previous example, when the specific code of the particle position is x i =(1.4, 2.4, 3.6, 3.2, 2.3, 1.8, 1.9, 2.6, 2.6), the integer part constitutes the pseudo index of the location of the maintenance point to be operated The decimal part constitutes the tool pseudo index In order to better describe the encoding strategy of the present invention, Figure 4 A schematic diagram of a position pseudo index and a tool pseudo index provided in an embodiment of the present invention.

[0084] The operation and maintenance point sequence refers to the sequential combination with the shortest sum of distances between the operation and maintenance points in the wind farm where the unmanned boat and the drone are located. In step S33, after obtaining the position pseudo-index, this embodiment obtains the operation and maintenance point sequence in a neighborhood optimization manner based on the position pseudo-index and the principle that the operation and maintenance point of the optimal solution is always nearby, thereby obtaining the unmanned boat and drone operation and maintenance path combination with the shortest operation and maintenance time, that is, the time for the unmanned boat and the drone to perform emergency operation and maintenance of the wind farm according to the operation and maintenance point sequence is the shortest and most reasonable.

[0085] The operation and maintenance tool sequence refers to an operation and maintenance tool coding sequence generated according to the tool pseudo index. In step S34, this embodiment constructs a production group of the operation and maintenance tool according to the tool pseudo index, and then generates and obtains the operation and maintenance tool sequence through the production group.

[0086] In step S35, after obtaining the operation and maintenance point sequence in step S33 and the operation and maintenance tool sequence in step S34, the present invention further combines the operation and maintenance point sequence and the operation and maintenance tool sequence, that is, combines the dimension values ​​corresponding to the same dimension in the operation and maintenance point sequence and the operation and maintenance tool sequence as a path node; traverses all dimensions to generate a temporary path; and then divides the operation and maintenance path of the unmanned boat and the operation and maintenance path of the drone according to the temporary path. At this point, the particle sequence decoding process is completed.

[0087] According to an embodiment of the present invention, obtaining the operation and maintenance point sequence according to the position pseudo index in step S33 includes:

[0088] S331: Initialize a selected operation and maintenance point set SETA and an unselected operation and maintenance point set SETB, wherein the selected operation and maintenance point set SETA is an empty set, and the unselected operation and maintenance point set SETB includes all the points to be operated and maintained;

[0089] S332: Initialize the current operation and maintenance point PA to 0 and the dimension variable p to 1;

[0090] S333: Obtain the distance AM between the current operation and maintenance point PA and the points to be operated and maintained in the unselected operation and maintenance point set SETB, sort the distance AM from small to large, and generate an operation and maintenance point distance sequence SAM;

[0091] S334: Determine whether the unselected operation and maintenance point set SETB is an empty set, if not, execute S335, if yes, execute S337;

[0092] S335: According to the position pseudo-index and the operation and maintenance point distance sequence SAM, a new operation and maintenance point is selected to update the current operation and maintenance point PA, and the new operation and maintenance point is added to the selected operation and maintenance point set SETA, and the new operation and maintenance point is deleted from the unselected operation and maintenance point set SETB;

[0093] S336: increment the dimension variable p by 1, and return to step S333;

[0094] S337: End the iteration. When the unselected operation and maintenance point set SETB is an empty set, obtain the selected operation and maintenance point set SETA as the operation and maintenance point sequence.

[0095] The selected maintenance point set SETA is used to store the sorted maintenance points to be maintained, and the unselected maintenance point set SETB is used to store the unsorted maintenance points to be maintained. The embodiment of the present invention predefines the selected maintenance point set SETA and the unselected maintenance point set SETB, initializes the selected maintenance point set SETA to an empty set, and the unselected maintenance point set SETB contains all the maintenance points to be maintained. The initial point is used as the starting position, which is defined as 0, that is, the current maintenance point PA is initialized to 0, and the dimension variable p starts from 1.

[0096] The operation and maintenance point distance sequence SAM is used to store the distance between the current operation and maintenance point PA and the points to be operated and maintained in the unselected operation and maintenance point set SETB. This embodiment traverses each point to be operated and maintained in the unselected operation and maintenance point set SETB, calculates the distance AM between the current operation and maintenance point PA and the points to be operated and maintained, and obtains a total of several distances AM; then sorts them from small to large, thereby generating the operation and maintenance point distance sequence SAM.

[0097] Determine whether the unselected operation and maintenance point set SETB is an empty set. If not, select a new operation and maintenance point NP according to the position pseudo index and the operation and maintenance point distance sequence SAM. Specifically, when selecting a new operation and maintenance point NP, obtain the value of the pth dimension on the position pseudo index according to the dimension variable p. Then take the value on the pth dimension As an index, according to the index, the value on the index is obtained from the operation and maintenance point distance sequence SAM as a new operation and maintenance point NP, and the new operation and maintenance point NP is added to the selected operation and maintenance point set SETA, and the new operation and maintenance point NP is deleted from the unselected operation and maintenance point set SETB, so that the current operation and maintenance point PA = NP, p = p + 1, and the above steps S333, S334, and S335 are repeated. When the unselected operation and maintenance point set SETB becomes an empty set, the selected operation and maintenance point set SETA is used as the operation and maintenance point sequence

[0098] For ease of understanding, continue with the position pseudo index described above and tools pseudo index As an example, the selected operation and maintenance point set SETA is initialized as an empty set, and the unselected operation and maintenance point set SETB contains all the points to be operated and maintained, that is, SETB={1,2,3,4,5,6,7,8,9}, current operation point PA=0, p=1. The distance AM between the current operation point PA=0 and each operation point in the unselected operation point set SETB is calculated and sorted to generate the operation point distance sequence SAM. Then, according to the position pseudo index In Select the vertex 3 in the first row from the operation and maintenance point distance sequence SAM as the new operation and maintenance point NP, that is, NP=3, update the selected operation and maintenance point set SETA={3}, and update the unselected operation and maintenance point set SETB={1,2,4,5,6,7,8,9}, and set the current operation and maintenance point PA=NP=3, p=p+1=2. Then, repeat the above steps until the unselected operation and maintenance point set SETB becomes an empty set. For ease of understanding, Figure 5 A flowchart for obtaining an operation and maintenance point sequence according to a location pseudo index provided in an embodiment of the present invention.

[0099] According to an embodiment of the present invention, the step S34 of acquiring the operation and maintenance tool sequence according to the tool pseudo index includes:

[0100] S341: construct a generative group of operation and maintenance tools according to the number K of drones carried by each unmanned boat and the number P of points to be operated and maintained;

[0101] S342: Obtain the operation and maintenance tool coding information corresponding to each dimension value in the tool pseudo index through the generation formula group of the operation and maintenance tool;

[0102] S343: Traverse each dimension value in the tool pseudo index to generate an operation and maintenance tool sequence.

[0103] The generative group of the operation and maintenance tool is used to calculate the operation and maintenance tool coding information according to each dimension value on the tool pseudo index. Assuming that the number of points to be operated and maintained is P, and the number of drones carried by each unmanned boat is K, the generative group of the operation and maintenance tool is:

[0104]

[0105] in, Indicates that the operation and maintenance services are performed by unmanned boats; They represent the operation and maintenance services provided by drones 1, 2, …, K respectively; Indicates that this point is the meeting point of the unmanned boat and all drones, and by default, this point is served by the unmanned boat. It should be noted that the present invention constrains the unmanned boat to arrive at the first point before it can leave with the drone. Here, the first point reached is considered as the meeting point, so At the same time, the constraint of the present invention requires that at the last operation and maintenance point, all drones and unmanned boats need to converge before returning to the port, so

[0106] When obtaining the operation and maintenance tool sequence according to the tool pseudo index, the present invention substitutes the number of drones K carried by each unmanned boat and the number of points to be operated and maintained P into the generative group of the above-mentioned operation and maintenance tools, and then traverses each dimension p and dimension value in the tool pseudo index Obtain a corresponding production formula from the production formula group of the operation and maintenance tool, and obtain the operation and maintenance tool coding information corresponding to the dimension p according to the production formula; combine the operation and maintenance tool coding information corresponding to each dimension value in the tool pseudo index to generate an operation and maintenance tool sequence.

[0107] For ease of understanding, continue with the position pseudo index described above and tools pseudo index For example, the number of drones carried by each unmanned boat K = 2 and the number of points to be operated and maintained P = 9 are substituted into the generative group of the above operation and maintenance tool, and we can get:

[0108]

[0109] According to the tool pseudo index Substitute each dimension value into the corresponding generative formula to obtain the operation and maintenance tool sequence:

[0110] According to an embodiment of the present invention, the step S35 of combining the operation and maintenance point sequence and the operation and maintenance tool sequence to generate a temporary path, and segmenting the operation and maintenance path of the unmanned boat and the operation and maintenance path of the drone according to the temporary path includes:

[0111] S351: A node is formed by using the dimension values ​​on the same dimension in the operation and maintenance point sequence and the operation and maintenance tool sequence to generate a temporary path;

[0112] S352: Acquire all nodes whose operation and maintenance tool coding information is the unmanned boat from the temporary path, and generate a first node sequence;

[0113] S353: adding a starting node consisting of the departure port and the operation and maintenance tool coding information of the unmanned boat to the front end and the rear end of the acquired first node sequence respectively, to generate an operation and maintenance path of the unmanned boat;

[0114] S354: Dividing the temporary path into a plurality of segmented paths according to the operation and maintenance tool coding information of the unmanned boat;

[0115] S355: For each segmented path, extract a corresponding operation and maintenance path for each drone.

[0116] Among them, in step S351, this embodiment first obtains the dimension values ​​on the same dimension in the operation and maintenance point sequence and the operation and maintenance tool sequence, combines the dimension values ​​on the same dimension to form a node, and combines the nodes on all dimensions to generate a temporary path. and operation and maintenance tool sequence The dimension values ​​combined on the same dimension form a node, that is, So as to get the temporary path

[0117] In step S352, according to the operation and maintenance tool coding information of the unmanned boat, this embodiment extracts all nodes whose operation and maintenance tool coding information is the unmanned boat from the temporary path to obtain a first node sequence. It means that the operation and maintenance services are provided by unmanned boats. Indicates the meeting point of the unmanned boat and the drone, so from the temporary path Extract all and , and obtain the first node sequence ((3,3),(2,0),(8,3),(9,3),(6,3)).

[0118] Among them, in step S353, since the unmanned boat departs from the port and returns to the port, this embodiment adds the starting node (0, 3) composed of the departure port and the operation and maintenance tool coding information of the unmanned boat at the front and back ends of the obtained first node sequence, respectively, to generate the operation and maintenance path of the unmanned boat. Continuing with the previous example, for the obtained first node sequence ((3, 3), (2, 0), (8, 3), (9, 3), (6, 3)), this embodiment adds the starting node (0, 3) at the beginning and end of the first node sequence, thereby obtaining the operation and maintenance path of the unmanned boat.

[0119] In step S354, this embodiment divides the temporary path into a plurality of segmented paths according to the operation and maintenance tool coding information of the unmanned boat. definition As a separator, the temporary path Divided into three segmented paths, namely: the first segmented path Second segment path The third segment path

[0120] In step S355, this embodiment analyzes each segmented path and extracts the service path corresponding to each drone. It should be understood that the segmented path may not have a service path for the drone after extraction.

[0121] According to an embodiment of the present invention, extracting a corresponding operation and maintenance path for each segmented path and each drone in step S355 includes:

[0122] S3551: In a segmented path, traverse the operation and maintenance tool coding information of each drone, extract corresponding nodes from the segmented path, and generate a second node sequence;

[0123] S3552: Add the first node in the segmented path to the head of the second node sequence, and add the tail node to the tail of the second node sequence to generate an operation and maintenance path for the drone.

[0124] In this embodiment, for a segmented path, this embodiment traverses the operation and maintenance tool coding information of each drone, extracts all nodes including the operation and maintenance tool coding information of the drone from the segmented path, obtains a second node sequence, and adds the head and tail nodes of the segmented path to the head and tail of the second node sequence, thereby obtaining a service path for the drone.

[0125] Following the previous example, the first segment path is obtained after segmentation Second segment path The third segment path First extract the first segment path All nodes whose operation and maintenance tool coding information is "1" in the , and combined with its head and tail nodes to obtain the first operation and maintenance path of drone k = 1 Next, extract the first segment path All nodes whose operation and maintenance tool code information is "2" in the , and combined with the head and tail nodes to obtain the first operation and maintenance path of drone k = 2 Similarly, analyze the third segment path The second operation and maintenance path of drone k=2 can be obtained It should be noted that the second segment path There is no node with the operation and maintenance tool code information of "1" or "2", so there is no operation and maintenance path for drone k=1 and drone k=2. For ease of understanding, Figure 6 A schematic diagram of a process for obtaining an operation and maintenance path of a drone provided in an embodiment of the present invention.

[0126] At this point, the particle sequence decoding program has completed decoding the position of the particles and obtained the operation and maintenance paths of the unmanned boat and the drone.

[0127] Since particles correspond to operation and maintenance paths one by one, that is, different service paths of unmanned boats and drones can be obtained after the positions of different particles are decoded. The present invention further calculates the fitness of particles according to the decoded operation and maintenance paths.

[0128] According to an embodiment of the present invention, the step S4 of calculating the fitness of particles according to the running speed and running time of the unmanned boat and the unmanned aerial vehicle includes:

[0129] S41: obtaining the nodes passed by the unmanned boat, the distance between the nodes, and the running speed of the unmanned boat according to the operation and maintenance path corresponding to the particle at the current position, and generating the running time of the unmanned boat;

[0130] S42: obtaining the nodes passed by the drone, the distance between the nodes, and the running speed of the drone according to the operation and maintenance path corresponding to the particle at the current position, and generating the running time of the drone;

[0131] S43: obtaining the nodes passed by the unmanned boat and the unit time of the wind turbine operated by the unmanned boat according to the operation and maintenance path corresponding to the particle at the current position, and generating the operation and maintenance time of the unmanned boat;

[0132] S44: obtaining the nodes passed by the drone and the unit time of the drone operating the wind turbine according to the operation and maintenance path corresponding to the particle at the current position, and generating the operation and maintenance time of the drone;

[0133] S45: Obtain the sum of the operating time of the unmanned boat, the operating time of the drone, the operation and maintenance time of the unmanned boat, and the operation and maintenance time of the drone as the fitness of the particle.

[0134] In order to cope with emergency situations, this embodiment aims to minimize the total driving time.

[0135] Among them, the operating time of the unmanned boat is the time required for the unmanned boat to travel between the operation and maintenance points.

[0136] As an example, in step S41, this embodiment calculates the number of points to be operated and maintained that the unmanned boat passes through and the distance d between the points. v，v′ , the unmanned boat running speed c1, calculate the unmanned boat running time T y1 The calculation formula is:

[0137] The operating time of the drone is the time required for the drone to travel between the operation and maintenance points.

[0138] As an example, in step S42, this embodiment calculates the distance d between the points to be operated and maintained that the drone passes through. v，v′ , the UAV running speed c2, calculate the running time T of the unmanned boat y2 The calculation formula is:

[0139] Among them, the operation and maintenance time of the unmanned boat is the time required for the unmanned boat to perform operation and maintenance tasks between the operation and maintenance points.

[0140] As an example, in step S43, this embodiment calculates the operation and maintenance time T of the unmanned boat according to the operation and maintenance point to be operated and maintained at the unmanned boat and the unit time T1 required for the unmanned boat to operate and maintain the wind turbine. y3 The calculation formula is: T y3 =∑ v ∑ v′ ∑ m r m，v，v ′T1,

[0141] The operation and maintenance time of the drone is the time required for the drone to perform the operation and maintenance task at the operation and maintenance point.

[0142] As an example, in step S44, this embodiment calculates the maintenance time T of the drone according to the maintenance point to be maintained where the drone performs the maintenance task and the unit time T2 required for the drone to maintain the wind turbine. y4 The calculation formula is: T y4 =∑ v ∑ v′ ∑ m ∑ k ∑ l s m，k，l，v，v′ , T2,

[0143] The goal of the present invention is to minimize the total time. Therefore, in step S45, the present invention obtains the sum of the operating time of the unmanned boat, the operating time of the drone, the operation and maintenance time of the unmanned boat, and the operation and maintenance time of the drone as the fitness of the particle, and the calculation formula is:

[0144]

[0145] Here, V represents the set of all nodes, V = C ∪ {0, P + 1}, where 0 represents the port as the starting point and P + 1 represents the port as the end point; v, v' represent the index of the maintenance point, v = 0, 1, ..., P + 1v' = 0, 1, ..., P + 1. H' represents the maximum endurance of the drone; H represents the maximum driving distance of the unmanned boat; L represents the maximum number of launches of each drone; l represents the index of the number of drone launches, l = 1, 2, ..., L.

[0146] The embodiment of the present invention takes into account the maximum driving distance constraint of the unmanned boat and the maximum range constraint of the unmanned aerial vehicle, which are respectively shown in the following formulas:

[0147]

[0148] This embodiment traverses all particles, executes the above steps S41 to S45, obtains the fitness corresponding to each particle, obtains the particle with the smallest fitness value as the global optimal particle, and records the global optimal particle and its corresponding operation and maintenance path.

[0149] According to an embodiment of the present invention, the use of the MPSO algorithm to update the position of each particle in the particle swarm in step S5 includes:

[0150] Step S51, updating the inertia weight of the particle.

[0151] At the tth iteration, the adaptive update formula of the inertia weight w is as follows:

[0152]

[0153] Among them, w min is the minimum value of the inertia weight, which is 0.4; w max is the maximum value of the inertia weight, which is 0.9; T max is the maximum number of iterations of the algorithm; r(t) is a random number generated by chaotic logic, and the calculation formula is as follows:

[0154] r(t)=4r(t)·(1-r(t))

[0155] Where r(0) is a random number from uniform distribution U(0,1).

[0156] Step S52, updating the velocity of the particle.

[0157] Calculate the SPbest of the i-th particle at time t

[0158]

[0159] Among them, CPbest(t) is the individual optimal position of the particle with the smallest fitness value fit among the individual optimal values ​​of all particles at time t; fit CPbest is the fitness value of CPbest(t); is the individual optimal position Pbest of the i-th particle i The fitness value of .

[0160] Calculate the average particle position Mbest(t) at time t. The calculation formula is as follows:

[0161]

[0162] in, is the value of the first dimension of the individual optimal position Pbest of the i-th particle, is the value of the pth dimension of the ith particle; N is the number of particles.

[0163] The particle's velocity adaptive update is given by the following formula:

[0164]

[0165] Among them, c1 and c2 are constants with a value of 2; r1 and r2 are both random numbers on the uniform distribution U(0,1).

[0166] Step S53, updating the position of the particle.

[0167] Each particle updates its current position X by learning the global optimal position solution Gbest i The new position update formula is as follows,

[0168]

[0169] Among them, rand is a random number uniformly distributed on U(0,1); Gbest is the global optimal solution, that is, the position with the minimum fitness value during the iteration process; p i The calculation formula is as follows:

[0170]

[0171] where fit Xi(t) is the fitness value of the ith particle at time t.

[0172] This embodiment traverses each particle in the particle group, executes the above steps S61 to S63 respectively, and updates the position of the particle. Then, it is determined whether the number of iterations reaches the preset number threshold. If so, the updated global optimal particle and its corresponding operation and maintenance path are output to dispatch the unmanned boat and the drone; if not, it returns to step S3, traverses each particle, and divides the position pseudo-index and the tool pseudo-index according to the position of the particle, and generates the operation and maintenance path corresponding to the particle at the current position according to the position pseudo-index and the tool pseudo-index.

[0173] The present invention realizes the emergency operation and maintenance path planning of the wind farm. By shortening the coding length of particles and introducing position pseudo-indexes for neighborhood search, the path planning time is shortened and the path planning speed is improved. The problems of low path planning efficiency and long emergency time in the prior art when performing emergency operation and maintenance on wind farms are effectively solved, and the emergency operation and maintenance needs of offshore wind farms can be met.

[0174] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0175] In one embodiment, the present invention further provides a wind farm emergency operation and maintenance device, which corresponds one-to-one to the wind farm emergency operation and maintenance method in the above embodiment. Figure 7 As shown, the functional modules of the wind farm emergency operation and maintenance device are described in detail as follows:

[0176] The acquisition module 11 is used to obtain the number of particles N in the particle swarm, and respectively set the number of unmanned boats M, the number of drones carried by each unmanned boat K, and the number of points to be operated and maintained P;

[0177] The encoding module 12 is used to initialize the position of each particle in the particle group by taking the number P of the points to be operated and maintained as the particle length;

[0178] A decoding module 13 is used to traverse each particle, divide the position pseudo index and the tool pseudo index according to the position of the particle, and generate an operation and maintenance path corresponding to the particle at the current position according to the position pseudo index and the tool pseudo index;

[0179] The optimization module 14 is used to calculate the fitness of the particles according to the running speed and running time of the unmanned boat and the unmanned aerial vehicle, obtain the global optimal particle according to the fitness of the particle, and record the global optimal particle and its corresponding operation and maintenance path;

[0180] An updating module 15 is used to update the position of each particle in the particle swarm by using an MPSO algorithm;

[0181] The judgment module 16 is used to judge whether the number of iterations reaches a preset number threshold. If so, it outputs the updated global optimal particle and its corresponding operation and maintenance path to dispatch the unmanned boat and the unmanned aerial vehicle; if not, it returns to the decoding module.

[0182] For the specific definition of the wind farm emergency operation and maintenance device, please refer to the definition of the wind farm emergency operation and maintenance method above, which will not be repeated here. Each module in the above-mentioned wind farm emergency operation and maintenance device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0183] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a wind farm emergency operation and maintenance method is implemented.

[0184] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0185] S1: Get the number of particles N in the particle swarm, set the number of unmanned boats M, the number of drones carried by each unmanned boat K, and the number of points to be operated and maintained P;

[0186] S2: Using the number of points to be operated and maintained P as the particle length, the position of each particle in the particle swarm is initialized;

[0187] S3: traverse each particle, divide the position pseudo index and the tool pseudo index according to the position of the particle, and generate the operation and maintenance path corresponding to the particle at the current position according to the position pseudo index and the tool pseudo index;

[0188] S4: Calculate the fitness of the particles according to the running speed and running time of the unmanned boat and the drone, obtain the global optimal particle according to the fitness of the particle, and record the global optimal particle and its corresponding operation and maintenance path;

[0189] S5: Use the MPSO algorithm to update the position of each particle in the particle swarm;

[0190] S6: Determine whether the number of iterations reaches a preset threshold. If so, output the updated global optimal particle and its corresponding operation and maintenance path to dispatch the unmanned boat and the unmanned aerial vehicle; if not, return to step S3.

[0191] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0192] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0193] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A wind farm emergency operation and maintenance method, characterized in that: The method comprises: S1: Get the number of particles N in the particle swarm, set the number of unmanned boats M, the number of drones carried by each unmanned boat K, and the number of points to be operated and maintained P respectively; S2: Using the number of points to be operated and maintained P as the particle length, the position of each particle in the particle swarm is initialized; S3: traverse each particle, divide the position pseudo index and the tool pseudo index according to the position of the particle, and generate the operation and maintenance path corresponding to the particle at the current position according to the position pseudo index and the tool pseudo index; S4: Calculate the fitness of the particles according to the running speed and running time of the unmanned boat and the drone, obtain the global optimal particle according to the fitness of the particle, and record the global optimal particle and its corresponding operation and maintenance path; S5: Use the MPSO algorithm to update the position of each particle in the particle swarm; S6: Determine whether the number of iterations reaches a preset threshold. If so, output the updated global optimal particle and its corresponding operation and maintenance path to dispatch the unmanned boat and the unmanned aerial vehicle; if not, return to step S3.

2. The wind farm emergency operation and maintenance method according to claim 1, characterized in that: The step of using the number of points to be operated and maintained P as the particle length and initializing the position of each particle in the particle swarm includes: The particle length is set to the number P of the points to be operated and maintained; Initialize each dimension value within the particle length according to the encoding value rule, and get the position of particle i as x i =(x i，1 , x i，2 , …, x i，P ), where the pth (1≤p≤P) dimension value x i，p The value range is [1, P), and the precision is 1 decimal place.

3. The wind farm emergency operation and maintenance method according to claim 1 or 2, characterized in that: The step of dividing the position pseudo index and the tool pseudo index according to the position of the particle, and generating the operation and maintenance path corresponding to the particle at the current position according to the position pseudo index and the tool pseudo index comprises: Divide each dimension value of the position of the particle into an integer part and a decimal part; The integer part of each dimension value is combined to form a position pseudo index, and the decimal part of each dimension value is combined to form a tool pseudo index; Acquire an operation and maintenance point sequence according to the position pseudo index; Acquire an operation and maintenance tool sequence according to the tool pseudo index; The operation and maintenance point sequence and the operation and maintenance tool sequence are combined to generate a temporary path, and the operation and maintenance path of the unmanned boat and the operation and maintenance path of the unmanned aerial vehicle are segmented according to the temporary path.

4. The wind farm emergency operation and maintenance method according to claim 3, characterized in that: The acquiring of the operation and maintenance point sequence according to the position pseudo index comprises: S331: Initialize a selected operation and maintenance point set SETA and an unselected operation and maintenance point set SETB, wherein the selected operation and maintenance point set SETA is an empty set, and the unselected operation and maintenance point set SETB includes all the points to be operated and maintained; S332: Initialize the current operation and maintenance point PA to 0 and the dimension variable p to 1; S333: Obtain the distance AM between the current operation and maintenance point PA and the points to be operated and maintained in the unselected operation and maintenance point set SETB, sort the distance AM from small to large, and generate an operation and maintenance point distance sequence SAM; S334: Determine whether the unselected operation and maintenance point set SETB is an empty set, if not, execute S335, if yes, execute S337; S335: According to the position pseudo-index and the operation and maintenance point distance sequence SAM, a new operation and maintenance point is selected to update the current operation and maintenance point PA, and the new operation and maintenance point is added to the selected operation and maintenance point set SETA, and the new operation and maintenance point is deleted from the unselected operation and maintenance point set SETB; S336: increment the dimension variable p by 1, and return to step S333; S337: End the iteration. When the unselected operation and maintenance point set SETB is an empty set, obtain the selected operation and maintenance point set SETA as the operation and maintenance point sequence.

5. The wind farm emergency operation and maintenance method according to claim 3, characterized in that: The acquiring of the operation and maintenance tool sequence according to the tool pseudo index comprises: According to the number of drones K carried by each unmanned boat and the number of points to be operated and maintained P, a generative group of operation and maintenance tools is constructed; For each dimension value in the tool pseudo index, obtain the operation and maintenance tool coding information corresponding to the dimension through the generation formula group of the operation and maintenance tool; Each dimension value in the tool pseudo index is traversed to generate an operation and maintenance tool sequence.

6. The wind farm emergency operation and maintenance method according to claim 3, characterized in that: The step of combining the operation and maintenance point sequence and the operation and maintenance tool sequence to generate a temporary path, and segmenting the operation and maintenance path of the unmanned boat and the operation and maintenance path of the drone according to the temporary path includes: A node is formed by using the dimension values ​​on the same dimension in the operation and maintenance point sequence and the operation and maintenance tool sequence to generate a temporary path; Acquire all nodes whose operation and maintenance tool coding information is the unmanned boat from the temporary path, and generate a first node sequence; Adding a starting node consisting of the departure port and the operation and maintenance tool coding information of the unmanned boat to the front end and the rear end of the obtained first node sequence respectively, to generate an operation and maintenance path of the unmanned boat; Dividing the temporary path into a plurality of segmented paths according to the operation and maintenance tool coding information of the unmanned boat; For each segmented path, the corresponding operation and maintenance path is extracted for each UAV.

7. The wind farm emergency operation and maintenance method according to claim 6, characterized in that: For each segmented path, extracting the corresponding operation and maintenance path for each drone includes: In a segmented path, traverse the operation and maintenance tool coding information of each drone, extract corresponding nodes from the segmented path, and generate a second node sequence; The first node in the segmented path is added to the head of the second node sequence, and the tail node is added to the tail of the second node sequence to generate an operation and maintenance path for the drone.

8. The wind farm emergency operation and maintenance method according to claim 1, characterized in that: The calculation of the fitness of particles according to the running speed and running time of the unmanned boat and the unmanned aerial vehicle includes: According to the operation and maintenance path corresponding to the particle at the current position, the nodes passed by the unmanned boat, the distance between the nodes and the running speed of the unmanned boat are obtained respectively, and the running time of the unmanned boat is generated; According to the operation and maintenance path corresponding to the particle at the current position, the nodes passed by the drone, the distance between nodes and the running speed of the drone are obtained respectively, and the running time of the drone is generated; According to the operation and maintenance path corresponding to the particle at the current position, the nodes passed by the unmanned boat and the unit time of the unmanned boat for operating the wind turbine are obtained respectively, and the operation and maintenance time of the unmanned boat is generated; According to the operation and maintenance path corresponding to the particle at the current position, the nodes passed by the drone and the unit time of the drone's operation and maintenance of the wind turbine are obtained respectively, and the operation and maintenance time of the drone is generated; The sum of the operating time of the unmanned boat, the operating time of the drone, the operation and maintenance time of the unmanned boat, and the operation and maintenance time of the drone is calculated as the fitness of the particle.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the wind farm emergency operation and maintenance method according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the wind farm emergency operation and maintenance method according to any one of claims 1 to 8 is implemented.

Images