Offshore wind turbine operation and maintenance scheduling method and system considering working hour utilization

Abstract

The invention discloses an offshore wind turbine operation and maintenance scheduling method and system considering man-hour utilization, and relates to the technical field of offshore wind plant multi-operation and maintenance task scheduling. The improved genetic algorithm is designed in combination with the operation and maintenance operation characteristics of the offshore wind plant, the advantages and disadvantages of the scheduling scheme are objectively and accurately evaluated by means of a fitness function, the powerful advantages of the improved genetic algorithm are fully played, and the scheduling scheme is continuously optimized and intelligently selected. According to the method, an initial population is formed by randomly generating a specified number of individuals, and the fitness value of each individual of the population is calculated; selecting parent individuals by adopting a probability-driven roulette method, and performing cross inheritance and mutation operation with an elitist retention strategy to ensure that high-quality individuals stably enter a next-generation population. And when the optimal individual fitness value of the population is not effectively improved in the preset evolution algebra, catastrophe operation is started, and new gene combinations and individuals are introduced, so that the diversity of the population is effectively improved, and the stiffness of falling into local optimum is broken.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-operation and maintenance task scheduling for offshore wind farms, and particularly relates to a method and system for scheduling the operation and maintenance of offshore wind turbines considering working hours utilization. Background Art

[0002] With the continuous growth of the global demand for clean energy, offshore wind power, relying on its rich resource base and huge development potential, is entering a new stage of rapid scale expansion. In regions such as the eastern coastal areas of China and the North Sea in Europe, large-scale offshore wind farms are springing up. These wind farms often deploy a large number of wind turbines, ranging from hundreds to thousands, and are widely distributed in vast sea areas with an extremely wide coverage. However, the marine environment where offshore wind turbines are located is extremely complex, changeable and harsh. Severe conditions such as strong winds, huge waves, and high salt fog frequently attack, resulting in offshore wind turbines being more prone to failure and having a faster performance degradation rate compared to onshore wind turbines. This undoubtedly brings greater difficulty and higher cost to the operation and maintenance work of offshore wind farms.

[0003] The operation and maintenance of offshore wind turbines not only highly depend on professional ships and equipment, but also must be carried out within a limited suitable weather window and are strictly restricted by various factors such as marine meteorological conditions and tides. In addition, the repair of offshore wind turbines requires professional technical personnel as well as specific repair tools and spare parts. However, in actual operation, the allocation and transportation of these resources face many challenges. For example, if the spare parts inventory management is improper, it may lead to delays in repair work, thereby increasing the operation and maintenance costs. Therefore, how to comprehensively consider various influencing factors and scientifically and reasonably optimize the scheduling of the operation and maintenance of offshore wind turbines has become an urgent technical problem in this field.

[0004] For the problem of multi-operation and maintenance task scheduling in offshore wind farms, there are mainly three types of related technical solutions at present:

[0005] (1) Scheduling methods based on empirical rules; they are highly subjective and lack sufficient quantitative basis: This method completely relies on the personal experience and subjective judgment of operation and maintenance personnel, lacking scientific quantitative analysis and systematic planning. Due to the differences in the experience and judgment criteria of different operation and maintenance personnel, this may lead to inconsistencies and irrationalities in the scheduling results. In the face of the situation where multiple wind turbines in a large-scale offshore wind farm fail simultaneously or there are various complex combinations of failures, this method is difficult to quickly and accurately determine the optimal operation and maintenance sequence and resource allocation plan. This may lead to unreasonable resource allocation, delays in the repair of some wind turbines, while other wind turbines over-occupy resources, thus increasing the overall downtime and operation and maintenance costs of the wind turbines.

[0006] (2) Traditional mathematical programming model scheduling method; Offshore wind turbine operation and maintenance involve many factors, including the operation status of wind turbines, marine environment, operation and maintenance resources, etc. Constructing an accurate mathematical programming model requires considering a large number of variables and complex constraint conditions, which makes the model construction and solution process very complex and the computational workload huge. Sometimes there may even be no solution or the solution time is too long, making it difficult to meet the timeliness requirements of actual operation and maintenance. Once the model is constructed, its structure and parameters are relatively fixed, making it difficult to adapt to the changing situations in the offshore wind power system. For example, new changes in the types of wind turbine failures, dynamic adjustments of operation and maintenance resources, or sudden anomalies in the marine environment all require reconstructing and solving the model, which increases the difficulty and cost of operation and maintenance management.

[0007] (3) Traditional genetic algorithm scheduling method; When dealing with the scheduling problem of offshore wind turbine operation and maintenance, due to the limitations of chromosome coding methods and genetic operations, ordinary genetic algorithms may require a large number of iterations to converge to a relatively optimal solution. The selection, crossover, and mutation operations of ordinary genetic algorithms may lead to a continuous decline in population diversity, causing the algorithm to converge prematurely to a local optimal solution and unable to find the global optimal operation and maintenance scheduling plan. When dealing with the scheduling problem of offshore wind turbine operation and maintenance, ordinary genetic algorithms ignore more possibilities during the round-trip process of the operation and maintenance ship and lack the function of local search for the round-trip of the operation and maintenance ship, which limits its effectiveness in practical applications. Summary of the Invention

[0008] The object of the present invention is to propose an offshore wind turbine operation and maintenance scheduling method and system considering work-hour utilization, improve the efficiency of wind farm operation and maintenance operations, increase the power generation and work-hour utilization efficiency of the wind farm, and reduce the consumption of operation and maintenance costs.

[0009] According to the first aspect of the embodiments of the present disclosure, an offshore wind turbine operation and maintenance scheduling method considering work-hour utilization is provided, including the following steps:

[0010] Obtain the information required for the wind farm operation and maintenance scheduling, where the information includes the general situation of the wind farm, details of the operation and maintenance tasks, and operation and maintenance resource data;

[0011] Preprocess the information, including numbering and discretizing the operation and maintenance ships and task wind turbines, and setting the operation and maintenance task types as variables;

[0012] Use the task wind turbine and operation and maintenance ship numbers as the gene content to form a chromosome individual M s , and form a population M;

[0013] Decode the individuals in the population into the operation and maintenance scheduling plans they represent, and take the decoded sequences of each individual as the object to evaluate the fitness values of all individuals in the population. The lower the fitness value, the closer the individual is to the optimal solution;

[0014] Select the optimal individual of the population based on the individual fitness value, and optimize it using the hill climbing algorithm with this individual as the object;

[0015] Use the roulette wheel method driven by probability to select parental individuals in the population;

[0016] For the selected parental individuals, perform crossover operations with the elite retention strategy on individuals that meet the crossover probability P j After the crossover operation, compare the fitness values of the parents and offspring, and implement elite individual screening; perform mutation operations on individuals that meet the mutation probability P b using the gene transposition method;

[0017] When the optimal individual of the population has not been optimized within the preset number of evolutionary generations, initiate the catastrophe optimization operation;

[0018] Obtain the optimal individual of the population, and the operation and maintenance scheduling plan it represents is the final application plan.

[0019] In one of the embodiments, the operation and maintenance task types are variably set, including characteristic variables related to the operation and maintenance ship, the operation and maintenance team, and the task wind turbines. The characteristic variables related to the operation and maintenance ship include: the total voyage segment characteristic variable x ijt , the first task voyage segment characteristic variable s ijt , the task wind turbine combination voyage segment characteristic variable e ijt , the return voyage segment characteristic variable b ijt , the status characteristic variable The service wind turbine status characteristic variable The characteristic variables related to the operation and maintenance team include: the service wind turbine status characteristic variable The characteristic variables related to the task wind turbines include: the combined status characteristic variable r ijt , the man-hour consumption characteristic variable T it .

[0020] In one of the embodiments, the operation and maintenance scheduling plan is encoded using the non-repeating natural number encoding method, and the chromosome individual M s is composed of the task wind turbine and operation and maintenance ship numbers as gene content, and the task wind turbine and operation and maintenance ship numbers appear only once; the chromosome individual M s represents the operation and maintenance scheduling plan, which includes the service scope of the operation and maintenance ship for the wind turbines and the operation sequence of the task wind turbines. Among them, the task wind turbines between two operation and maintenance ship numbers are the service scope of the operation and maintenance ship with a higher order, and the operation sequence of the task wind turbines is determined according to the encoding sequence;

[0021] The decoding process of the individuals in the population includes the selection of the service wind turbines by the operation and maintenance ship, the first task, the combination of the task wind turbines, and the return journey; let M s be the s-th chromosome in the population; The set of wind turbines that need services for the operation and maintenance vessel k; They are M respectively s The set of wind turbines that the operation and maintenance vessel k needs to service on the t-th day represented, the number of teams carried, the set of wind turbines for the first mission, the optimal path for the first mission, the set of wind turbines that the team is currently operating and maintaining, the sequence of task wind turbine combinations, the set of wind turbines for the return journey, and the optimal path for the return journey;

[0022] In the two stages of the first mission and the return journey, the branch and bound search method is embedded. This method is based on minimizing the sailing cost, and or Taking the wind turbine elements as the content, several sets of first mission or return journey plans are generated. The above plan sets are used as the nodes of the search tree, and the cumulative sailing distance of the operation and maintenance vessel for each plan is used as the upper bound value of each node. If the upper bound value of a certain node in the calculation process is equal to or greater than the upper bound value of the current optimal node, the child nodes of this node will no longer be generated;

[0023] Population initialization method: In one embodiment, a task combination strategy is introduced to comprehensively consider the work-hour utilization efficiency of the operation and maintenance team. The associated variables of the task combination strategy are the segment feature variable e of the task wind turbine combination ijt and the combination status feature variable r ijt , and the preset known quantity is the task combination threshold R A , when e ijt =1, the wind turbines i and j in the task are combined. The wind turbine numbered i in the first mission set is postponed one place backward to the last order of the first mission and is recorded in the operation and maintenance schedule plan for the t-th day. Conversely, when e ijt =0, the wind turbines i and j are not combined, and the wind turbine numbered j is postponed one place backward to the last order.

[0024] In one embodiment, the fitness value of an individual is:

[0025]

[0026] Among them, D ij represents the sailing distance between the wind turbines i and j, in kilometers; C J represents the sailing cost per unit distance of the operation and maintenance vessel, in yuan / km; G i represents the fault status of the wind turbine i. If it is a shutdown fault, then G i =1, conversely G i =0; W represents the average output power of the wind turbine, in kWh; C E represents the cost per unit of electricity, in yuan / kWh; L i represents the total duration from the start of the operation and maintenance cycle to the completion of the operation and maintenance of the wind turbine i, in hours; C BIt represents the daily rental cost of a single operation and maintenance vessel, with the unit of yuan / day; C R It represents the average daily labor cost of a single operation and maintenance team, with the unit of yuan / team; T represents the total number of days of the operation and maintenance cycle, with the unit of day; N represents the set of task wind turbine numbers N = {1, 2,..., n}; K represents the set of operation and maintenance vessel numbers K = {1, 2,..., v}; M represents the set of operation and maintenance team numbers M = {1, 2,..., p}.

[0027] In one embodiment, a roulette wheel method driven by probability is used to select parental individuals in the population as follows:

[0028] Obtain the individual M in the population s The reciprocal of the fitness value

[0029] Take the ratio of the reciprocal of the individual fitness value to the sum of the reciprocal of the fitness values of the population individuals as the selection probability P(M s ) of the individual M s );

[0030] In the order of the population, use the cumulative method of the probability P(M s ) to determine the area R occupied by the individual M s between 0 and 1, generate a random number within the interval [0, 1], and select the individual corresponding to its area as the parental individual. s

[0031] In one embodiment, the elite retention strategy includes two stages: crossover operation and elite individual screening; in the crossover operation stage, a random region gene crossover method is adopted. By generating two non-repeating random numbers within the interval [0, individual gene length] to confirm the crossover interval, the parental individual genes are divided into the anterior gene of the crossover interval, the gene of the crossover interval, and the posterior gene of the crossover interval; during the crossover process of the parental individual genes, the anterior gene of the crossover interval is directly inherited to the offspring individual, and the gene of the crossover interval and the posterior gene of the crossover interval are compared with the existing genes of the corresponding offspring. If there are duplicate genes, they are postponed backward, otherwise, they are directly inherited into the offspring individual, and then a complete offspring individual is obtained;

[0032] The elite individual screening stage is after the crossover operation stage. By comparing the fitness of all individuals in the crossover process, compare the fitness of all parents and offspring, and select the two best individuals among them to replace the offspring individuals and inherit them to the next generation to ensure the inheritance of high-quality genes in the population.

[0033] In one embodiment, for the mutation operation, for the parental individuals that meet the mutation probability P b , use the gene transposition method to generate two random numbers within the interval [0, individual gene length] as the mutation sites, and swap their gene positions; ​

[0034] The catastrophic optimization operation is to select a certain proportion of non-repetitive better and worse individuals from the population. At the same time, the same number of new individuals as the unselected individuals are randomly generated, and the new individuals and the selected individuals are combined into a new population to replace the original population and continue the evolutionary iteration.

[0035] According to the second aspect of the embodiments of the present disclosure, a maintenance scheduling system for offshore wind turbines considering man-hour utilization is provided, including:

[0036] A maintenance scheduling method for offshore wind turbines considering man-hour utilization includes the following steps:

[0037] An information acquisition module acquires the information required for the maintenance scheduling of the wind farm, and the information includes the general situation of the wind farm, the details of the maintenance tasks, and the maintenance resource data;

[0038] A preprocessing module preprocesses the information, including numbering and discretizing the maintenance vessels and task wind turbines, and variablizing the types of maintenance tasks;

[0039] A population construction module forms chromosome individuals M s with the numbers of the task wind turbines and the maintenance vessels as the gene content,

[0040] A coding and decoding module decodes the individuals in the population into the maintenance scheduling schemes they represent, and takes the decoded sequences of each individual as the object to evaluate the fitness values of all individuals in the population. The lower the fitness value, the closer the individual is to the optimal solution;

[0041] An optimization module selects the optimal individual in the population according to the individual fitness value and performs hill climbing algorithm optimization with it as the object;

[0042] A selection module selects parental individuals in the population by using the roulette wheel method driven by probability;

[0043] An elite retention strategy module, for the selected parental individuals, performs crossover operations of the elite retention strategy on the individuals that meet the crossover probability P j , compares the fitness values of the parents and offspring after the crossover operation, and implements elite individual screening; performs mutation operations in the form of gene transposition on the individuals that meet the mutation probability P b ;

[0044] A catastrophe module starts the catastrophic optimization operation when the optimal individual in the population has not been optimized in the preset number of evolutionary generations;

[0045] A scheme acquisition module obtains the optimal individual in the population, and the maintenance scheduling scheme it represents is the final application scheme.

[0046] According to the third aspect of the embodiments of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program running on the memory. When the processor executes the program, it implements the method for scheduling the operation and maintenance of an offshore wind turbine considering the utilization of working hours.

[0047] According to the fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, it implements the method for scheduling the operation and maintenance of an offshore wind turbine considering the utilization of working hours.

[0048] The advantages of the above technical solutions adopted in the present invention compared with the prior art are as follows: (1) The present invention transforms the problem of scheduling multiple operation and maintenance tasks in an offshore wind farm into the problem of task wind turbine selection for operation and maintenance teams in an executable task (idle) state, and uses an improved genetic algorithm that comprehensively considers the total operation and maintenance cost and the utilization of working hours of the operation and maintenance teams to optimize the selection of the operation and maintenance scheduling plan for the offshore wind farm. Specifically, an improved genetic algorithm framework is constructed in combination with the actual situation of offshore wind farm operations to solve the problem of scheduling multiple operation and maintenance tasks in an offshore wind farm. The total operation and maintenance cost calculation function is set as the fitness function to evaluate the quality of the scheduling plan, and the optimization selection of the scheduling plan is completed with the help of the improved genetic algorithm. The improved genetic algorithm encodes each scheduling plan as a population individual for crossover and genetic operations. The population after completing the corresponding number of evolutions represents the non-dominated solution set of the current scheduling plan. The scheduling plan is selected according to the total operation and maintenance cost and the working hour utilization efficiency index of the operation and maintenance team, realizing the scheduling optimization goal of multiple operation and maintenance tasks in the offshore wind farm.

[0049] (2) To quantify the order of operation and maintenance operations, a non-repeating natural number coding method is adopted with the operation and maintenance ship and task wind turbine numbers as the content. Each numbered element appears only once in the scheduling plan sequence, and after all elements appear, it represents the coding sequence of the current individual scheduling plan. To enhance the local search ability of the algorithm, a branch and bound search method is embedded in the decoding process of the improved genetic algorithm. For the first task and the return journey stages, the cumulative voyage distance of the operation and maintenance ship is used as the upper bound value of the node, and the optimal node is continuously updated; to improve the quality of the population genes, an elite retention strategy is set after the crossover and genetic operations. The fitness values of the parent and offspring individuals after the crossover operation are compared, and two of the best individuals are selected to enter the population for subsequent operations; to improve the convergence efficiency of the algorithm, a hill climbing optimization algorithm is added to the algorithm, and the optimal individual of the population after each evolution is used as the object for optimization, and the selection is made according to the fitness values before and after optimization; to improve the population diversity, a catastrophe optimization operation is introduced. Taking the population in which the optimal individual of the population has not been optimized within the preset number of generations as the object, a certain proportion of non-repeating fitness individuals in the population and randomly generated new individuals are combined to form a population to participate in subsequent genetic operations.

[0050] (3) According to the characteristics of the operation and maintenance work of offshore wind farms, the present invention designs targeted operation and maintenance scheduling characteristic variables, including: total voyage segment characteristic variables, first mission voyage segment characteristic variables, mission wind turbine combination voyage segment characteristic variables, return voyage segment characteristic variables, status characteristic variables, operation and maintenance ship service wind turbine status characteristic variables, operation and maintenance team service wind turbine status characteristic variables, combined status characteristic variables, and man-hour consumption characteristic variables. The above characteristic variables quantify the operation and maintenance ship path, the man-hour consumption characteristics of each operation task wind turbine, the service wind turbine status, and the wind turbine combination status characteristics; it helps the accurate solution of the algorithm and improves the practicability of the algorithm.

[0051] (4) In order to comprehensively consider the impact of the man-hour utilization problem of the operation and maintenance team on the operation and maintenance cost, the present invention introduces a mission wind turbine combination strategy to determine the mission wind turbine combination part of each day and form a daily operation and maintenance scheduling plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings forming a part of this application are used to provide a further understanding of this application. The schematic embodiments and descriptions thereof of this application are used to explain this application and do not constitute an improper limitation of this application.

[0053] Figure 1 Flowchart of the method for scheduling the operation and maintenance of offshore wind turbines considering man-hour utilization;

[0054] Figure 2 Schematic diagram of the encoding and decoding process in the present invention;

[0055] Figure 3 Flowchart of the branch and bound search method in the present invention;

[0056] Figure 4 Flowchart of the improved genetic algorithm in the present invention;

[0057] Figure 5 Distribution map of wind turbine units in the embodiment. SPECIFIC EMBODIMENTS

[0058] The present disclosure will be further described below in conjunction with the accompanying drawings and embodiments.

[0059] It should be noted that the following detailed description is illustrative and is intended to provide further explanation of this application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs.

[0060] It should be noted that the terms used herein are for the purpose of describing specific embodiments only and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular forms are also intended to include the plural forms. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they specify the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0061] It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of methods and systems according to various embodiments of the present disclosure. It should be noted that each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, the program segment, or the part of code may include one or more executable instructions for implementing the logical functions specified in each embodiment. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. Similarly, it should be noted that each block in the flowchart and / or block diagram, and the combinations of blocks in the flowchart and / or block diagram, may be implemented using a dedicated hardware-based system for performing the specified functions or operations, or may be implemented using a combination of dedicated hardware and computer instructions.

[0062] An offshore wind farm usually has a unified operation and maintenance center, which is equipped with one or more operation and maintenance vessels and multiple operation and maintenance teams, and is uniformly allocated by the operation and maintenance center. Given the specific locations of the wind turbines in the wind farm, the consumables required for the operation and maintenance work of each task wind turbine, and the estimated working hours, under the constraints of the maximum daily working hours of the operation and maintenance teams, the maximum navigation distance of the vessels, the maximum load, etc., the operation and maintenance scheduling plan of the wind turbines is optimized by comprehensively considering the navigation costs, rental costs of the operation and maintenance vessels, the labor costs of the operation and maintenance teams, and the economic losses caused by wind turbine failures.

[0063] Embodiment 1:

[0064] This embodiment provides a method for scheduling the operation and maintenance of offshore wind turbines considering the utilization of working hours. An improved genetic algorithm is used to solve the problem of scheduling offshore wind turbines, and the selection and optimization of the operation and maintenance scheduling plan for task wind turbines are realized. The process is shown as Figure 1 shown; the core idea is: designing an improved genetic algorithm in combination with the characteristics of the operation and maintenance operations of offshore wind farms, and objectively and accurately evaluating the advantages and disadvantages of the scheduling plan with the help of a fitness function, giving full play to the powerful advantages of the improved genetic algorithm, and continuously optimizing and intelligently selecting the scheduling plan. The method includes the following steps:

[0065] S1. Obtain the information required for the operation and maintenance scheduling of the wind farm, including the general situation of the wind farm, the details of the operation and maintenance tasks, and the operation and maintenance resource data;

[0066] In this embodiment, there is one operation and maintenance center, numbered 0, with a fixed location; the types of operation and maintenance vessels are the same, and they return to the operation and maintenance center after completing the transportation task; the operation and maintenance work starts as soon as the operation and maintenance vessel arrives at the location of the wind turbine; only one operation and maintenance team is allowed to work on each wind turbine at the same time; one operation and maintenance team can maintain multiple wind turbines per day, and the maximum number of wind turbines that an operation and maintenance team can maintain per day and the maximum working hours per day are limited.

[0067] S2. Preprocess the information, including numbering and discretizing the operation and maintenance vessels and the task wind turbines, and setting the operation and maintenance task types as variables;

[0068] In this embodiment, setting the operation and maintenance task types as variables includes characteristic variables related to the operation and maintenance vessel, the operation and maintenance team, and the task wind turbine. The characteristic variables related to the operation and maintenance vessel include: the total voyage characteristic variable x ijt , the first task voyage characteristic variable s ijt , the task wind turbine combination voyage characteristic variable e ijt , the return voyage characteristic variable b ijt , the status characteristic variable The service wind turbine status characteristic variable The characteristic variables related to the operation and maintenance team include: the service wind turbine status characteristic variable The characteristic variables related to the task wind turbine include: the combined status characteristic variable r ijt , the working hour consumption characteristic variable T it .

[0069] The specific descriptions of the above variables are as follows:

[0070] The total voyage characteristic variable x ijt , representing the voyage quantity characteristic of the operation and maintenance vessel from wind turbine i to j on the t-th day, and x ijt = s ijt + e ijt + b ijt .

[0071] The first task voyage characteristic variable s ijt , representing the voyage type of the operation and maintenance vessel from wind turbine i to j in the first task stage on the t-th day. When it exists, s ijt = 1, otherwise s ijt = 0.

[0072] The task wind turbine combination voyage characteristic variable e ijt , representing the voyage type of the operation and maintenance vessel from wind turbine i to j in the task wind turbine combination stage on the t-th day. When it exists, e ijt = 1, otherwise e ijt = 0.

[0073] Return leg segment characteristic variable b ijt , representing the leg type of the maintenance ship from wind turbine i to j during the return stage on the t-th day. When it exists, b ijt = 1; otherwise, b ijt = 0.

[0074] Status characteristic variable Representing the rental status of the maintenance ship k on the t-th day. If it is rented, then otherwise

[0075] Service wind turbine status characteristic variable Representing the service status of the maintenance ship k for the task wind turbine i on the t-th day. If it is planned to serve, then otherwise

[0076] Service wind turbine status characteristic variable Representing the service status of the maintenance team m for the task wind turbine i on the t-th day. If it is planned to serve, then otherwise

[0077] Combined status characteristic variable r ijt , representing the combined status of the task wind turbines i and j on the t-th day, and is associated with the task wind turbine combined leg characteristic variable e ijt . The association formula is as follows:

[0078] r ijt = (T M - T it ) ÷ T jM

[0079] M + e ijt ≥ r ijt - R A

[0080] R A e ijt ≤ r ijt

[0081] Among them, T i is the working duration required to complete the maintenance of the task wind turbine i; T M is the maximum daily working hours of the maintenance team; T jM is the remainder of T i divided by T M ; M + is a sufficiently large constant; R A is the set task wind turbine combination threshold parameter.

[0082] Working hour consumption characteristic variable T it, representing the characteristic of the maintenance working hours consumed by the fan i on the t-th day, and its value range is 0 to T M .

[0083] S3. Using the task fan and maintenance ship numbers as the gene content to form a chromosome individual M s , forming a population M;

[0084] In this embodiment, a non-repeating natural number coding method is used to code the maintenance scheduling scheme. Using the task fan and maintenance ship numbers as the gene content to form a chromosome individual M s , where the task fan and maintenance ship numbers appear only once; the chromosome individual M s represents the maintenance scheduling scheme, which includes the service scope of the maintenance ship for the fan and the operation order of the task fans. Among them, the task fans between two maintenance ship numbers are the service scope of the maintenance ship with a higher order, and the operation order of the task fans is determined according to the coding order;

[0085] The decoding process of the individuals in the population includes the selection of the fan serviced by the maintenance ship, the first task, the combination of task fans and the return journey. The encoding and decoding process is shown as Figure 2 shown; Let M s be the s-th chromosome in the population; be the set of fans that need to be serviced by the maintenance ship k; are respectively the set of fans that the maintenance ship k needs to service on the t-th day, the number of teams carried, the set of first task fans, the optimal path of the first task, the set of fans that the team is currently maintaining, the task fan combination sequence, the set of return fans and the optimal return path represented by M s ;

[0086] To enhance the local search ability of the algorithm, the branch and bound search method is embedded in the two stages of the first task and the return journey in the decoding process. This method is based on minimizing the sailing cost, and uses or fan elements as the content to generate several first task or return journey plan sets. These plan sets are used as the nodes of the search tree, and the cumulative sailing distance of the maintenance ship for each plan is used as the upper bound value of each node. If the upper bound value of a certain node in the calculation process is equal to or greater than the upper bound value of the current optimal node, the child nodes of this node are no longer generated (pruned), as Figure 3 shown.

[0087] Population initialization method: Let the population size be A. Combine the set K of maintenance ship numbers and the set N of task fan numbers into a set S. Randomly select j ∈ S, and generate a non-repeating element sequence containing the number of elements in S in the selection order to form this coding sequence (individual) M s , s ∈ {1, 2,..., A}; Repeat this operation to generate A coding sequences (individuals) to form a population M.

[0088] S4. Decode the individuals in the population into the respective operation and maintenance scheduling plans they represent, and take the decoded sequences of each individual as objects to evaluate the fitness values of all individuals in the population. The lower the fitness value, the closer the individual is to the optimal solution.

[0089] In this embodiment, by introducing a task combination strategy, the utilization efficiency of the working hours of the operation and maintenance teams is comprehensively considered. The associated variables of the task combination strategy are the task fan combination flight segment characteristic variable e ijt and the combined state characteristic variable r ijt , and the preset known quantity is the task combination threshold R A . When e ijt =1, the task fan i is combined with, and the fan numbered i in the first task set is postponed one position backward to the last order of the first task, and is recorded in the operation and maintenance scheduling plan for the t-th day. Conversely, when e ijt =0, the task fans i and j are not combined and the fan numbered j is postponed one position backward to the last order.

[0090] The fitness value of an individual is:

[0091]

[0092] Among them, D ij represents the sailing distance between the task fans i and j, in kilometers; C J represents the sailing cost per unit distance of the operation and maintenance ship, in yuan / km; G i represents the failure state of the task fan i. If it is a shutdown failure, then G i =1, otherwise G i =0; W represents the average output power of the fan, in kilowatt-hours; C E represents the cost per unit of electricity, in yuan / kilowatt-hour; L i represents the total duration from the start point of the operation and maintenance cycle to the completion of the maintenance of the fan i, in hours; C B represents the daily rental cost of a single operation and maintenance ship, in yuan / day; C R represents the average daily labor cost of a single operation and maintenance team, in yuan / team; T represents the total number of days of the operation and maintenance cycle, in days; N represents the set of task fan numbers N = {1, 2,..., n}; K represents the set of operation and maintenance ship numbers K = {1, 2,..., v}; M represents the set of operation and maintenance team numbers M = {1, 2,..., p}.

[0093] S5. Select the optimal individual in the population based on the individual fitness value and perform hill climbing algorithm optimization with it as the object;

[0094] In this embodiment, the hill-climbing optimization algorithm takes the optimal individual of the population after each evolutionary iteration as the optimization object, and uses the gene transposition method to change the gene composition of the object to generate a new individual. If the new individual is better than the original individual, it replaces the original individual as the optimal individual of the population; otherwise, the original individual is retained. The optimization algorithm stops when the preset number of operations is reached.

[0095] S6. Select the parental individuals in the population using the probability-driven roulette wheel method;

[0096] S61. Obtain the individual M in the population s reciprocal of the fitness value

[0097] S62. Take the ratio of the reciprocal of the individual fitness value to the sum of the reciprocal of the fitness values of the population individuals as the selection probability P(M s ) of the individual M s );

[0098] S63. In the order of the population, use the cumulative method of the probability P(M s ) to determine the area R s occupied by the individual M between 0 and 1, generate a random number within the interval [0, 1], and select the individual corresponding to its area as the parental individual. s

[0099] Among them, the selection probability P(M s ) and the individual roulette area R s are calculated as follows:

[0100]

[0101]

[0102] S7. For the selected parental individuals, perform the crossover operation of the elitist retention strategy on the individuals that meet the crossover probability P j , compare the fitness values of the parental and offspring individuals after the crossover operation, and implement the selection of elite individuals; perform the mutation operation of the gene transposition method on the individuals that meet the mutation probability P b ;

[0103] In this embodiment, the elitist retention strategy includes two stages: crossover operation and elite individual selection; in the crossover operation stage, the random region gene crossover method is adopted, and its crossover probability P jThe recommended value range is 0.6 - 0.95. Two non-repeating random numbers within the interval [0, individual gene length] are generated to confirm the crossover interval, thereby dividing the parental individual gene into the front gene of the crossover interval, the gene in the crossover interval, and the rear gene of the crossover interval. During the crossover process of the parental individual gene, the front gene of the crossover interval is directly inherited to the offspring individual, and the gene in the crossover interval and the rear gene of the crossover interval are compared with the existing genes of the corresponding offspring. If there are duplicate genes, they are postponed backward; otherwise, they are directly inherited into the offspring individual, thus obtaining a complete offspring individual;

[0104] The elite individual screening stage is after the crossover operation stage. By comparing the fitness of all individuals in the crossover link, the fitness of all parents and offspring is compared, and the two optimal individuals are selected to replace the offspring individuals and inherit them to the next generation, so as to ensure the inheritance of high-quality genes in the population and improve the convergence efficiency of the algorithm.

[0105] Mutation operation, for parental individuals that meet the mutation probability P b (The recommended value of P b is 0.01 - 0.18), using the gene transposition method, two random numbers are generated within the interval [0, individual gene length] as mutation sites, and their gene positions are swapped;

[0106] S8. When the optimal individual in the population has not been optimized within the preset number of evolutionary generations, start the catastrophe optimization operation;

[0107] To improve the population diversity, a catastrophe optimization operation is introduced. This operation selects a certain proportion of non-repeating better and worse individuals from the population, and at the same time randomly generates new individuals with the same number as the unselected individuals. The new individuals and the selected individuals are combined into a new population to replace the original population and continue the evolutionary iteration. Its trigger condition is that the fitness value of the optimal individual in the population has not been optimized within the preset number of evolutionary generations.

[0108] S9. Obtain the optimal individual in the population, and the operation and maintenance scheduling plan it represents is the final application plan.

[0109] In the application stage of the scheduling algorithm, the improved genetic algorithm uses the operation and maintenance tasks, resources, and wind farm-related information (operation and maintenance task types, number of operation and maintenance vessels, etc.) collected and preprocessed in the early stage as input data, and updates the operation and maintenance scheduling plan according to the improved genetic algorithm, achieving the optimization effect of the operation and maintenance scheduling plan with the goal of minimizing the operation and maintenance cost and taking into account the utilization of working hours, as Figure 4 shown.

[0110] Based on the data of a certain offshore wind farm in Jiangsu as the engineering background, the experimental scheme of the present invention is designed. There are 50 wind turbines with a single capacity of 1 MW. The operation and maintenance center is located 14 km due west of the X-01 wind turbine. The column spacing of the wind turbines is 0.6 km, and the row spacing is 1.4 km. The distribution of the wind turbines is asFigure 5 As shown in the figure. Classify the task wind turbines according to whether they stop due to faults, and adopt an operation and maintenance method that combines regular maintenance and condition-based maintenance. The operation and maintenance team and materials start from the operation and maintenance center. The center is equipped with 1 operation and maintenance ship and 6 operation and maintenance teams. The maximum daily working hours of the team is 8h, the maximum load capacity of the ship is 35t, the sailing cost is 180 yuan / km, and the ship rental fee is 30,000 yuan / day. The working hour requirements for 7 types of regular inspections and wind turbine fault operation and maintenance tasks are shown in Table 1 in detail. Referring to the on-grid price of offshore wind power, the electricity price is 0.85 yuan / kW·h. There are 15 task wind turbines, and the detailed information of the task wind turbines is shown in Table 2 in detail. The experimental population size is 60, the maximum number of evolutions is 1000, the crossover probability P j = 0.9, the mutation probability P b = 0.1 and the task wind turbine combination threshold R A = 0.94.

[0111] Table 1 Maintenance operation resources required for wind turbines

[0112]

[0113]

[0114] Table 2 Detailed information of task wind turbines

[0115] Task fan number Fault type Repair duration XG-01 Shutdown 13h XG-05 Non-shutdown 19.3h XG-11 Shutdown 23h XG-13 Non-shutdown 10.5h XG-19 Shutdown 11.3h XG-29 Non-shutdown 13.8h XG-31 Shutdown 7.5h XG-37 Non-shutdown 17.5h XG-38 Shutdown 19.3h XG-39 Shutdown 17.3h XG-41 Non-shutdown 7.3h XG-45 Shutdown 20h XG-46 Non-shutdown 18h XG-48 Shutdown 15.5h XG-50 Non-shutdown 14h

[0116] Experiments show that the multi-operation and maintenance task scheduling method for offshore wind farms proposed by the present invention can effectively solve the corresponding scheduling scheme. Table 3 gives the working hour utilization efficiency and total operation and maintenance cost of the present invention and the reference method, where the reference method is the classical genetic algorithm. It can be seen that compared with the reference method, the total operation and maintenance cost is saved by more than 19%, the working hour utilization rate is increased by more than 11%, the operation and maintenance cost of the wind farm is reduced, and the utilization efficiency of the operation and maintenance team is enhanced.

[0117] Table 3 Comparative experiment results

[0118]

[0119]

[0120] Example two:

[0121] This embodiment provides an offshore wind turbine operation and maintenance scheduling system considering working hour utilization, including:

[0122] An information acquisition module that acquires the information required for the operation and maintenance scheduling of the wind farm, and this information includes the general situation of the wind farm, the details of the operation and maintenance tasks, and the operation and maintenance resource data;

[0123] The preprocessing module preprocesses the information, including numbering and discretizing the operation and maintenance vessels and task wind turbines, and variablizing the operation and maintenance task types;

[0124] The population construction module forms chromosome individuals M with the numbers of task wind turbines and operation and maintenance vessels as gene content s , constituting population M;

[0125] The encoding and decoding module decodes the individuals in the population into the operation and maintenance scheduling plans they represent, and evaluates the fitness values of all individuals in the population with the decoded sequences of each individual as the objects. The lower the fitness value, the closer the individual is to the optimal solution;

[0126] The optimization module selects the optimal individual in the population according to the individual fitness value and performs hill climbing algorithm optimization with it as the object;

[0127] The selection module selects parental individuals in the population by using the roulette wheel method driven by probability;

[0128] The elite retention strategy module, for the selected parental individuals, performs crossover operations of the elite retention strategy on the individuals that meet the crossover probability P j . After the crossover operation, compare the fitness values of the parents and offspring, and implement elite individual screening; perform mutation operations in the form of gene transposition on the individuals that meet the mutation probability P b ;

[0129] The catastrophe module starts the catastrophe optimization operation when the optimal individual in the population has not been optimized in the preset number of evolutionary generations;

[0130] The scheme acquisition module obtains the optimal individual in the population, and the operation and maintenance scheduling plan it represents is the final application scheme.

[0131] Example 3:

[0132] An electronic device includes a memory, a processor, and a computer program running on the memory. When the processor executes the program, it implements the above-mentioned method for scheduling the operation and maintenance of offshore wind turbines considering man-hour utilization, including:

[0133] Obtain the information required for the operation and maintenance scheduling of the wind farm, including the general situation of the wind farm, the details of the operation and maintenance tasks, and the operation and maintenance resource data;

[0134] Preprocess the information, including numbering and discretizing the operation and maintenance vessels and task wind turbines, and variablizing the operation and maintenance task types;

[0135] Form chromosome individuals M with the numbers of task wind turbines and operation and maintenance vessels as gene content s , constituting population M;

[0136] Decode the individuals in the population into the respective operation and maintenance scheduling plans they represent, and take the decoded sequences of each individual as the objects to evaluate the fitness values of all individuals in the population. The lower the fitness value, the closer the individual is to the optimal solution;

[0137] Select the optimal individual in the population according to the individual fitness value, and perform hill climbing algorithm optimization with it as the object;

[0138] Use the roulette wheel method driven by probability to select parental individuals in the population;

[0139] For the selected parental individuals, perform crossover operations with the elite retention strategy on the individuals that meet the crossover probability P j . After the crossover operation, compare the fitness values of the parents and offspring, and implement elite individual screening; perform mutation operations in the form of gene transposition on the individuals that meet the mutation probability P b ;

[0140] When the optimal individual in the population is not optimized within the preset number of evolutionary generations, start the catastrophe optimization operation;

[0141] Obtain the optimal individual in the population, and the operation and maintenance scheduling plan it represents is the final application plan.

[0142] Example 4:

[0143] A computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the above-mentioned method for scheduling the operation and maintenance of offshore wind turbines considering man-hour utilization, including:

[0144] Obtain the information required for the operation and maintenance scheduling of the wind farm, including the general situation of the wind farm, the details of the operation and maintenance tasks, and the operation and maintenance resource data;

[0145] Preprocess the information, including numbering and discretizing the operation and maintenance vessels and task wind turbines, and setting the operation and maintenance task types as variables;

[0146] Use the numbers of the task wind turbines and operation and maintenance vessels as the gene content to form chromosome individuals M s , and constitute a population M;

[0147] Decode the individuals in the population into the respective operation and maintenance scheduling plans they represent, and take the decoded sequences of each individual as the objects to evaluate the fitness values of all individuals in the population. The lower the fitness value, the closer the individual is to the optimal solution;

[0148] Select the optimal individual in the population according to the individual fitness value, and perform hill climbing algorithm optimization with it as the object;

[0149] Use the roulette wheel method driven by probability to select parental individuals in the population;

[0150] For the selected parent individuals, perform crossover operations with elitist retention strategy on individuals that satisfy the crossover probability P j . After the crossover operation, compare the fitness values of the parent and offspring, and implement the screening of elite individuals; perform mutation operations in the form of gene transposition on individuals that satisfy the mutation probability P b .

[0151] When the optimal individual in the population has not been optimized in the preset number of evolutionary generations, initiate the catastrophic optimization operation;

[0152] Obtain the optimal individual in the population, and the operation and maintenance scheduling scheme it represents is the final application scheme.

[0153] Those skilled in the art should understand that the above-mentioned modules or steps of the present disclosure can be implemented by a general computer device. Optionally, they can be implemented by program codes executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. The present disclosure is not limited to any specific combination of hardware and software.

[0154] The above are only the preferred embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0155] Although the specific implementation manners of the present disclosure have been described above in conjunction with the accompanying drawings, it is not a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that based on the technical solutions of the present disclosure, various modifications or deformations that can be made without creative efforts by those skilled in the art are still within the protection scope of the present disclosure.

Claims

1. A method for scheduling offshore wind turbine operation and maintenance considering man-hour utilization, characterized in that: The following steps are involved: Obtain the information required for wind farm operation and maintenance scheduling, including wind farm overview, operation and maintenance task details, and operation and maintenance resource data; Preprocessing the information, including numbering and discretizing the operation and maintenance ships and task wind turbines, and setting the operation and maintenance task types in a variable manner; The chromosome individual M is composed of the mission wind turbine and maintenance ship number as the genetic content s , forming a population M; Decode the individuals in the population into the operation and maintenance scheduling solutions they represent, and evaluate the fitness values ​​of all individuals in the population based on the decoding sequence of each individual. The lower the fitness value, the closer the individual is to the optimal solution. The best individuals in the population are selected based on their individual fitness values, and the hill climbing algorithm is optimized based on them. A probability-driven roulette wheel method is used to select parent individuals in the population; For the selected parent individuals, satisfy the crossover probability P j The individuals of the elite retention strategy perform crossover operations, compare the fitness values ​​of the parent and offspring after the crossover operation, and implement elite individual screening; b The individuals undergo mutation operations in the form of gene transposition; When the optimal individual of the population is not optimized in the preset evolutionary generations, the catastrophic optimization operation is initiated; The optimal individual in the population is obtained, and the operation and maintenance scheduling plan represented by it is the final application plan.

2. According to claim 1, a method for scheduling offshore wind turbine operation and maintenance taking into account the use of working hours is characterized in that: The operation and maintenance task type is variable, including the characteristic variables related to the operation and maintenance ship, the operation and maintenance team, and the task wind turbine. The characteristic variables related to the operation and maintenance ship include: the total voyage characteristic variable x ijt , the first mission segment characteristic variable s ijt , mission fan combination segment characteristic variable e ijt , return flight segment characteristic variable b ijt , state characteristic variables Service fan status characteristic variables The characteristic variables related to the operation and maintenance team include: Service fan status characteristic variables The characteristic variables related to the task fan include: combined state characteristic variables r ijt , characteristic variable T of working time consumption it .

3. The offshore wind turbine operation and maintenance scheduling method considering man-hour utilization according to claim 1, characterized in that: The operation and maintenance scheduling scheme is encoded using a non-repeating natural number encoding method, and the task wind turbine and operation and maintenance ship number are used as the gene content to form the chromosome individual M s , where the mission wind turbine and maintenance ship number appear only once; the chromosome individual M s Represents the operation and maintenance scheduling plan, which includes the service scope of the operation and maintenance ship and the operation order of the task wind turbines. The task wind turbines between two operation and maintenance ship numbers are the service scope of the operation and maintenance ship with the earlier order. The operation order of the task wind turbines is determined according to the coding order; The individual decoding process in the group includes the selection of wind turbines served by the maintenance ship, the first mission, the mission wind turbine combination and the return trip; let M s is the sth chromosome in the population; A collection of wind turbines required for the operation and maintenance of ship k; M s The wind turbine set that the maintenance ship k needs to serve on the tth day, the number of teams carried, the set of wind turbines for the first mission, the optimal path for the first mission, the set of wind turbines being maintained by the team, the combination sequence of task wind turbines, the set of return wind turbines and the optimal return path; A branch and bound search method is embedded in the first mission and the return mission. This method is based on minimizing the navigation cost. or The wind turbine element is used as the content to generate several sets of first-time missions or return plans. The above plan sets are used as search tree nodes, and the cumulative distance of the operation and maintenance ship of each plan is used as the upper limit value of each node. If the upper limit value of a node in the calculation process is equal to or greater than the upper limit value of the current optimal node, the child node of the node will no longer be generated; Population initialization method: Assume that the population size is A, merge the maintenance ship number set K and the task wind turbine number set N into a set S, randomly select j∈S, and generate a non-repeating element sequence containing S elements in the selection order to form the coding sequence (individual) M s , s∈{1,2,…,A}; repeat this operation to generate A coding sequences (individuals) to form a population M.

4. According to claim 2, a method for scheduling offshore wind turbine operation and maintenance taking into account the use of working hours is characterized in that: The task combination strategy is introduced to comprehensively consider the efficiency of the operation and maintenance team's working hours. The associated variable of the task combination strategy is the characteristic variable e of the task wind turbine combination segment. ijt and the combined state characteristic variable r ijt , the preset known quantity is the task combination threshold R A , when e ijt = 1 means that the task wind turbines i and j are combined, and the wind turbine numbered i in the first task set is postponed to the last order of the first task and recorded in the operation and maintenance schedule of the tth day. ijt =0, the task fans i and j are not combined and the fan numbered j is postponed to the last position in the sequence.

5. The offshore wind turbine operation and maintenance scheduling method considering man-hour utilization according to claim 1, characterized in that: The fitness value of an individual is: Among them, D ij represents the navigation distance between mission wind turbines i and j, in kilometers; C J G represents the navigation cost per unit distance of the operation and maintenance ship, in yuan / km; i Indicates the fault status of task fan i. If it is a shutdown fault, G i =1, otherwise G i =0; W represents the average output power of the fan, in kilowatt-hours; C E Indicates the unit electricity cost, in yuan / kWh; L i It indicates the total time from the start of the operation and maintenance cycle to the completion of the operation and maintenance of wind turbine i, in hours; C B It represents the daily rental fee of a single operation and maintenance vessel, in RMB / day; C R represents the average daily labor cost of a single operation and maintenance team, in yuan / team; T represents the total number of days in the operation and maintenance cycle, in days; N represents the set of task wind turbine numbers N = {1,2,…,n}; K represents the set of operation and maintenance ship numbers K = {1,2,…,v}; M represents the set of operation and maintenance team numbers M = {1,2,…,p}.

6. The offshore wind turbine operation and maintenance scheduling method considering man-hour utilization according to claim 1, characterized in that: The probability-driven roulette method is used to select parent individuals in the population as follows: Get the individual M in the population s The inverse of the fitness value The ratio of the reciprocal of the individual fitness value to the reciprocal of the fitness value of the population is taken as the individual M s The probability of being selected P(M s ); According to the population order, the probability of using P(M s ) Accumulated method to determine the individual M s The area R between 0 and 1 s , generate a random number in the interval [0,1], and select the individual corresponding to the area where it is located as the parent individual.

7. The offshore wind turbine operation and maintenance scheduling method considering man-hour utilization according to claim 1, characterized in that: The elite retention strategy includes two stages: crossover operation and elite individual screening. In the crossover operation stage, a random region gene crossover method is used to confirm the crossover interval by generating two non-repeating random numbers in the interval [0, individual gene length], thereby dividing the parent individual genes into the front gene of the crossover interval, the crossover interval gene and the back gene of the crossover interval. During the crossover of the parent individual genes, the front gene of the crossover interval is directly inherited to the offspring individual, and the crossover interval gene and the back gene of the crossover interval are compared with the corresponding offspring genes. If there are repeated genes, they are postponed, otherwise, they are directly inherited to the offspring individual, thereby obtaining a complete offspring individual. The elite individual screening stage is after the crossover operation stage. The fitness of all individuals in the crossover stage is compared, the fitness of all parents and offspring are compared, and the two best individuals are selected to replace the offspring individuals to be inherited to the next generation, so as to ensure the inheritance of high-quality genes in the population.

8. An offshore wind turbine operation and maintenance scheduling system considering man-hour utilization, characterized in that: include: An information acquisition module obtains the information required for wind farm operation and maintenance scheduling, including wind farm overview, operation and maintenance task details, and operation and maintenance resource data; The preprocessing module preprocesses the information, including numbering and discretizing the operation and maintenance ships and task wind turbines, and setting the operation and maintenance task types in a variable manner; Population construction module, with the mission wind turbine and operation and maintenance ship number as the gene content to form chromosome individual M s , forming a population M; The encoding and decoding module decodes the individuals in the population into the operation and maintenance scheduling solutions they represent, and evaluates the fitness values ​​of all individuals in the population based on the decoding sequences of each individual. The lower the fitness value, the closer the individual is to the optimal solution. The optimization module selects the best individuals in the population according to their individual fitness values ​​and uses them as objects for hill climbing algorithm optimization; The selection module uses a probability-driven roulette method to select parent individuals in the population; The elite retention strategy module selects the parent individuals and selects the individuals that meet the crossover probability P. j The individuals of the elite retention strategy perform crossover operations, compare the fitness values ​​of the parent and offspring after the crossover operation, and implement elite individual screening; b The individuals undergo mutation operations in the form of gene transposition; Catastrophic module, when the optimal individual of the population is not optimized in the preset evolutionary generations, the catastrophic optimization operation is initiated; The solution acquisition module obtains the optimal individual in the population, and the operation and maintenance scheduling solution represented by it is the final application solution.

9. An electronic device comprising a memory, a processor and a computer program stored and running on the memory, characterized in that: When the processor executes the program, the offshore wind turbine operation and maintenance scheduling method considering the utilization of working hours is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the offshore wind turbine operation and maintenance scheduling method considering the utilization of working hours is implemented.

Images