Multi-ship cooperative offshore wind power operation and maintenance scheduling efficient optimization method and related device

Abstract

This application proposes an efficient optimization method and related apparatus for multi-vessel collaborative offshore wind power operation and maintenance scheduling. The method decomposes the constructed multi-vessel collaborative operation and maintenance scheduling model into multiple single-vessel operation and maintenance optimization scheduling sub-models that satisfy the constraints of the multi-vessel collaborative operation and maintenance scheduling model. After solving each sub-model separately, the solutions of each single-vessel operation and maintenance optimization scheduling sub-model are combined to obtain the solution of the multi-vessel collaborative operation and maintenance scheduling model, which serves as the optimization strategy for offshore wind power operation and maintenance scheduling. This achieves efficient solution of the multi-vessel collaborative optimization scheduling model for offshore wind farms, helping wind power operators and third-party operation and maintenance service providers improve the efficiency of operation and maintenance task scheduling, reduce risks, and lower operation and maintenance costs. Even with large-scale multi-vessel collaborative operation and maintenance scheduling models, it can quickly complete the solution and obtain the optimization strategy, demonstrating high efficiency and computational accuracy.

Description

Technical Field

[0001] This application pertains to operation and maintenance scheduling optimization methods, specifically involving a multi-vehicle collaborative offshore wind power operation and maintenance scheduling efficiency optimization method and related devices. Background Technology

[0002] Offshore wind farm maintenance scheduling and route planning are core scenarios for intelligent operation and maintenance (O&M) of offshore wind power. In practical applications, O&M tasks need to be executed based on the scheduling and route planning results. Crew travel vessels (CTVs) are used to transport technical personnel and materials between the O&M base and the wind farm. Due to their lower cost compared to other types of vessels, they are widely used. However, CTVs cannot stay at sea overnight and can only carry a small amount of maintenance tools and spare parts. Once maintenance activities are completed, they need to return to the O&M base on the same day. Due to the relatively long distance between the O&M base and the wind farm, a vessel typically only makes one round trip per day. Due to the high cost of SOVs (Single-State Air Vehicles), most daily O&M tasks for offshore wind power are currently performed by CTVs. Offshore wind farms have numerous maintenance nodes, while the workload of a single CTV is limited. Therefore, in practice, multiple CTVs are usually used in collaboration to accelerate the execution efficiency of O&M tasks and cope with fleeting O&M time windows.

[0003] Offshore wind power operation and maintenance scheduling models are typically MILP (Mixed Integer Linear Programming) problems. Existing methods for solving offshore wind power operation and maintenance scheduling models mainly fall into three categories: exhaustive search, branch and bound, and heuristic methods. Since the computational cost of solving MILP problems increases exponentially with the problem size, exhaustive search is only suitable for solving very small-scale operation and maintenance scheduling models and is insufficient for the collaborative operations of multiple vessels in offshore wind farm clusters. Commercial solvers are usually based on branch and bound, which significantly improves efficiency compared to exhaustive search and can obtain an exact solution to the original problem. However, when the problem size is large and the solution time is limited, branch and bound still struggles to return a satisfactory solution, and only with a longer solution time can a reasonably feasible solution be obtained. As a compromise, heuristic methods are used to find approximate solutions. Even so, achieving a single optimization is still time-consuming and labor-intensive. For example, precise solving techniques, such as the Gurobi commercial solver, can take up to tens of hours to solve a single multi-ship collaborative optimization problem, while metaheuristic methods, such as Large Neighborhood Sort (LNS) algorithms, still take anywhere from tens of minutes to several hours. Moreover, once external conditions change, this time-consuming and laborious optimization process must be repeated. Summary of the Invention

[0004] The purpose of this application is to solve the problems in the prior art and provide an efficient optimization method and related device for multi-vessel collaborative offshore wind power operation and maintenance scheduling.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, this application proposes an efficient optimization method for multi-vehicle collaborative offshore wind power operation and maintenance scheduling, including:

[0007] Construct a multi-ship collaborative operation and maintenance scheduling model;

[0008] Construct a multi-ship collaborative operation and maintenance scheduling decomposition model;

[0009] Based on the multi-ship collaborative operation and maintenance scheduling decomposition model, the multi-ship collaborative operation and maintenance scheduling model is decomposed into multiple single-ship operation and maintenance optimization scheduling sub-models that satisfy the constraints of the operation and maintenance scheduling model.

[0010] Solve each single-ship operation and maintenance optimization scheduling sub-model sequentially to obtain the solution of each single-ship operation and maintenance optimization scheduling sub-model;

[0011] By merging the solutions of each individual vessel operation and maintenance optimization scheduling sub-model, the solution of the multi-vessel collaborative operation and maintenance scheduling model is obtained, which serves as the optimization strategy for offshore wind power operation and maintenance scheduling.

[0012] Preferably, the objective function of the multi-ship collaborative operation and maintenance scheduling decomposition model includes:

[0013]

[0014] Where I represents the set of units requiring maintenance, V represents the set of ships, and x iv =1 or x iv =0, x iv =1 indicates that the unit i to be repaired is being repaired by the ship v, x iv =0 indicates that the unit i to be maintained has not been maintained by the ship v, x jv =1 or x jv =0, x jv =1 indicates that the unit j to be repaired is being repaired by the ship v, x jv =0 indicates that the unit j to be repaired has not been repaired by the ship v, d max =max i,j∈I d ij , representing the maximum distance between units to be maintained; I(·) is an indicator function, when x iv =x jv When it is established, I(x) iv =x jv ) = 1, otherwise, I(x) = 1. iv =x jv ) = 0; d ijThis represents the distance from maintenance node i to maintenance node j.

[0015] Preferably, the constraints of the multi-ship collaborative operation and maintenance scheduling decomposition model include:

[0016] Uniqueness constraint for maintenance task assignment:

[0017]

[0018] Minimum crew task constraints:

[0019]

[0020] Ship passenger capacity restrictions:

[0021]

[0022] Where, ρ ip This represents the number of technicians of type p required for unit i to be maintained. This indicates the maximum number of passengers that ship v can carry;

[0023] Maintenance vessel load capacity constraints:

[0024]

[0025] Among them, w i This indicates the weight of the spare parts and maintenance equipment required for unit i to be maintained. This indicates the maximum weight of spare parts that ship v can carry;

[0026] Ship engine unit matching constraints:

[0027]

[0028] Among them, I v This refers to a set of units that can be maintained by a ship.

[0029] Integer constraint for variables:

[0030]

[0031] Preferably, the step of decomposing the multi-ship collaborative operation and maintenance scheduling model into multiple single-ship operation and maintenance optimization scheduling sub-models that satisfy the constraints of the multi-ship collaborative operation and maintenance scheduling model includes:

[0032] The CP-SAT solver is used to solve the decomposition model using the constraint programming method. Based on the solution of the decomposition model, the multi-ship collaborative operation and maintenance scheduling model is decomposed into multiple single-ship operation and maintenance optimization scheduling sub-models, and all of the multiple single-ship operation and maintenance optimization scheduling sub-models satisfy the constraint conditions of the multi-ship collaborative operation and maintenance scheduling model.

[0033] Preferably, the solutions of each single-ship operation and maintenance optimization scheduling sub-model include: single-ship path planning and operation and maintenance task scheduling.

[0034] Preferably, the process of merging the solutions of each individual ship operation and maintenance optimization scheduling sub-model further includes conflict checking:

[0035] Check whether the operation and maintenance tasks overlap, whether the operation and maintenance times conflict, and whether the time to complete the operation and maintenance tasks is within the given time window in the solutions of each single ship operation and maintenance optimization scheduling sub-model. If all requirements are met, merge the solutions of each single ship operation and maintenance optimization scheduling sub-model; otherwise, re-decompose the multi-ship collaborative operation and maintenance scheduling model.

[0036] Secondly, this application proposes a highly efficient and optimized multi-vessel collaborative offshore wind power operation and maintenance scheduling system, including:

[0037] The first building module is used to build a multi-ship collaborative operation and maintenance scheduling model;

[0038] The second building module is used to construct a multi-ship collaborative operation and maintenance scheduling decomposition model;

[0039] The decomposition module is used to decompose the multi-ship collaborative operation and maintenance scheduling model into multiple single-ship operation and maintenance optimization scheduling sub-models that satisfy the constraints of the multi-ship collaborative operation and maintenance scheduling model, based on the multi-ship collaborative operation and maintenance scheduling decomposition model.

[0040] The solution module is used to solve each single-ship operation and maintenance optimization scheduling sub-model in sequence to obtain the solution of each single-ship operation and maintenance optimization scheduling sub-model;

[0041] The merging module is used to merge the solutions of each single-ship operation and maintenance optimization scheduling sub-model to obtain the solution of the multi-ship collaborative operation and maintenance scheduling model, which serves as the offshore wind power operation and maintenance scheduling optimization strategy.

[0042] Preferably, it also includes an inspection module;

[0043] The solutions of each single-ship operation and maintenance optimization scheduling sub-model include: single-ship path planning and operation and maintenance task scheduling;

[0044] The inspection module is used to check whether the operation and maintenance tasks overlap, whether the operation and maintenance times conflict, and whether the time to complete the operation and maintenance tasks is within a given time window in the solutions of each single-ship operation and maintenance optimization scheduling sub-model before the merging module merges the solutions of each single-ship operation and maintenance optimization scheduling sub-model. If all requirements are met, the solutions of each single-ship operation and maintenance optimization scheduling sub-model are merged; otherwise, the multi-ship collaborative operation and maintenance scheduling model is decomposed again.

[0045] Thirdly, this application proposes an electronic device, comprising:

[0046] Memory, used to store computer programs;

[0047] The processor is used to execute the computer program to implement the steps of the above-mentioned efficient optimization method for multi-ship collaborative offshore wind power operation and maintenance scheduling.

[0048] Fourthly, this application proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-mentioned efficient optimization method for multi-ship collaborative offshore wind power operation and maintenance scheduling.

[0049] Compared with the prior art, this application has the following beneficial effects:

[0050] This application proposes an efficient optimization method for multi-vessel collaborative offshore wind power operation and maintenance scheduling. The method decomposes the constructed multi-vessel collaborative operation and maintenance scheduling model into multiple single-vessel operation and maintenance optimization scheduling sub-models that satisfy the constraints of the multi-vessel collaborative operation and maintenance scheduling model. After solving each sub-model separately, the solutions of each single-vessel operation and maintenance optimization scheduling sub-model are combined to obtain the solution of the multi-vessel collaborative operation and maintenance scheduling model, which serves as the optimization strategy for offshore wind power operation and maintenance scheduling. This method achieves efficient solution of the multi-vessel collaborative optimization scheduling model for offshore wind farms, helping wind power operators and third-party operation and maintenance service providers improve the efficiency of operation and maintenance task scheduling, reduce risks, and lower operation and maintenance costs. Even with large-scale multi-vessel collaborative operation and maintenance scheduling models, it can quickly complete the solution and obtain the optimization strategy, demonstrating high efficiency and computational accuracy.

[0051] This application also proposes a multi-vessel collaborative offshore wind power operation and maintenance scheduling high-efficiency optimization system, electronic equipment, and computer-readable storage medium, which can realize the above-mentioned multi-vessel collaborative offshore wind power operation and maintenance scheduling high-efficiency optimization method through different hardware forms, has broad application value, and possesses all the advantages of the above-mentioned multi-vessel collaborative offshore wind power operation and maintenance scheduling high-efficiency optimization method. Attached Figure Description

[0052] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a schematic diagram of the first process of the efficient optimization method for multi-vehicle collaborative offshore wind power operation and maintenance scheduling in this application.

[0054] Figure 2 This is a schematic diagram of the second process of the efficient optimization method for multi-vehicle collaborative offshore wind power operation and maintenance scheduling in this application.

[0055] Figure 3 This is a comparison chart of the solution speeds of the three solution methods in the embodiments of this application;

[0056] Figure 4 This is a comparison chart showing the advantages and disadvantages of the solutions obtained by the three solution methods in the embodiments of this application;

[0057] Figure 5 This is a connection diagram illustrating an embodiment of the efficient optimization system for multi-vehicle collaborative offshore wind power operation and maintenance scheduling in this application. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0059] Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0060] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0061] In the description of the embodiments of this application, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on this application. In addition, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0062] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0063] In the description of the embodiments of this application, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0064] Offshore wind farms have numerous maintenance nodes, and maintenance windows are fleeting. In the event of unforeseen circumstances, timely adjustments and rapid replanning of operation and maintenance schemes are crucial, placing extremely high demands on the performance of optimization scheduling solutions. Currently, combinatorial optimization methods based on operations research are commonly used to establish operation and maintenance scheduling models, and commercial solvers are used to solve these models. However, the computational complexity of this method increases exponentially with the problem size, making it difficult to meet the needs of multi-vehicle collaborative operations in offshore wind farm clusters.

[0065] Currently, there are three main types of common methods for solving the multi-vessel collaborative offshore wind power operation and maintenance scheduling problem: exhaustive search, branch and bound, and heuristic methods.

[0066] 1) Exhaustive Search. Also known as brute-force search or exhaustive search, it is a basic algorithm for solving optimization problems. The basic idea is to find the optimal solution or a set of optimal solutions by trying all possible solutions. The main advantage of exhaustive search is that it guarantees finding the globally optimal solution because it considers all possible solutions. However, its main disadvantage is that the computational cost can be very high when the solution space is large or the problem complexity is high, as it requires considering a large number of combinations. Since the computational cost of solving MILP problems increases exponentially with the problem size, exhaustive search is only suitable for solving very small-scale operation and maintenance scheduling models and is difficult to adapt to the needs of multi-vehicle collaborative operations in offshore wind farm clusters.

[0067] 2) Branch and Bound. This is an algorithm for solving mathematical optimization and combinatorial optimization problems, aiming to find the optimal solution to a problem or an optimal solution that satisfies specific conditions. It involves dividing the solution space of the problem into multiple subspaces and searching within each subspace to progressively narrow down the range of potential solutions and determine the optimal solution. Commercial solvers, such as Gurobi and CPLEX, use branch and bound as a key component in their mixed integer programming problem solving, combining it with other advanced optimization techniques, such as pruning, heuristics, linear programming relaxation, and polynomial algorithms, to improve performance and efficiency. While commercial solvers based on branch and bound offer significantly higher efficiency than exhaustive search, they still struggle to return satisfactory solutions when the problem size is large and time constraints are limited, requiring longer solution times to achieve a reasonably feasible solution.

[0068] 3) Heuristic methods. These are optimization problem-solving strategies, typically used to solve complex combinatorial optimization problems. Based on experience, rules, or heuristic information, they find near-optimal or high-quality solutions by rapidly exploring the solution space. Heuristic methods are approximate algorithms, characterized by not guaranteeing a globally optimal solution but seeking a solution close to the optimal one within a reasonable timeframe. Large Neighborhood Search (LNS) is a heuristic search method specifically designed for combinatorial optimization problems. Its core idea is to select and explore a large neighborhood space during the search process to find high-quality solutions. LNS methods are typically used to handle complex problems where the solution space is extremely large, making it difficult for traditional search methods to efficiently find optimal or high-quality solutions. However, due to the massive solution scale of multi-vehicle collaborative operation and maintenance scheduling models for offshore wind farms, even using LNS methods, achieving a single optimization is still time-consuming and labor-intensive, and the optimality of the solution cannot be guaranteed.

[0069] To address the problems of existing methods, this application proposes an efficient optimization method and related apparatus for multi-vessel collaborative offshore wind power operation and maintenance scheduling. This method decomposes the collaborative optimization problem into multiple single-vessel scheduling problems while ensuring that the decomposed single-vessel scheduling problems satisfy the constraints of the original problem, thereby significantly improving the solution efficiency of the offshore wind farm operation and maintenance scheduling model.

[0070] The present application will be further described in detail below with reference to the embodiments and accompanying drawings:

[0071] like Figure 1 The diagram shown is a first flowchart illustrating the efficient optimization method for multi-vehicle collaborative offshore wind power operation and maintenance scheduling proposed in this application, which may include:

[0072] S101, Construct a multi-ship collaborative operation and maintenance scheduling model.

[0073] It should be noted that the multi-vessel collaborative operation and maintenance scheduling model is a mathematical model used to describe and solve multi-vessel collaborative operation and maintenance scheduling problems. Its goal is generally to optimize the effectiveness and efficiency of operation and maintenance scheduling while satisfying various constraints. For example, the multi-vessel collaborative operation and maintenance scheduling model can include vessel navigation status, task allocation, time scheduling, and resource utilization. The specific form of the multi-vessel collaborative operation and maintenance scheduling model can be adjusted according to actual requirements, and there can be multiple model forms; this application does not impose any restrictions. Offshore wind farms typically have multiple operation and maintenance vessels, which need to be rationally scheduled to ensure that the maintenance and repair of wind power equipment can be carried out efficiently. Through the multi-vessel collaborative operation and maintenance scheduling model, the optimal vessel scheduling scheme can be found, improving the operational efficiency and economic benefits of the wind farm.

[0074] S102, based on the multi-ship collaborative operation and maintenance scheduling decomposition model, the multi-ship collaborative operation and maintenance scheduling model is decomposed into multiple single-ship operation and maintenance optimization scheduling sub-models that satisfy the constraints of the multi-ship collaborative operation and maintenance scheduling model.

[0075] S103, solve each single-ship operation and maintenance optimization scheduling sub-model in sequence to obtain the solution of each single-ship operation and maintenance optimization scheduling sub-model.

[0076] S104. The solutions of each single-ship operation and maintenance optimization scheduling sub-model are merged to obtain the solution of the multi-ship collaborative operation and maintenance scheduling model, which serves as the offshore wind power operation and maintenance scheduling optimization strategy.

[0077] This application proposes an efficient optimization method for multi-vehicle collaborative offshore wind power operation and maintenance scheduling. The core of this method is a DivideFusion approach, which includes constructing a decomposition model, solving the decomposed model, solving the decomposed subproblems, and merging the solutions. This application decomposes the multi-vehicle collaborative optimization scheduling problem into two layers of optimization problems for hierarchical solution. The first layer decomposes the multi-vehicle collaborative optimization scheduling model into single-vehicle operation and maintenance scheduling problems, while ensuring that the decomposed single-vehicle scheduling problems satisfy the constraints of the original multi-vehicle collaborative optimization scheduling problem. The second layer solves the multiple decomposed single-vehicle problems sequentially, and the results are summarized to obtain the solution to the multi-vehicle collaborative optimization scheduling problem. This method successfully achieves efficient solution of the multi-vehicle collaborative optimization scheduling model for offshore wind farms, helping wind power operators and third-party operation and maintenance service providers improve the efficiency of operation and maintenance task scheduling, reduce risks, and lower operation and maintenance costs.

[0078] like Figure 2 The diagram shown is a second flowchart of an efficient optimization method for multi-vehicle collaborative offshore wind power operation and maintenance scheduling according to this application, which may include:

[0079] S201, Construct a multi-ship collaborative operation and maintenance scheduling model.

[0080] The objective function consists of three parts, as shown in equation (1).

[0081]

[0082]

[0083]

[0084] Among them, T m Indicates the time required to complete the maintenance task; Z C Z represents the number of corrective maintenance tasks not included in the maintenance schedule, as shown in equation (2); P The number of preventative maintenance tasks not included in the maintenance schedule is represented by equation (3), α. C and α P The weighting coefficients for the objective. Since the corrective maintenance has higher weights, therefore α... C >α P .

[0085] The objective function contains three distinct but related objectives. As the number of tasks scheduled for maintenance increases, i.e., Z... C and Z P When reduced, the time T to complete the maintenance m The number of units scheduled for maintenance will increase accordingly. Conversely, when the number of units included in the maintenance plan decreases, i.e., Z... C and Z P When added, the time T for completing the maintenance is... m This will be reduced accordingly. To achieve the goal of scheduling as many unit maintenance tasks as possible, and to reduce overall operation and maintenance time by optimizing maintenance paths, the target Z is... C and Z P A larger weight forces the model to prioritize scheduling more unit maintenance tasks, and to prioritize corrective maintenance tasks. The weight α C It should be greater than α P And it is much greater than 1, that is, α C >α P >>1. When the number of maintenance tasks for the unit cannot be increased, path optimization can be used to reduce the total maintenance time.

[0086] The constraints are shown in equations (4) to (32). Constraint (4) ensures that the maintenance completion time is not less than the sum of the arrival time of any node and the time for transporting technicians and equipment. Constraint (5) ensures that the send-off node and the receive-off node of each unit can only be visited once. Constraint (6) ensures that the maintenance vessel of each unit can only go from the send-off node to the receive-off node, that is, it cannot return from the receive-off node to the send-off node. Constraints (7) and (8) ensure that the vessel can only visit the send-off node and the receive-off node of the maintenance base once each. Constraint (9) ensures that the vessel returns from the receive-off node. Constraint (10) ensures that the number of times a vessel enters node j and leaves node j is the same, that is, if a vessel visits a node, then the vessel must also leave that node. Constraint (11) ensures that the number of times the send-off node and the receive-off node of each unit are visited is the same. Constraint (12) is a constraint on the vessel's load capacity. Constraints (13), (14), and (15) are constraints on the number of personnel on board, which together ensure that the number of technicians on board does not exceed the maximum number of personnel on board. The number of technicians on board is tracked by constraints (16) and (17). Constraints (18) and (19) are maintenance time window constraints, which ensure that the time for a vessel to perform maintenance tasks is within its allowed time window. Constraint (20) ensures that the time taken for maintenance and navigation during the journey from the current node to the next node is compatible with the time taken to reach the next node. Constraint (21) guarantees that the time interval between picking up and dropping off personnel is greater than the time required to perform maintenance. Constraint (22) is a constraint on the number of available technicians at the maintenance base, which ensures that the sum of the number of technicians on all vessels is less than or equal to the number of available technicians at the maintenance base. If the presence of a vessel is required during the execution of a maintenance task, constraint (23) ensures that the vessel only travels directly from the delivery node to the pickup node, i.e., waits for the maintenance task to be performed at the same location. Constraints (24)-(27) ensure the flow conservation of the pick-up and drop-off nodes at the maintenance base, while excluding invalid node transfers. Constraints (28)-(29) ensure that specific maintenance tasks require maintenance by specific vessels. Constraints (30)-(32) indicate the types of decision variables.

[0087]

[0088]

[0089]

[0090]

[0091]

[0092]

[0093]

[0094]

[0095]

[0096]

[0097]

[0098]

[0099]

[0100]

[0101]

[0102]

[0103]

[0104]

[0105]

[0106]

[0107]

[0108]

[0109]

[0110]

[0111]

[0112]

[0113]

[0114]

[0115]

[0116] S202, Construct a multi-ship collaborative operation and maintenance scheduling decomposition model.

[0117] Define the parameters, decision variables, objective function, and constraints of the decomposition model.

[0118] (1) Define the decision variable x of the decomposition model iv Among them, x iv When x = 1, it means that the unit i to be maintained is being maintained by the ship v. iv When =0, it means that the unit i to be maintained has not been maintained by the ship v.

[0119] (2) Define the parameters of the decomposition model. V represents the set of ships, v is the ship index, and the total number of ships is n. v =|V|; I represents the set of units requiring maintenance, i is the index, and the total number of units requiring maintenance is n = |I|; I v This refers to the set of units that can be repaired by a ship; d ij Represents the distance from maintenance node i to maintenance node j; P represents the set of technician types; w i Indicates the weight of spare parts and maintenance equipment required for unit i to be maintained; ρ ip This represents the number of technicians of type p required for unit i; This indicates the maximum number of passengers that ship v can carry; This indicates the maximum weight of spare parts that ship v can carry.

[0120] (3) Establish the objective function:

[0121]

[0122] Where, d max =max i,j∈I d ij , represents the maximum distance between units to be maintained; I(·) is the indicator function; when x iv =x jv When it is established, I(x) iv =x jv ) = 1, otherwise, I(x) = 1. iv =x jv ) = 0.

[0123] The objective function aims to maximize the minimum distance between maintenance units covered by different maintenance vessels. That is, to find a method for dividing maintenance tasks such that maintenance units that are close together are assigned to the same maintenance vessel, while maintaining maintenance units covered by different maintenance vessels as far apart as possible.

[0124] (4) Establish the following constraints:

[0125] Establish a unique constraint on maintenance task allocation, meaning that the maintenance task for each wind turbine can only be assigned to a single maintenance vessel:

[0126]

[0127] Establish a minimum crew task constraint, meaning each maintenance vessel must perform maintenance on at least one crew:

[0128]

[0129] Establish restrictions on the number of passengers a ship can carry:

[0130]

[0131] Establish load limits for maintenance vessels:

[0132]

[0133] Establish ship unit matching constraints, meaning that the maintenance vessel must support the maintenance tasks of the selected unit:

[0134]

[0135] Establish integer constraints for variables:

[0136]

[0137] S203 uses the CP-SAT solver of OR-Tools to solve the decomposition model through the Constraint Programming (CP) method, decomposing the multi-ship collaborative optimization scheduling model into multiple single-ship operation and maintenance optimization scheduling sub-models.

[0138] In practical applications, OR-Tools, short for Operations Research Tools, is an open-source operations research and optimization tool designed to find the optimal solution from a large number of possible solutions. OR-Tools provides various solvers, including Gurobi, CPLEX, SCIP, GLPK, GLOP, and CP-SAT. These solvers can handle different types of optimization problems, and the appropriate solver can be selected based on the characteristics and requirements of the problem.

[0139] The CP-SAT solver is a constraint satisfaction problem solver that can solve optimization problems with constraints. The solution process requires defining the variables, constraints, and objective function for each sub-model and selecting an appropriate solution algorithm for computation.

[0140] When decomposing multiple single-ship operation and maintenance optimization scheduling sub-models, the following methods can be used:

[0141] S203-1, Initialize the CP-SAT solver. Set an appropriate search time limit according to the problem size. The solution time should not be too short. It should be sufficient for the solver to find the global optimal solution of the decomposed model.

[0142] S203-2 Select an appropriate search strategy and continuously check whether the constraints are satisfied. If the assignment of a certain variable causes the constraint to be unsatisfied, the solver can backtrack to the previous state and try other assignments.

[0143] S203-3, continuously evaluate the value of the objective function to determine the quality of the current solution.

[0144] S203-4: After the solver completes the search, it outputs the optimal solution.

[0145] In practical applications, the solver can find multiple feasible optimal solutions. In this case, only one solution needs to be output.

[0146] S203-5, when the solution is finished, check whether the solution is globally optimal. If it is globally optimal, the search ends. If only a feasible solution is returned instead of the globally optimal solution, you can try adjusting the solver parameters or the search strategy and repeat steps S203-1 to S203-4.

[0147] S203-6, Based on the decision variable x in the solution obtained from the decomposition model iv The numerical value allows all maintenance tasks to be allocated to each maintenance vessel while ensuring that the constraints of the multi-vessel collaborative maintenance scheduling model are met. This process achieves model decoupling. At this point, for the maintenance tasks covered by each maintenance vessel, combining the same objective function and constraints as the multi-vessel collaborative maintenance scheduling model, a set of single-vessel maintenance optimization scheduling sub-models can be obtained. These single-vessel maintenance optimization scheduling sub-models are not coupled and can be solved independently. Since the number of tasks handled by a single maintenance vessel is limited, the solution speed of the single-vessel scheduling model will be very fast.

[0148] S204. Solve each single-ship operation and maintenance optimization scheduling sub-model in sequence, and merge the solutions to obtain the solution of the entire multi-ship collaborative operation and maintenance scheduling model.

[0149] Considering only a single maintenance vessel's single-ship maintenance optimization scheduling sub-model, the solution process from steps S203-1 to S203-4 is applied one by one to obtain the solution for that maintenance vessel, including the vessel's route planning and maintenance task scheduling. The same method is used for each maintenance vessel until solutions for all maintenance vessels are obtained.

[0150] Before merging the solutions from various maintenance vessels, conflict checks can be performed, including checking for overlapping maintenance task assignments, conflicting maintenance times, and whether the completion time for maintenance tasks falls within a given time window. If conflicts are found, the multi-vessel collaborative maintenance scheduling model can be re-decomposed.

[0151] S205, merges conflict-free single-ship solutions to obtain an optimization strategy for offshore wind power operation and maintenance scheduling of the entire multi-ship collaborative operation and maintenance scheduling model.

[0152] Offshore wind power operation and maintenance scheduling optimization strategies can include multi-vessel collaborative operation and maintenance task allocation, route planning, operation and maintenance time arrangement, spare parts arrangement, and maintenance personnel arrangement.

[0153] It should be noted that in other embodiments of this application, after obtaining the solution of the multi-ship collaborative operation and maintenance scheduling model, the feasibility of the solution can be checked again to ensure the availability of the final output results.

[0154] To fully evaluate the solution speed and optimization degree of the proposed efficient optimization method for multi-vessel collaborative offshore wind power operation and maintenance scheduling, a set of comparative examples were designed. For different numbers of vessels and turbines, the proposed method was compared with the open-source constraint programming solver OR-Tools and the commercial solver Gurobi for directly solving the multi-vessel collaborative model. The main evaluation focuses on the solution speed and optimality of the solution of the three methods.

[0155] The simulation setup included 12 offshore wind power maintenance and scheduling model solving tasks, ranging from 5 turbines per ship to 16 turbines per 4 ships, with the task size increasing exponentially. It should be noted that in a standard PC environment, the problem size for 16 turbines per 4 ships far exceeds the optimal solution size that the CP-SAT and Gurobi solvers can find. Therefore, a time limit of 2.78 hours (10,000 seconds) was set. If no optimal solution is found after this time limit, the solver will return to the best feasible solution found so far.

[0156] like Figure 3 The image shows a comparison of the solution speeds of the three methods. Figure 3 In this context, "DivideFusion" refers to the method proposed in this application, from... Figure 3 As can be seen, the solution time consumed by the Gurobi solver and the OR-Tools solver increases exponentially with the problem size, quickly reaching the set solution time limit (10,000 seconds), while the solution time of the method proposed in this application does not exceed 10 seconds, showing a significant difference in solution performance. Furthermore, the problem size of 4 ships and 16 maintenance units is far from reaching the upper limit of the solution capability of the method proposed in this application. It is worth noting that the OR-Tools solver exhibited an abnormally sharp drop in solution time on the last task. This may be because the OR-Tools solver found a relatively good solution within the first few hundred seconds of solving, but failed to find a better solution in the subsequent time, thus returning to a shorter solution time.

[0157] like Figure 4 The diagram shows a comparison of the advantages and disadvantages of the solutions obtained by the three methods. It can be seen that the feasible solution objective function value obtained by the method in this application is very close to that of the other two exact solution methods, especially when solving large-scale problems. This also proves that the solution found by the method in this application within 10 seconds has a similar degree of optimization as the best feasible solution obtained by the exact solution algorithm within 10,000 seconds. Furthermore, based on the above example settings, it can also be shown that, under the premise of similar solution accuracy, the solution speed of the method proposed in this application is nearly 1000 times faster than commercial / open-source solvers based on the branch and bound method. While solving the problem of multi-vehicle collaborative operation and maintenance scheduling in offshore wind farms, this method is expected to significantly improve the efficiency of operation and maintenance task scheduling for wind power operators and third-party operation and maintenance service providers, reduce operation and maintenance costs, and enhance the competitiveness of offshore wind power.

[0158] The method proposed in this application can achieve sub-second solutions to the multi-vessel collaborative operation and maintenance scheduling problem of offshore wind farms, significantly improving the solution efficiency of large-scale operation and maintenance scheduling problems without sacrificing the optimality of the solution. While improving solution efficiency, it is expected to significantly improve the efficiency of operation and maintenance task scheduling for wind power operators and third-party operation and maintenance service providers, reduce operation and maintenance costs, and enhance the competitiveness of offshore wind power. This brings greater sustainability and competitiveness to the offshore wind power industry and is expected to promote the effective development and utilization of more wind power resources. In practical applications, the efficient optimization method for multi-vessel collaborative offshore wind power operation and maintenance scheduling proposed in this application can also be used to solve other optimization problems with the same structure as the multi-vessel collaborative operation and maintenance scheduling model for offshore wind power.

[0159] like Figure 5 As shown, based on the above-mentioned efficient optimization method for offshore wind power operation and maintenance scheduling through multi-vessel collaboration, this application also proposes an efficient optimization system for offshore wind power operation and maintenance scheduling through multi-vessel collaboration, including:

[0160] The first building module is used to build a multi-ship collaborative operation and maintenance scheduling model;

[0161] The second model is used to construct a multi-ship collaborative operation and maintenance scheduling decomposition model.

[0162] The decomposition module is used to decompose the multi-ship collaborative operation and maintenance scheduling model into multiple single-ship operation and maintenance optimization scheduling sub-models that satisfy the constraints of the multi-ship collaborative operation and maintenance scheduling model. The objective function of the multiple single-ship operation and maintenance optimization scheduling sub-models is to maximize the minimum distance between the maintenance units covered by different operation and maintenance ships.

[0163] The solution module is used to solve each single-ship operation and maintenance optimization scheduling sub-model in sequence to obtain the solution of each single-ship operation and maintenance optimization scheduling sub-model;

[0164] The merging module is used to merge the solutions of each single-ship operation and maintenance optimization scheduling sub-model to obtain the solution of the multi-ship collaborative operation and maintenance scheduling model, which serves as the offshore wind power operation and maintenance scheduling optimization strategy.

[0165] In other embodiments of the multi-vessel collaborative offshore wind power operation and maintenance scheduling high-efficiency optimization system of this application, a checking module may also be included. The solution of each single-vessel operation and maintenance optimization scheduling sub-model includes: single-vessel path planning and operation and maintenance task scheduling. The checking module is used to check whether the operation and maintenance task allocation overlaps, whether the operation and maintenance time conflicts, and whether the completion time of the operation and maintenance tasks is within a given time window in the solutions of each single-vessel operation and maintenance optimization scheduling sub-model before the merging module merges the solutions. If all requirements are met, the solutions of each single-vessel operation and maintenance optimization scheduling sub-model are merged; otherwise, the multi-vessel collaborative operation and maintenance scheduling model is re-decomposed.

[0166] It should be noted that in other embodiments of the multi-vessel collaborative offshore wind power operation and maintenance scheduling high-efficiency optimization system of this application, the specific functions of each module can also adopt the aforementioned embodiments of the multi-vessel collaborative offshore wind power operation and maintenance scheduling high-efficiency optimization method, which will not be repeated here.

[0167] It should be noted that, in the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another device, or some features may be ignored or not executed. The modules described as separate components may or may not be physically separated. The components shown as modules may be one or more physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the modules can be selected to achieve the purpose of the solution in this embodiment according to actual needs.

[0168] Furthermore, in the various embodiments of the present invention, the modules can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The integrated unit described above can be implemented in hardware or as a software functional unit.

[0169] An electronic device provided in this application includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the steps of the efficient optimization method for multi-ship collaborative offshore wind power operation and maintenance scheduling as described in any of the above embodiments.

[0170] Another electronic device provided in this application embodiment may further include: an input port connected to a processor for transmitting multimodal data collected by an external acquisition device to the processor; a display unit connected to the processor for displaying the processor's processing results to the outside world; and a communication module connected to the processor for enabling communication between the electronic device and the outside world. The display unit may be a display panel, a laser scanner, or the like; the communication method used by the communication module includes, but is not limited to, Mobile High Definition Link (HML), Universal Serial Bus (USB), High Definition Multimedia Interface (HDMI), wireless connectivity: Wi-Fi, Bluetooth communication, Bluetooth Low Energy communication, and IEEE 802.11s-based communication technology.

[0171] This application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps of the efficient optimization method for multi-ship collaborative offshore wind power operation and maintenance scheduling described in any of the above embodiments.

[0172] The computer-readable storage media involved in this application include random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage media known in the art.

[0173] For descriptions of relevant parts of the multi-vessel collaborative offshore wind power operation and maintenance scheduling high-efficiency optimization system, electronic equipment, and computer-readable storage medium provided in this application's embodiments, please refer to the detailed descriptions of the corresponding parts in the multi-vessel collaborative offshore wind power operation and maintenance scheduling high-efficiency optimization method provided in this application's embodiments; they will not be repeated here. Furthermore, parts of the technical solutions provided in this application that are consistent with the implementation principles of corresponding technical solutions in the prior art are not described in detail to avoid excessive elaboration.

[0174] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A highly efficient and optimized method for multi-vessel collaborative operation and maintenance scheduling of offshore wind power, characterized in that, include: Construct a multi-ship collaborative operation and maintenance scheduling model; Construct a multi-ship collaborative operation and maintenance scheduling decomposition model; Based on the multi-ship collaborative operation and maintenance scheduling decomposition model, the multi-ship collaborative operation and maintenance scheduling model is decomposed into multiple single-ship operation and maintenance optimization scheduling sub-models that satisfy the constraints of the operation and maintenance scheduling model; the multi-ship collaborative operation and maintenance scheduling decomposition model is used to determine the maintenance allocation relationship between wind turbine units and operation and maintenance vessels, and the maintenance task decomposition is achieved by constructing a model with the goal of maximizing the minimum distance between the sets of maintenance units covered by different operation and maintenance vessels. The objective function of the multi-ship collaborative operation and maintenance scheduling decomposition model includes: in, I This indicates a set of units that require maintenance. V Indicates a collection of ships. or , Indicates the unit awaiting maintenance. i Ship v repair, Indicates the unit awaiting maintenance. i Not by ship v repair, or , Indicates the unit awaiting maintenance. j Ship v repair, Indicates the unit awaiting maintenance. j Not by ship v repair, This indicates the maximum distance between units requiring maintenance; For the characteristic function, when At the time of its establishment, ,otherwise, ; Indicates maintenance node To the maintenance node The distance; The constraints of the multi-ship collaborative operation and maintenance scheduling decomposition model include: Uniqueness constraint for maintenance task assignment: Minimum crew task constraints: Ship passenger capacity restrictions: in, Indicates the unit awaiting maintenance. The required type is The number of technical personnel Indicates a ship The maximum number of passengers that can be carried; Maintenance vessel load capacity constraints: in, Indicates the unit awaiting maintenance. The required weight of spare parts and maintenance equipment Indicates a ship The maximum weight of spare parts that can be carried; Ship engine unit matching constraints: in, Indicates that it can be used by ships A collection of units under maintenance; Integer constraint for variables: Solve each single-ship operation and maintenance optimization scheduling sub-model sequentially to obtain the solution of each single-ship operation and maintenance optimization scheduling sub-model; By merging the solutions of each individual vessel operation and maintenance optimization scheduling sub-model, the solution of the multi-vessel collaborative operation and maintenance scheduling model is obtained, which serves as the optimization strategy for offshore wind power operation and maintenance scheduling.

2. The efficient optimization method for multi-vessel collaborative offshore wind power operation and maintenance scheduling according to claim 1, characterized in that, The decomposition of the multi-ship collaborative operation and maintenance scheduling model into multiple single-ship operation and maintenance optimization scheduling sub-models that satisfy the constraints of the operation and maintenance scheduling model, according to the multi-ship collaborative operation and maintenance scheduling decomposition model, includes: The CP-SAT solver is used to solve the decomposition model using the constraint programming method. Based on the solution of the decomposition model, the multi-ship collaborative operation and maintenance scheduling model is decomposed into multiple single-ship operation and maintenance optimization scheduling sub-models, and all of the multiple single-ship operation and maintenance optimization scheduling sub-models satisfy the constraint conditions of the multi-ship collaborative operation and maintenance scheduling model.

3. The efficient optimization method for multi-vessel collaborative offshore wind power operation and maintenance scheduling according to claim 2, characterized in that, The solutions of each individual ship operation and maintenance optimization scheduling sub-model include: the path planning and operation and maintenance task scheduling of the individual ship.

4. The efficient optimization method for multi-vessel collaborative offshore wind power operation and maintenance scheduling according to claim 3, characterized in that, The solution of merging the solutions of each individual ship operation and maintenance optimization scheduling sub-model also includes conflict checking: Check whether the operation and maintenance tasks overlap, whether the operation and maintenance times conflict, and whether the time to complete the operation and maintenance tasks is within the given time window in the solutions of each single ship operation and maintenance optimization scheduling sub-model. If all requirements are met, merge the solutions of each single ship operation and maintenance optimization scheduling sub-model; otherwise, re-decompose the multi-ship collaborative operation and maintenance scheduling model.

5. A highly efficient optimization system for multi-vehicle collaborative offshore wind power operation and maintenance scheduling to implement the method of claim 1, characterized in that, include: The first building module is used to build a multi-ship collaborative operation and maintenance scheduling model; The second building module is used to construct a multi-ship collaborative operation and maintenance scheduling decomposition model; The decomposition module is used to decompose the multi-ship collaborative operation and maintenance scheduling model into multiple single-ship operation and maintenance optimization scheduling sub-models that satisfy the constraints of the multi-ship collaborative operation and maintenance scheduling model. The multi-ship collaborative operation and maintenance scheduling decomposition model is used to determine the maintenance allocation relationship between wind turbine units and operation and maintenance vessels, and to decompose maintenance tasks by constructing a model that aims to maximize the minimum distance between the sets of maintenance units covered by different operation and maintenance vessels. The solution module is used to solve each single-ship operation and maintenance optimization scheduling sub-model in sequence to obtain the solution of each single-ship operation and maintenance optimization scheduling sub-model; The merging module is used to merge the solutions of each single-ship operation and maintenance optimization scheduling sub-model to obtain the solution of the multi-ship collaborative operation and maintenance scheduling model, which serves as the offshore wind power operation and maintenance scheduling optimization strategy.

6. The efficient optimization system for multi-vessel collaborative offshore wind power operation and maintenance scheduling according to claim 5, characterized in that, It also includes an inspection module; The solutions of each single-ship operation and maintenance optimization scheduling sub-model include: single-ship path planning and operation and maintenance task scheduling; The inspection module is used to check whether the operation and maintenance tasks overlap, whether the operation and maintenance times conflict, and whether the time to complete the operation and maintenance tasks is within a given time window in the solutions of each single-ship operation and maintenance optimization scheduling sub-model before the merging module merges the solutions of each single-ship operation and maintenance optimization scheduling sub-model. If all requirements are met, the solutions of each single-ship operation and maintenance optimization scheduling sub-model are merged; otherwise, the multi-ship collaborative operation and maintenance scheduling model is decomposed again.

7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor is configured to execute the computer program to implement the steps of the efficient optimization method for multi-ship collaborative offshore wind power operation and maintenance scheduling as described in any one of claims 1 to 4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the efficient optimization method for multi-ship collaborative offshore wind power operation and maintenance scheduling as described in any one of claims 1 to 4.

Images