Multi-objective optimization decision-making method and system for wind power plant maintenance plan

Abstract

The invention discloses a multi-objective optimization decision-making method and system for a wind power plant maintenance plan, and belongs to the technical field of wind power plant operation and maintenance management. Based on the operation data of the wind power plant, a maintenance plan is calculated through a multi-objective optimization algorithm, the multi-objective optimization algorithm takes at least three optimization objectives as optimization basis, and the optimization objectives comprise a power generation efficiency objective, a maintenance cost objective and a maintenance cycle objective; generating fault early warning information based on the wind power plant operation data; dynamically adjusting the maintenance plan based on the fault early warning information, and generating a final maintenance plan; and according to the final maintenance plan, scheduling resources and executing a maintenance task, so that the problems of insufficient optimization of the wind power plant maintenance plan and unreasonable resource scheduling are solved.

Description

Technical Field

[0001] The invention belongs to the technical field of wind farm operation and maintenance management, and relates to a multi-objective optimization decision-making method and system for a wind farm maintenance plan. Background Art

[0002] As an important renewable energy power generation method, the operating efficiency of wind farms directly affects the stability and economy of power supply. With the continuous development and application of wind power technology, the scale of wind farms has gradually expanded, and the operating data of a single wind turbine has presented a large amount of complex information. These data not only involve the real-time operating status of the wind turbine, but also include meteorological data, equipment maintenance records, fault warning information, etc. How to effectively manage and analyze these massive data and optimize the operation and maintenance plan of wind turbines has become the key to improving the overall efficiency of wind farms.

[0003] At present, the operation and maintenance management of wind farms mainly relies on manual experience and traditional regular inspection methods. However, with the expansion of the scale of wind farms, traditional maintenance methods can no longer meet the needs of efficient operation and maintenance. Many wind farms still have problems such as unscientific maintenance plans, unreasonable resource allocation, and untimely fault diagnosis, which lead to low operating efficiency of wind turbines and even equipment failures that may cause downtime and economic losses. In addition, most of the existing wind farm operation and maintenance management systems lack intelligent optimization decision support and can only provide basic data monitoring functions, lacking the ability to comprehensively optimize multiple goals such as maintenance cycle, cost and efficiency. Summary of the invention

[0004] The purpose of the present invention is to solve the technical problems of insufficient optimization of wind farm maintenance plans and unreasonable resource scheduling in the prior art, and to provide a multi-objective optimization decision-making method and system for wind farm maintenance plans, which can comprehensively consider multiple objectives such as the power generation efficiency, maintenance cost and maintenance cycle of the wind farm, generate the optimal maintenance plan through an intelligent optimization algorithm, maximize the operating efficiency of the wind farm, and improve the availability and economy of the wind turbines.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: A first aspect of the present invention provides a multi-objective optimization decision-making method for a wind farm maintenance plan, comprising the following steps: Obtain wind farm operation data; Based on the operation data of the wind farm, a maintenance plan is calculated by a multi-objective optimization algorithm, wherein the multi-objective optimization algorithm takes at least three optimization objectives as optimization basis, and the optimization objectives include: power generation efficiency objective, maintenance cost objective and maintenance cycle objective; Generate fault warning information based on wind farm operation data; dynamically adjust the maintenance plan based on the fault warning information to generate a final maintenance plan; According to the final maintenance plan, resources are dispatched and maintenance tasks are performed.

[0006] Furthermore, the multi-objective optimization method for wind farm maintenance plan of the present invention further includes: Monitor the execution of maintenance tasks in real time, and provide decision support and adjustment suggestions to operation and maintenance personnel.

[0007] Furthermore, after the maintenance task is executed, the method further includes displaying a visualized optimization decision result to the operation and maintenance personnel and providing real-time status feedback of the task execution.

[0008] Furthermore, the multi-objective optimization algorithm adopts a particle swarm optimization algorithm.

[0009] Furthermore, the wind farm operation data includes real-time operation data collected from the wind farm's SCADA system, CMS diagnostic system and meteorological system.

[0010] Furthermore, the generating of fault warning information specifically includes: based on the wind farm operation data, using the SVM model to perform fault warning on the operation status of the wind turbine to generate the fault warning information.

[0011] A second aspect of the present invention provides a multi-objective optimization decision-making system for a wind farm maintenance plan, comprising: Data collection and management module, used to obtain wind farm operation data; An optimization decision module, used to calculate a maintenance plan based on the operation data of the wind farm by a multi-objective optimization algorithm, wherein the multi-objective optimization algorithm takes at least three objectives as optimization basis, and the objectives include: power generation efficiency objective, maintenance cost objective and maintenance cycle objective; The wind turbine fault diagnosis and early warning module is used to generate fault early warning information based on the wind farm operation data; based on the fault early warning information, the maintenance plan is dynamically adjusted to generate a final maintenance plan; The task scheduling and execution module is used to schedule resources and execute maintenance tasks according to the final maintenance plan.

[0012] Furthermore, the system also includes a visual decision support module for displaying visual optimization results to operation and maintenance personnel and providing real-time status feedback of task execution.

[0013] Furthermore, the visual decision support module includes a decision display unit and a decision adjustment feedback unit. The decision display unit provides a graphical interface for displaying the optimized maintenance plan and task execution progress; the decision adjustment feedback unit provides a feedback channel to support operation and maintenance personnel to adjust the maintenance plan.

[0014] Furthermore, the task scheduling and execution module includes a resource scheduling unit and a task execution unit; the resource scheduling unit is responsible for allocating required resources according to the maintenance plan, and the task execution unit is responsible for specific task execution and feedback.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a multi-objective optimization decision-making method for a wind farm maintenance plan. By introducing a multi-objective optimization decision-making method, it is possible to comprehensively consider multiple objectives such as the power generation efficiency, maintenance cost, and maintenance cycle of the wind farm, thereby solving the problems of unscientific wind farm maintenance plans and unreasonable resource scheduling in the prior art. Through intelligent analysis and optimization calculation of a large amount of wind farm operation data, the system can dynamically adjust the maintenance plan to ensure that the wind turbine is maintained at the most appropriate time, thereby effectively reducing the failure rate of the wind turbine and improving power generation efficiency. At the same time, the optimized maintenance plan not only meets the maintenance needs, but also significantly reduces the maintenance cost and downtime, thereby improving the overall operation and maintenance efficiency.

[0016] Furthermore, the invention is highly scalable and can adapt to the needs of wind farms of different sizes and types, providing strong technical support for the intelligent operation and maintenance management of wind farms and promoting the sustainable development and optimization of the wind power industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic diagram of a flow chart of a multi-objective optimization decision-making method for a wind farm maintenance plan according to an embodiment of the present invention; Figure 2 The figure is a schematic diagram of the structure of a multi-objective optimization decision-making system for a wind farm maintenance plan according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention described and marked in the drawings here can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0022] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0023] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0024] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0025] The present invention is further described in detail below in conjunction with the accompanying drawings: Example 1 This embodiment proposes a multi-objective optimization decision-making method for wind farm maintenance plan, such as Figure 1 As shown, the basic goal of the method is to dynamically adjust the maintenance plan of the wind farm through a multi-objective optimization algorithm to maximize the operating efficiency of the wind farm, minimize the maintenance cost, and optimize the configuration of maintenance resources; the multi-objective optimization method of the wind farm maintenance plan of this embodiment includes the following steps: S1, first of all, data collection is carried out. This stage is to provide basic data for subsequent optimization decisions. The data mainly comes from the SCADA system, CMS diagnostic system and meteorological data acquisition system of the wind farm. Specifically, the SCADA system provides the operating status data of the wind turbine, such as wind turbine power, wind speed, temperature, humidity and other environmental parameters. The CMS diagnostic system provides the fault record, equipment status, maintenance history and equipment wear of the wind turbine. In addition, the meteorological data acquisition system obtains real-time meteorological conditions, which has an important impact on the evaluation of wind turbine performance and fault prediction.

[0026] S2, after data collection is completed, all raw data are preprocessed, missing data and outliers are cleaned, and standardized to ensure data consistency and availability. The preprocessed data will be input into the subsequent optimization decision model.

[0027] S3, based on data collection and preprocessing, it is necessary to define multiple optimization objective functions. The specific objective functions include: S301, Wind farm power generation efficiency target: The wind farm power generation efficiency target is to maximize the power generation efficiency of the wind farm. The power generation efficiency is usually measured by the actual power of the wind turbine. With theoretical power The goal is to minimize the deviation between the two. The formula is:

[0028] in, For a specific wind speed The fan power measured under is the theoretical power predicted based on wind speed.

[0029] S302, maintenance cost target: This objective function aims to minimize the various resource costs required during the maintenance process, including personnel costs, equipment costs, and material costs. The specific calculation method is based on historical data and estimated resource usage, and the formula is expressed as:

[0030] in, Represents the cost of resources and materials required for maintenance.

[0031] S303, maintenance cycle optimization objective: This objective function is used to optimize the periodic arrangement of maintenance tasks to ensure that maintenance tasks are neither delayed nor too frequent. The maintenance cycle should avoid unnecessary downtime and excessive maintenance while ensuring the normal operation of the wind farm. The formula is:

[0032] in, Indicates the time required to complete the maintenance task.

[0033] S4, after the objective function is defined, the maintenance plan is optimized using a multi-objective optimization algorithm. Common multi-objective optimization algorithms include particle swarm optimization (PSO), genetic algorithm (GA) and ant colony algorithm (ACO). In this embodiment, the particle swarm optimization algorithm (PSO) is used. The particle swarm optimization algorithm searches for the optimal solution of multiple objective functions by simulating the foraging behavior of bird flocks in nature.

[0034] The basic idea of ​​the particle swarm optimization algorithm is to randomly generate a set of solutions (i.e., maintenance plans) at the beginning, then evaluate the pros and cons of each solution based on the fitness of the objective function, update the speed and position of the solution, and gradually approach the optimal solution. Each iteration will update the solution set until the preset stop condition (such as the maximum number of iterations or fitness threshold) is met.

[0035] The key to the optimization process is to find the best point to balance power generation efficiency, maintenance cost and cycle by adjusting the configuration of various wind farm resources (such as personnel, equipment, materials, etc.). Ultimately, the optimization result will obtain an optimal maintenance plan, including wind turbine maintenance time, resource allocation, and priority information.

[0036] S5, through the fan fault diagnosis and early warning module, the system can use machine learning algorithms (such as support vector machines, decision trees, etc.) to predict faults based on historical fault data and real-time operation data. According to the prediction results, the system can make dynamic adjustments during the execution of the maintenance plan. For example, if a fan is predicted to have a possible failure, the maintenance priority of the fan will be automatically increased.

[0037] In addition, the system will monitor the operating status of the wind farm in real time. Once any abnormality is found in the operation of the wind turbine, the system will use the early warning mechanism to remind the operation and maintenance personnel to take countermeasures to ensure the operating stability of the wind farm.

[0038] Example 2 This embodiment proposes a wind farm maintenance plan optimization system. The system integrates multiple functional modules, including a data collection and management module, an optimization decision module, a wind turbine fault diagnosis and early warning module, a task scheduling and execution module, and a visual decision support module. The design goal of the system is to improve the maintenance efficiency of wind farms, reduce costs, and monitor and optimize maintenance plans in real time.

[0039] The multi-objective optimization system architecture of wind farm maintenance plan is shown in the attached figure. Figure 2 As shown in the figure, the system consists of five main modules: 1. Data collection and management module: This module is responsible for obtaining the operation data of the wind farm from multiple systems (such as SCADA system, CMS diagnostic system, meteorological monitoring system, etc.). Through these data, the system can grasp the operation status and environmental conditions of the wind farm in real time. The acquired data includes but is not limited to the real-time power of the wind turbine, meteorological data, equipment operation status and fault history. All data are transmitted to the data storage module, cleaned and formatted to ensure the accuracy and consistency of subsequent processing.

[0040] 2. Optimization decision module: The optimization decision module is the core module of the system, responsible for multi-objective optimization based on the collected data and the defined objective function. This module uses the particle swarm optimization (PSO) algorithm to optimize the maintenance plan. Based on the actual operation data, the optimization algorithm will balance the wind farm's power generation efficiency, maintenance cost and cycle, and generate an optimal maintenance plan.

[0041] 3. Fan fault diagnosis and early warning module: This module uses machine learning algorithms (such as support vector machines, decision trees, etc.) to predict fan faults based on real-time monitoring data and historical fault data. When the system detects that a fan may fail, it will generate early warning information and pass it to the optimization decision module to dynamically adjust the maintenance plan.

[0042] 4. Task scheduling and execution module: This module schedules maintenance tasks to different locations of the wind farm based on the results of the optimization decision, and adjusts the maintenance execution order based on the priority of the task and the resource situation. The task scheduling module ensures that the maintenance tasks can be completed on time by coordinating personnel, equipment and material resources.

[0043] 5. Visual Decision Support Module: This module is responsible for displaying the optimization results to the operation and maintenance personnel in a graphical way. Through the interactive interface, the operation and maintenance personnel can clearly view the execution of the maintenance plan, including the progress status of each task, the maintenance priority of the fan and other information. The Visual Decision Support Module can also generate detailed reports according to needs, helping managers make more accurate decisions and adjust the maintenance plan when necessary.

[0044] The workflow of the wind farm maintenance plan optimization system in this embodiment is as follows: First, the data collection and management module obtains the operating data of the wind farm from multiple data sources (SCADA, CMS, and meteorological systems, etc.) in real time. After preprocessing, the data enters the optimization decision module to perform multi-objective optimization based on the objective function. On this basis, the wind turbine fault diagnosis and early warning module analyzes the system status through the fault prediction model, and feeds back possible fault warnings to the optimization decision module. The optimization decision module dynamically adjusts the maintenance plan based on this information, and schedules the task to the task scheduling and execution module for actual operation. Finally, the visual decision support module graphically displays the overall operating status of the system and the execution of maintenance tasks for reference and adjustment by operation and maintenance personnel.

[0045] In this embodiment, the key technical features of the system are as follows: 1. Multi-objective optimization algorithm: The system uses particle swarm optimization (PSO) as a multi-objective optimization algorithm to ensure that the optimal maintenance plan is found while balancing multiple objective functions (such as power generation efficiency, maintenance cost, and maintenance cycle).

[0046] 2. Wind turbine fault prediction: Through the wind turbine fault diagnosis and early warning module, combined with machine learning algorithms (such as support vector machines, decision trees, etc.), possible faults can be predicted in advance and maintenance plans can be dynamically adjusted to ensure the efficiency and stability of the wind farm during operation.

[0047] 3. Task scheduling and resource optimization: Based on the optimal maintenance plan output by the optimization decision module, the task scheduling and execution module is responsible for reasonably arranging the execution order of maintenance tasks to ensure that maintenance resources (such as personnel, equipment, etc.) are reasonably allocated to avoid waste of resources.

[0048] 4. Visualized decision support: The system provides a visual decision support platform to help operation and maintenance personnel better understand the execution of maintenance tasks and the operating status of wind farms. Through this platform, managers can monitor the progress of maintenance tasks in real time and make adjustments.

[0049] The multi-objective optimization system for wind farm maintenance plan provided by the present invention solves the problems of low efficiency, unreasonable resource allocation and high cost in traditional wind farm maintenance plan through multi-objective optimization algorithm, dynamic adjustment and fault prediction, intelligent task scheduling and other technical means. The system not only improves the maintenance efficiency of wind farms, but also can optimize and dynamically adjust maintenance tasks in real time to ensure that wind farms can maintain efficient and stable operation.

[0050] The present invention provides a multi-objective optimization decision-making method and system for wind farm maintenance planning, aiming to solve the problems of low efficiency, high cost and uneven resource allocation in traditional wind farm maintenance planning through big data analysis and intelligent algorithms. The technical solution combines the real-time data of the wind farm with the multi-objective optimization algorithm, and through the precise optimization model and intelligent decision support system, it realizes the efficient scheduling of wind farm maintenance tasks, accurate resource allocation and fault prediction, thereby improving the overall efficiency of the wind farm and reducing operating costs.

[0051] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A multi-objective optimization decision-making method for wind farm maintenance plan, characterized in that: The following steps are involved: Obtain wind farm operation data; Based on the operation data of the wind farm, a maintenance plan is calculated by a multi-objective optimization algorithm, wherein the multi-objective optimization algorithm takes at least three optimization objectives as optimization basis, and the optimization objectives include: power generation efficiency objective, maintenance cost objective and maintenance cycle objective; Generate fault warning information based on wind farm operation data; dynamically adjust the maintenance plan based on the fault warning information to generate a final maintenance plan; According to the final maintenance plan, resources are dispatched and maintenance tasks are performed.

2. The multi-objective optimization method for wind farm maintenance plan according to claim 1, characterized in that: Also includes: Monitor the execution of maintenance tasks in real time, and provide decision support and adjustment suggestions to operation and maintenance personnel.

3. The multi-objective optimization method for wind farm maintenance plan according to claim 1, characterized in that: After the maintenance task is executed, the method further includes displaying a visualized optimization decision result to the operation and maintenance personnel and providing real-time status feedback of the task execution.

4. The multi-objective optimization method for wind farm maintenance plan according to claim 1, characterized in that: The multi-objective optimization algorithm adopts a particle swarm optimization algorithm.

5. The multi-objective optimization method for wind farm maintenance plan according to claim 1, characterized in that: The wind farm operation data includes real-time operation data collected from the wind farm's SCADA system, CMS diagnosis system and meteorological system.

6. The multi-objective optimization method for wind farm maintenance plan according to claim 1, characterized in that: The generating of fault warning information specifically includes: based on the wind farm operation data, using the SVM model to perform fault warning on the operation status of the wind turbine, and generating the fault warning information.

7. A multi-objective optimization decision-making system for wind farm maintenance planning, characterized in that: include: Data collection and management module, used to obtain wind farm operation data; An optimization decision module, used to calculate a maintenance plan based on the operation data of the wind farm by a multi-objective optimization algorithm, wherein the multi-objective optimization algorithm takes at least three objectives as optimization basis, and the objectives include: power generation efficiency objective, maintenance cost objective and maintenance cycle objective; The wind turbine fault diagnosis and early warning module is used to generate fault early warning information based on the wind farm operation data; based on the fault early warning information, the maintenance plan is dynamically adjusted to generate a final maintenance plan; The task scheduling and execution module is used to schedule resources and execute maintenance tasks according to the final maintenance plan.

8. The multi-objective optimization system for wind farm maintenance plan according to claim 7, characterized in that: It also includes a visual decision support module, which is used to display visual optimization results to operation and maintenance personnel and provide real-time status feedback of task execution.

9. The multi-objective optimization system for wind farm maintenance plan according to claim 8, characterized in that: The visual decision support module includes a decision display unit and a decision adjustment feedback unit. The decision display unit provides a graphical interface for displaying the optimized maintenance plan and task execution progress; the decision adjustment feedback unit provides a feedback channel to support operation and maintenance personnel to adjust the maintenance plan.

10. The multi-objective optimization system for wind farm maintenance plan according to claim 7, characterized in that: The task scheduling and execution module includes a resource scheduling unit and a task execution unit; the resource scheduling unit is responsible for allocating required resources according to the maintenance plan, and the task execution unit is responsible for specific task execution and feedback.

Images