Operation and maintenance planning method for wind farm

Abstract

The present invention relates to the technical field of wind power generation, and specifically relates to an operation and maintenance planning method for a wind farm. The method comprises: acquiring historical operation data of a wind farm and preprocessing same; extracting the position distribution of wind turbines in the wind farm, and constructing a fault prediction model, so as to output a spare part demand prediction result; constructing a spare part scheduling model to output a spare part scheduling plan; and constructing an operation and maintenance personnel scheduling model on the basis of the spare part scheduling plan, so as to output an operation and maintenance personnel scheduling result. The purpose thereof is to solve the technical problem of efficient and low-cost operation and maintenance of small-capacity wind turbines.

Description

A wind farm operation and maintenance planning method Technical Field

[0001] This invention relates to the field of wind power generation technology, and more specifically to a wind farm operation and maintenance planning method. Background Technology

[0002] Against the backdrop of the current global energy transition, wind power, as a crucial renewable energy source, is undergoing unprecedented transformation and upgrading in its power generation technology and applications. Small wind turbines, especially 1.5MW and 2.0MW units, have played a key role in the wind power market over the past decade. However, as these devices gradually exceed the manufacturer's warranty period, they face more severe operation and maintenance challenges. These early wind turbines may have had shortcomings in the design and production stages, such as inappropriate material selection, unreasonable structural design, or lax process control, leading to poor equipment stability, high failure rates, and thus affecting overall power generation efficiency and economic benefits. Over time, after the wind turbines eventually expire, original manufacturer support weakens, spare parts procurement cycles become long and costly, and the diversity of turbine models results in a wide variety of spare parts, placing enormous pressure on inventory management and cost control. In particular, spare parts shortages directly lead to extended unplanned downtime of wind turbines, affecting power generation and operation and maintenance efficiency.

[0003] Currently, large power generation groups are placing higher demands on the real-time monitoring and operation and maintenance response of wind turbines. Although wind farm control centers can collect a large amount of wind turbine operation data, traditional operation and maintenance management models struggle to meet the rapid response needs of these smaller wind turbine units. This ultimately leads to a significant increase in operation and maintenance costs over time, making traditional operation and maintenance models inadequate for the efficient and low-cost operation and maintenance requirements of modern wind power systems. Therefore, there is an urgent need to develop an operation and maintenance planning methodology for wind farms. Summary of the Invention

[0004] To address the technical challenges of efficient and low-cost operation and maintenance of small-capacity wind turbine generators, this invention aims to provide a wind farm operation and maintenance planning method. The specific technical solution adopted is as follows:

[0005] A wind farm operation and maintenance planning method, the method comprising:

[0006] Acquire historical operational data of the wind farm and perform preprocessing;

[0007] Extract the location distribution of wind turbines within the wind farm, construct a fault prediction model, and output the spare parts demand prediction results;

[0008] Construct a spare parts scheduling model and output a spare parts scheduling plan;

[0009] A scheduling model for maintenance personnel is built based on the spare parts scheduling plan, and the scheduling results for maintenance personnel are output.

[0010] Furthermore, the historical operating data of the wind farm includes at least wind turbine operating status data, historical fault data, spare parts consumption data, wind turbine location data, and wind turbine warranty period data.

[0011] Furthermore, the location distribution of wind turbines within the wind farm is extracted, a fault prediction model is constructed, and the output spare parts demand prediction results include:

[0012] Integrate wind farm turbine location data, warehouse location data, topographic data, and road network data;

[0013] Based on historical operating data of wind farms, predict wind turbine failures within the wind farm and forecast the demand for spare parts in the future.

[0014] Calculate the initial cost of the faulty fan based on the spare parts demand.

[0015] Furthermore, based on historical operating data of wind farms, predictions of wind turbine failures within the wind farm and forecasts of spare parts demand in the near future also include:

[0016] Obtain the location data of the faulty fans, calculate the straight-line distance between the faulty fans, and divide the faulty fans into clusters;

[0017] Calculate the cluster effect coefficient and isolation coefficient of the faulty fan;

[0018] Predict the demand for spare parts in the near future based on the cluster effect coefficient and the isolation coefficient.

[0019] Furthermore, the initial cost of a faulty fan, calculated based on spare parts requirements, includes:

[0020] Based on the initial cost of spare parts demand, Monte Carlo simulation is used to simulate the uncertainty of spare parts demand and obtain the probability distribution of spare parts demand.

[0021] Using Monte Carlo simulation, combined with the wind turbine's operating years and warranty period, the initial cost is optimized based on the spare parts costs inside and outside the warranty period.

[0022] Furthermore, based on historical operating data of wind farms, predictions of wind turbine failures within the wind farm and forecasts of spare parts demand in the near future also include:

[0023] A clustering algorithm is used to divide the wind turbines into different clusters based on a preset distance.

[0024] Calculate the cluster effect coefficient and isolation coefficient based on the average fan density within the cluster;

[0025] Isolation fans are identified based on the isolation coefficient, and temporary spare parts storage points are set up for the isolation fans.

[0026] Furthermore, a spare parts scheduling model is constructed, and the output spare parts scheduling plan includes:

[0027] Obtain the fluctuation distribution of spare parts supply;

[0028] Define the quantity of decision variables;

[0029] To minimize spare parts replacement costs, a spare parts scheduling model is constructed. The model takes into account the spare parts demand forecast results under the influence of wind turbine location and warranty period, and solves for the optimal spare parts scheduling scheme.

[0030] Furthermore, the spare parts scheduling model includes:

[0031] The minimum spare parts inventory level constraint is defined as the spare parts inventory level not being lower than the preset minimum spare parts inventory level at any time.

[0032] The wind turbine downtime limit constraint is defined as any wind turbine downtime not being less than the preset maximum wind turbine downtime;

[0033] Spare parts inventory level constraint is defined as the spare parts inventory level at any time being able to cover spare parts demand adjusted by cluster effect coefficient and isolation coefficient;

[0034] Warranty period constraint is defined as the ability of spare parts inventory levels at any given time to cover spare parts demand adjusted by the warranty option weighting factor.

[0035] Furthermore, based on the spare parts scheduling plan, a scheduling model for maintenance personnel is constructed, and the output scheduling results for maintenance personnel include:

[0036] Define decision variables for operations and maintenance personnel;

[0037] Enter the preset operation and maintenance policy;

[0038] With the goal of minimizing the cost of operations and maintenance personnel, a scheduling model for operations and maintenance personnel is constructed, and the optimal scheduling plan is solved.

[0039] Furthermore, the operations and maintenance personnel scheduling model includes:

[0040] The hour constraint is defined as the total number of working hours of maintenance personnel at any given time not exceeding the preset maximum allowed working hours.

[0041] The first headcount constraint is defined as the minimum number of maintenance personnel required to complete the spare parts replacement task at any given time.

[0042] The second head constraint is defined as the number of maintenance personnel at any given time meeting the spare parts requirements adjusted by the cluster effect coefficient and the isolated turbine flag.

[0043] The third constraint on the number of personnel is defined as ensuring that the number of maintenance personnel at any given time meets the spare parts requirements adjusted by the warranty option weighting factor.

[0044] The present invention has the following beneficial effects:

[0045] This invention provides a wind farm operation and maintenance planning method. By predicting the failure probability of wind turbines, and based on the predicted demand for spare parts, it further considers the impact of wind turbine location and warranty period on spare parts replacement time and cost. This helps decision-makers understand the fluctuation range of spare parts demand, avoids excessive reserves and waste, and also avoids the problems of wind turbine downtime and high procurement costs caused by insufficient spare parts. Finally, it extracts the optimal operation and maintenance personnel scheduling plan and spare parts dispatching scheme, reduces personnel and spare parts costs, and ensures timely availability of spare parts. The model can be adjusted according to the specific conditions of wind farms to adapt to wind farms of different sizes and distributions. Attached Figure Description

[0046] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 is a flowchart illustrating a wind farm operation and maintenance planning method according to an embodiment of the present invention. Detailed Implementation

[0048] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a wind farm operation and maintenance planning method proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0050] The following description, in conjunction with the accompanying drawings, details a specific scheme for a wind farm operation and maintenance planning method provided by the present invention.

[0051] Please refer to Figure 1, which shows a flowchart of a wind farm operation and maintenance planning method according to an embodiment of the present invention. The wind farm operation and maintenance planning method includes:

[0052] Step S100: Obtain historical operating data of the wind farm and perform preprocessing; the historical operating data of the wind farm shall include at least wind turbine operating status data, historical fault data, spare parts consumption data, wind turbine location data, and wind turbine warranty period data; the wind turbine operating status data shall include at least start, stop, and fault status; the historical fault data shall include at least: fault type, occurrence time, and repair time; the spare parts consumption data shall include at least: spare parts name, consumption time, and consumption quantity; the wind turbine location data shall include at least: latitude and longitude coordinates and altitude; the preprocessing of this data shall include, but is not limited to, removing outliers, filling missing values, and standardizing values;

[0053] Step S200: Extract the location distribution of wind turbines in the wind farm, construct a fault prediction model, and output the spare parts demand prediction results; specifically, the specific location information of wind turbines can be extracted through a geographic information system (GIS), and machine learning or deep learning models can be trained in combination with historical fault data to predict the types of faults that may occur in the future and their probabilities, and then the required quantity of spare parts can be determined by predicting the possible faults in advance.

[0054] Step S200 specifically includes:

[0055] Step S210: Integrate wind farm turbine location data, warehouse location data, topographic data, and road network data; specifically, collect the exact geographical coordinates of each wind turbine within the wind farm using a GIS system; warehouse location data includes the coordinates of spare parts warehouses, which can be used to calculate the shortest path from the warehouse to the wind turbine; topographic data includes at least slope and soil type, which can be obtained through remote sensing images or topographic maps; road network data includes at least road type, width, and length, which helps determine the optimal route for spare parts transportation; integrate the above data to provide comprehensive information support for subsequent fault prediction and spare parts demand forecasting;

[0056] Step S220: Predict wind turbine failures within the wind farm based on historical wind farm operation data, and predict the demand for spare parts and the downtime of wind turbines in the future. Specifically, extract features from the historical wind farm operation data, including but not limited to average wind speed, temperature change, generator vibration frequency, operating hours, wind turbine load, ambient humidity, and power output. Models such as random forests, support vector machines, and neural networks can be used to perform the prediction task. The expression is: P f (t)=f(x t ;θ)

[0057] In the formula, P f (t) is the probability of the wind turbine failing at time t; x t Let represent the feature vector input at time t; θ represent the first model parameters; f(.) represent the prediction model;

[0058] Step S220 specifically includes:

[0059] Step S221: Obtain the location data of the faulty fans, calculate the straight-line distance between the faulty fans, and divide the faulty fans into clusters. The expression is as follows:

[0060] In the formula, d im This represents the straight-line distance from faulty fan i to faulty fan m; (x i -y i ) 2 and (x) m -y m ) 2 These are the coordinates of the faulty fan i and the faulty fan m, respectively.

[0061] Then, based on a preset distance threshold r, the wind turbines are divided into different clusters. This can be achieved using clustering algorithms (such as K-means) or distance-based clustering methods (such as DBSCAN), and the expression is as follows:

[0062] In the formula, C k Indicates the m-th cluster;

[0063] Step S222: Calculate the cluster effect coefficient and isolation coefficient of the failed wind turbine, the expression of which is:

[0064] In the formula, ρ i A represents the average fan density of fan i; i The cluster area of ​​fan i is represented by r; r is a preset distance threshold used to define the fan with the faulty collar; d im This represents the straight-line distance from the faulty fan i to the faulty fan m.

[0065] In the formula, C i The maximum value represents the clustering effect coefficient of wind turbine i; m (ρ m This represents the maximum average wind turbine density among all wind turbines;

[0066] In the formula, I i Indicates the isolated flag for fan i; τ indicates a pre-set isolated prefabrication, if ρ iIf the wind turbine is less than τ, it is considered an isolated wind turbine. By grouping wind turbines in similar locations into the same cluster, the impact of location factors on spare parts demand can be considered more effectively. Wind turbines in similar locations may share some spare parts, which is beneficial for centralized storage and scheduling of spare parts. Considering isolated wind turbines: For isolated wind turbines, it is possible to replenish spare parts in advance, because these wind turbines may have difficulty obtaining spare parts support quickly. It is possible to set up temporary spare parts storage points for isolated wind turbines to reduce the transportation distance and time from the spare parts warehouse to the isolated wind turbines.

[0067] Step S223: Predict the spare parts demand over a future period based on the cluster effect coefficient and the isolation coefficient. The expression for this is:

[0068] In the formula, N(t) represents the spare parts demand at time t; P f (t) represents the probability of the wind turbine failing at time t; C i Indicates the clustering effect coefficient of wind turbines; I i Indicates the isolation coefficient of the wind turbine; η i The spare parts consumption coefficient of a wind turbine reflects the number of spare parts consumed when the turbine fails; N represents the total number of wind turbines in the wind farm. Specifically, when constructing the spare parts demand forecasting model, a cluster effect coefficient and an isolated turbine indicator are introduced to reflect the different characteristics of turbines within a cluster and isolated turbines. For example, for turbines within a cluster, spare parts reserves can be appropriately increased because they face similar operating environments and higher failure probabilities. For isolated turbines, spare parts can be replenished in advance because these turbines may have difficulty obtaining spare parts support quickly. By grouping turbines with similar locations into the same cluster, the impact of location factors on spare parts demand can be considered more effectively. Turbines with similar locations may share some spare parts, which is beneficial for centralized storage and scheduling of spare parts. At the same time, when constructing the spare parts transportation time model and cost model, turbines within a cluster can be given priority because turbines within a cluster are usually geographically close and can share a spare parts transportation route, thereby reducing transportation time and costs. It should be noted that isolated wind turbines may require separate spare parts transportation routes due to their remote geographical location. Therefore, the special characteristics of these wind turbines need to be considered when building the model. Temporary spare parts storage points can be set up for isolated wind turbines to reduce the transportation distance and time from the spare parts warehouse to the isolated wind turbines.

[0069] Step S230: Calculate the initial cost of the faulty fan based on the spare parts requirement;

[0070] Step S230 specifically includes:

[0071] Step S231: Based on the initial cost of spare parts demand, use Monte Carlo simulation to simulate the uncertainty of spare parts demand and obtain the probability distribution of spare parts demand, which is expressed as: N(t)~D(gP)f (t),C i ,I i ,η i ;θ′)

[0072] In the formula, N(t) is the probability distribution of spare parts demand at time t; D(.) represents the probability distribution function obtained through Monte Carlo simulation; θ′ represents the second model parameter;

[0073] Step S232: Using Monte Carlo simulation, and considering the wind turbine's operating years and warranty period, optimize the initial cost based on spare parts costs within and outside the warranty period. The expression is as follows:

[0074] In the formula, C total Represents the initial cost; E[N(t)] represents the expected value of the spare parts demand at time t; C piece Indicates the cost of a single spare part; 1 wi (t) represents the warranty option weighting coefficient; if wind turbine i is still within the warranty period within time t, then it is w. in Otherwise, it is w out ; It can be defined as:

[0075] In the formula, T warranty This indicates the end date of the wind turbine's warranty period.

[0076] In summary, this method predicts spare parts demand over a future period based on cluster effect coefficients and isolated turbine indicators. Then, based on the initial cost of spare parts demand, Monte Carlo simulation is used to simulate the uncertainty of spare parts demand, obtaining the probability distribution of spare parts demand. Finally, Monte Carlo simulation combined with the turbine's operating years and warranty period is used to optimize the initial cost based on spare parts costs within and outside the warranty period. This method quantifies the impact of turbine location and warranty period on spare parts demand prediction results, improves the accuracy of spare parts management and cost control, and helps wind farm managers better understand the uncertainty of spare parts demand, formulate more scientific and reasonable spare parts reserve strategies, thereby reducing operating costs and improving operation and maintenance efficiency.

[0077] Step S300: Construct a spare parts scheduling model and output a spare parts scheduling plan;

[0078] Step S300 specifically includes:

[0079] Step S310: Obtain the fluctuation distribution of spare parts supply, which is obtained based on historical data and information provided by suppliers. Its expression is: S(t)~D supply

[0080] In the formula, S(t) represents the spare parts supply quantity at time t, and D supply This indicates the fluctuation distribution of spare parts supply;

[0081] Step S320: Define the spare parts quantity decision variable, representing Q(t), which is the quantity of spare parts to be purchased at time t;

[0082] Step S330: To minimize spare parts replacement costs, construct a spare parts scheduling model. Input the spare parts demand forecast results considering the influence of wind turbine location and warranty period, and solve for the optimal spare parts scheduling scheme. Its expression is:

[0083] c re (t) represents the cost of replacing spare parts at time t;

[0084] The minimum spare parts inventory level constraint is defined as the spare parts inventory level never falling below a preset minimum spare parts inventory level at any time. Its expression is:

[0085] In the formula, t′ represents any point in time before time t; N(t′) represents the spare parts demand calculated in step S200; L represents the minimum spare parts inventory level; and the formula compares the cumulative number of spare parts purchased from the start time to the current time t. Subtract the total spare parts demand during this period This ensures that there is always sufficient spare parts inventory to deal with wind turbine failures.

[0086] The wind turbine downtime limit constraint is defined as any wind turbine downtime not being less than the preset maximum wind turbine downtime, and its expression is:

[0087] In the formula, T down Indicates the fan shutdown time; D max This represents the maximum wind turbine downtime; it is calculated by accumulating the wind turbine downtime T from the start time to the current time t. down (t′) and combine it with the maximum allowable downtime D. max This is achieved through comparison, which helps ensure that the normal operation of wind farms is not affected by prolonged shutdowns;

[0088] The spare parts inventory level constraint is defined as the spare parts inventory level at any given time being able to cover the spare parts demand adjusted by the cluster effect coefficient and the isolated fan flag. Its expression is:

[0089] In the formula, P f (t) represents the probability of the wind turbine failing at time t; C i Indicates the clustering effect coefficient of wind turbines; I i Indicates the isolation coefficient of the wind turbine; η iThe spare parts consumption coefficient represents the number of spare parts consumed when the turbine fails; N represents the total number of turbines in the wind farm; the number of spare parts purchased is compared from the start time to the current time t. Compared with the adjusted total spare parts demand This approach ensures that the different characteristics of wind turbines within a cluster and isolated wind turbines are taken into account, so as to better meet actual needs.

[0090] The warranty period constraint is defined as the ability of spare parts inventory levels at any given time to cover spare parts demand adjusted by the warranty option weighting factor. Its expression is:

[0091] In the formula, This represents the warranty option weighting factor; it is calculated by comparing the cumulative number of spare parts procured during the period from the start time to the current time t. Compared with the adjusted total spare parts demand To achieve this, the system ensures that the cost of wind turbine maintenance is low during the warranty period, thereby reducing spare parts costs. Then, linear programming or mixed-integer programming methods are used to solve for the optimal spare parts scheduling scheme. In the model, the spare parts demand N(t) is used as input, and constraints ensure that the spare parts inventory level meets the spare parts demand for a future period. The clustering effect coefficient C is then used to determine the optimal spare parts scheduling scheme. i We can understand that the spare parts demand for wind turbines within a cluster may be higher because they face similar operating environments and a higher probability of failure. Therefore, in the model, we can reflect this effect by adjusting the spare parts demand. On the other hand, isolated wind turbines, due to their geographical distance, may require more spare parts reserves to cope with potential delays. In the model, we can also reflect this effect by adjusting the spare parts demand. Since the maintenance cost of wind turbines within the warranty period is lower than that outside the warranty period, we use a warranty option weighting coefficient in the model. This approach adjusts spare parts demand to minimize spare parts costs during the warranty period. By constructing a spare parts scheduling model, this embodiment can more effectively manage and schedule spare parts, reduce unnecessary inventory costs, and ensure sufficient spare parts to cope with wind turbine failures. By considering the impact of spare parts demand, cluster effect coefficient, isolated wind turbine status, and warranty period, spare parts demand can be predicted more accurately, and spare parts costs can be optimized.

[0092] Step S400: Construct an operation and maintenance personnel scheduling model based on the spare parts scheduling plan, and output the operation and maintenance personnel scheduling results;

[0093] Step S400 specifically includes: defining decision variables for operations and maintenance personnel;

[0094] Step S410: Input the preset operation and maintenance policy;

[0095] Step S420: To minimize the cost of maintenance personnel, construct a maintenance personnel scheduling model and solve for the optimal scheduling plan. The maintenance personnel scheduling model includes: hour constraints, defined as the total number of working hours of maintenance personnel at any time not exceeding the preset maximum allowed working hours; first number constraints, defined as the number of maintenance personnel at any time being at least the minimum number of personnel required to complete the spare parts replacement task; second number constraints, defined as the number of maintenance personnel at any time meeting the spare parts demand adjusted by the cluster effect coefficient and the isolated wind turbine flag; third number constraints, defined as the number of maintenance personnel at any time meeting the spare parts demand adjusted by the warranty option weighting coefficient. Specifically, the constraints of the maintenance personnel scheduling model are similar to those of the spare parts scheduling model, so they will not be repeated here. In step S400, considering the spare parts demand N(t), we can calculate the number of spare parts replacement tasks that need to be completed at each time point, which will directly determine the number of maintenance personnel that need to be arranged at a specific time point. Through the cluster effect coefficient C... i We can understand that the demand for maintenance personnel for wind turbines within a cluster may be higher because they face similar operating environments and a higher probability of failure. Therefore, in this model, we can reflect this effect through the number of maintenance personnel. By considering isolated wind turbines, which may require more maintenance personnel due to their geographical distance to ensure rapid response, we can also reflect this effect in the model by adjusting the number of maintenance personnel. The maintenance cost of wind turbines within the warranty period is lower, while the maintenance cost of wind turbines outside the warranty period is higher. Therefore, in this model, we adjust the number of maintenance personnel through a warranty option weighting coefficient to ensure that maintenance personnel costs are minimized within the warranty period. Maintenance personnel scheduling: By constructing a maintenance personnel scheduling model, we can reasonably arrange the working hours of maintenance personnel, improve work efficiency, and ensure the timeliness and effectiveness of wind turbine maintenance work.

[0096] In summary, this wind farm operation and maintenance planning method aims to improve the efficiency and cost-effectiveness of wind farm operation and maintenance. Through a series of steps, it achieves refined management of the wind farm. Based on predicting turbine failures, it comprehensively considers factors such as cluster effect coefficients, isolated turbine characteristics, and warranty periods to construct a spare parts demand prediction model. Optimizing spare parts demand prediction helps reduce spare parts storage costs and minimize maintenance delays caused by insufficient spare parts, thereby improving the availability and reliability of the wind farm. By constructing a spare parts scheduling model, it achieves efficient spare parts scheduling, ensuring timely availability and reducing turbine downtime. Improving spare parts scheduling efficiency can reduce turbine downtime, increase wind farm power generation, and thus increase economic benefits. By constructing an operation and maintenance personnel scheduling model, it can rationally arrange the working hours of operation and maintenance personnel, ensuring sufficient manpower to handle spare parts replacement and other operation and maintenance tasks at the right time. By integrating the above steps, a complete wind farm operation and maintenance (O&M) planning scheme can be formed, achieving comprehensive optimization of wind farm O&M strategies. This scheme organically combines fault prediction, spare parts demand prediction, spare parts scheduling, and O&M personnel scheduling to form a closed-loop O&M management system. Comprehensive optimization of wind farm O&M strategies helps improve the overall operational efficiency of wind farms, reduce O&M costs, and enhance their competitiveness. This wind farm O&M planning method, through a series of scientific and reasonable steps and technical means, optimizes wind farm O&M strategies. Specifically, it improves the accuracy of fault prediction, optimizes spare parts demand prediction, enhances spare parts scheduling efficiency, rationally arranges O&M personnel scheduling, and comprehensively optimizes wind farm O&M strategies. These technical effects not only help improve the O&M efficiency of wind farms but also significantly reduce costs, ultimately achieving a dual improvement in economic and social benefits.

[0097] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0098] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A wind farm operation and maintenance planning method, characterized in that, The method includes: Acquire historical operational data of the wind farm and perform preprocessing; Extract the location distribution of wind turbines within the wind farm, construct a fault prediction model, and output the spare parts demand prediction results; Construct a spare parts scheduling model and output a spare parts scheduling plan; A scheduling model for maintenance personnel is built based on the spare parts scheduling plan, and the scheduling results for maintenance personnel are output.

2. The wind farm operation and maintenance planning method as described in claim 1, characterized in that, Historical operating data for wind farms should include at least the following: wind turbine operating status data, historical fault data, spare parts consumption data, wind turbine location data, and wind turbine warranty period data.

3. The wind farm operation and maintenance planning method as described in claim 1, characterized in that, Extract the location distribution of wind turbines within the wind farm, construct a fault prediction model, and output the spare parts demand prediction results, including: Integrate wind farm turbine location data, warehouse location data, topographic data, and road network data; Based on historical operating data of wind farms, predict wind turbine failures within the wind farm and forecast the demand for spare parts in the future. Calculate the initial cost of the faulty fan based on the spare parts demand.

4. The wind farm operation and maintenance planning method as described in claim 3, characterized in that, Based on historical wind farm operation data, predictions of wind turbine failures within the wind farm, and forecasts of spare parts demand in the near future, also include: Obtain the location data of the faulty fans, calculate the straight-line distance between the faulty fans, and divide the faulty fans into clusters; Calculate the cluster effect coefficient and isolation coefficient of the faulty fan; Predict the demand for spare parts in the near future based on the cluster effect coefficient and the isolation coefficient.

5. The wind farm operation and maintenance planning method as described in claim 4, characterized in that, The initial cost of a faulty fan, calculated based on spare parts demand, includes: Based on the initial cost of spare parts demand, Monte Carlo simulation is used to simulate the uncertainty of spare parts demand and obtain the probability distribution of spare parts demand. Using Monte Carlo simulation, combined with the wind turbine's operating years and warranty period, the initial cost is optimized based on the spare parts costs inside and outside the warranty period.

6. The wind farm operation and maintenance planning method as described in claim 5, characterized in that, Based on historical wind farm operation data, predictions of wind turbine failures within the wind farm, and forecasts of spare parts demand in the near future, also include: A clustering algorithm is used to divide the wind turbines into different clusters based on a preset distance. Calculate the cluster effect coefficient and isolation coefficient based on the average fan density within the cluster; Isolation fans are identified based on the isolation coefficient, and temporary spare parts storage points are set up for the isolation fans.

7. A wind farm operation and maintenance planning method as described in any one of claims 1 to 6, characterized in that, Construct a spare parts scheduling model and output a spare parts scheduling plan, including: Obtain the fluctuation distribution of spare parts supply; Define the quantity of decision variables; To minimize spare parts replacement costs, a spare parts scheduling model is constructed. The model takes into account the spare parts demand forecast results under the influence of wind turbine location and warranty period, and solves for the optimal spare parts scheduling scheme.

8. A wind farm operation and maintenance planning method as described in claim 7, characterized in that, The spare parts scheduling model includes: The minimum spare parts inventory level constraint is defined as the spare parts inventory level not being lower than the preset minimum spare parts inventory level at any time. The wind turbine downtime limit constraint is defined as any wind turbine downtime not being less than the preset maximum wind turbine downtime; Spare parts inventory level constraint is defined as the spare parts inventory level at any time being able to cover spare parts demand adjusted by cluster effect coefficient and isolation coefficient; Warranty period constraint is defined as the ability of spare parts inventory levels at any given time to cover spare parts demand adjusted by the warranty option weighting factor.

9. A wind farm operation and maintenance planning method as described in claim 8, characterized in that, Based on the spare parts scheduling plan, an operations and maintenance personnel scheduling model is constructed, and the output of the operations and maintenance personnel scheduling results includes: Define decision variables for operations and maintenance personnel; Enter the preset operation and maintenance policy; With the goal of minimizing the cost of operations and maintenance personnel, a scheduling model for operations and maintenance personnel is constructed, and the optimal scheduling plan is solved.

10. A wind farm operation and maintenance planning method as described in claim 9, characterized in that, The operation and maintenance personnel scheduling model includes: The hour constraint is defined as the total number of working hours of maintenance personnel at any given time not exceeding the preset maximum allowed working hours. The first headcount constraint is defined as the minimum number of maintenance personnel required to complete the spare parts replacement task at any given time. The second head constraint is defined as the number of maintenance personnel at any given time meeting the spare parts requirements adjusted by the cluster effect coefficient and the isolated turbine flag. The third constraint on the number of personnel is defined as ensuring that the number of maintenance personnel at any given time meets the spare parts requirements adjusted by the warranty option weighting factor.

Images