Method, device and storage medium for determining de-icing capacity of wind turbine

Abstract

The embodiment of the application relates to the technical field of safe operation of a power system and new energy dispatching, and provides a method and device for determining icing deactivation capacity of a wind turbine and a storage medium. The method comprises the following steps: obtaining predicted meteorological information of a to-be-predicted wind turbine in a prediction time period; determining wind turbine parameters, a capture coefficient and a freezing coefficient of the to-be-predicted wind turbine according to the predicted meteorological information, and determining an icing index of the to-be-predicted wind turbine, wherein the capture coefficient represents a proportion of water droplets captured by blades of the to-be-predicted wind turbine, and is positively correlated with the relative speed of the water droplets, and the freezing coefficient represents a freezing proportion of the captured water droplets; determining a shutdown probability of the to-be-predicted wind turbine in the prediction time period according to the icing index; determining a wind power icing deactivation probability of the to-be-predicted wind turbine in the prediction time period according to the shutdown probability and an operation probability of an operation of each wind farm operation and maintenance personnel on the to-be-predicted wind turbine; and determining the icing deactivation capacity of the to-be-predicted wind turbine in the prediction time period according to the shutdown probability and the wind power icing deactivation probability.

Description

Technical Field

[0001] This application relates to the fields of power system safe operation and new energy dispatch technology, specifically to a method, apparatus and storage medium for determining the reserve capacity of wind turbines icing. Background Technology

[0002] During cold waves, wind farms in high-altitude mountainous areas are highly susceptible to icing and shutdown due to high humidity and low temperatures, resulting in losses of wind power reserve capacity. This not only severely restricts wind power generation capacity but also significantly increases the uncertainty of wind power forecasting. Given the current rapid development of new energy sources, this is insufficient to meet the requirements for safe and stable operation and refined dispatching of the power system. Therefore, conducting research on predicting the limited icing capacity of wind farms under icing weather conditions is of great significance for ensuring reliable power supply and the safe and stable operation of the power system.

[0003] Existing icing prediction methods mainly rely on laboratory icing test data, but these methods have the following three major drawbacks:

[0004] (1) Insufficient timeliness: unable to respond in real time to dynamic changes in meteorological conditions;

[0005] (2) Poor scene adaptability: It is difficult to cover the different icing characteristics of different terrains and wind turbine models;

[0006] (3) Inaccurate outage prediction: It can only determine the icing status, but cannot accurately predict the outage time window and backup capacity, and fails to consider the maintenance personnel's ability to shut down the system in advance based on the development of icing.

[0007] Therefore, there is an urgent need for an intelligent forecasting method that combines real-time meteorological data with operation and maintenance experience to improve the ability to manage and control the risk of icing in wind farms. Summary of the Invention

[0008] The purpose of this application is to provide a method, apparatus, and storage medium for determining the icing back-off capacity of a wind turbine.

[0009] To achieve the above objectives, a first aspect of this application provides a method for determining the wind turbine icing backup capacity, comprising:

[0010] Obtain forecast meteorological information for the wind turbine to be predicted within the forecast period;

[0011] Based on the predicted meteorological information, the wind turbine parameters, capture coefficient, and freezing coefficient of the wind turbine to be predicted are determined. The capture coefficient represents the proportion of water droplets captured by the blades of the wind turbine to be predicted, and is positively correlated with the relative velocity of the water droplets. The freezing coefficient represents the freezing proportion of the captured water droplets, and is related to the air temperature and wind speed.

[0012] The icing index of the wind turbine to be predicted is determined based on the preset collision coefficient, the capture coefficient, the freezing coefficient, and the wind turbine parameters.

[0013] The probability of the wind turbine to be predicted being shut down during the predicted time period is determined based on the icing index.

[0014] The probability of wind turbine icing and de-emergence during the prediction period is determined based on the downtime probability and the operation probability of each wind farm maintenance personnel performing downtime operation on the wind turbine to be predicted.

[0015] The icing reserve capacity of the wind turbine to be predicted during the prediction period is determined based on the downtime probability and the wind power icing reserve decommissioning probability.

[0016] In this embodiment of the application, determining the wind turbine parameters, capture coefficient, and freezing coefficient of the wind turbine to be predicted based on the predicted meteorological information includes: inputting the predicted meteorological information into the wind turbine icing prediction model to output the predicted air temperature at the hub height of the wind turbine to be predicted based on the wind turbine icing prediction model; when the predicted air temperature is within a preset air temperature range and the relative humidity of the environment where the wind turbine to be predicted is located is greater than a preset humidity threshold, determining the wind turbine parameters of the wind turbine to be predicted based on the predicted meteorological information, the wind turbine parameters including air temperature, wind speed, liquid water content, relative velocity of water droplets, and effective cross-sectional area of ​​water droplets colliding with the wind turbine.

[0017] In this embodiment, the relative velocity U of the water droplet is calculated according to formula (1):

[0018] (1)

[0019] in, This refers to wind speed. , Let R be the blade angular velocity of the wind turbine to be predicted, and R be the blade radius of the wind turbine to be predicted. The angle between the wind direction and the plane of blade rotation.

[0020] In this embodiment of the application, determining the capture coefficient of the wind turbine to be predicted based on the relative velocity of water droplets includes determining the capture coefficient according to formula (2). :

[0021] (2)

[0022] Where k is an empirical coefficient, ranging from 0.1 to 0.3, and U is the relative velocity of the water droplet.

[0023] In this embodiment of the application, determining the freezing coefficient of the wind turbine to be predicted based on the air temperature, wind speed, and liquid water content of the wind turbine to be predicted includes determining the freezing coefficient according to formula (3). :

[0024] (3)

[0025] Where T refers to the predicted air temperature at the height of the wind turbine hub.

[0026] In this embodiment of the application, determining the icing index of the wind turbine to be predicted based on the preset collision coefficient, capture coefficient, freezing coefficient, and wind turbine parameters includes determining the icing index I according to formula (4):

[0027] (4)

[0028] in, To preset the collision coefficient, The capture coefficient, The freezing coefficient is... U represents the liquid water content, U represents the relative velocity of the water droplets, and A represents the effective cross-sectional area of ​​the water droplets colliding with the fan. Indicates the time interval The cumulative amount of ice accumulation within.

[0029] In this embodiment of the application, determining the icing decommissioning capacity of the wind turbine to be predicted within the predicted time period based on the icing index includes: determining the outage probability of the wind turbine to be predicted within the predicted time period based on the icing index; determining the wind power icing decommissioning probability of the wind turbine to be predicted within the predicted time period based on the outage probability and the operation probability of each wind farm maintenance personnel performing an outage operation on the wind turbine to be predicted; and determining the icing decommissioning capacity of the wind turbine to be predicted within the predicted time period based on the outage probability and the wind power icing decommissioning probability.

[0030] In this embodiment of the application, determining the icing reserve capacity of the wind turbine to be predicted within the prediction period based on the outage probability and the wind power icing reserve decommissioning probability includes: when the outage probability is greater than the wind power icing reserve decommissioning probability, determining the icing reserve capacity as the power generation capacity of the wind turbine to be predicted; when the outage probability is less than or equal to the wind power icing reserve decommissioning probability, determining the icing reserve capacity as zero.

[0031] In this embodiment of the application, the method further includes: after determining the wind power icing de-emergence probability of the wind turbine to be predicted within the prediction period based on the shutdown probability and the operation probability of each wind farm operation and maintenance personnel to perform shutdown operation on the wind turbine to be predicted, the wind power icing de-emergence probability is corrected based on the wind power icing de-emergence probability, the probability of manually initiating shutdown operation under the current icing index, and the probability of manually initiating shutdown operation under the icing shutdown threshold.

[0032] A second aspect of this application provides an apparatus for determining the icing back-off capacity of a wind turbine, comprising:

[0033] The memory is configured to store instructions;

[0034] The processor is configured to retrieve instructions from memory and, when executing the instructions, to implement a method for determining the wind turbine icing back-off capacity according to any of the foregoing.

[0035] This method integrates historical icing records of wind turbines, real-time meteorological monitoring data, and numerical weather prediction results to form a multi-dimensional feature dataset. It uses an icing index model to predict icing risk and combines it with an operational status model to predict downtime. Finally, it quantifies the reserve capacity. Compared with existing technologies, this method significantly improves the efficiency and accuracy of obtaining the capacity of wind turbines that are out of service due to icing, and can provide a more reliable basis for the scheduling and operation of the power system.

[0036] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0037] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings:

[0038] Figure 1 The illustration shows a flowchart of a method for determining the icing backup capacity of a wind turbine according to an embodiment of this application;

[0039] Figure 2 The schematic diagram illustrates a process flow diagram of a method for determining wind turbine icing backup capacity according to another embodiment of this application;

[0040] Figure 3 This illustration schematically shows the increase in the probability of manual shutdown according to an embodiment of this application;

[0041] Figure 4 The diagram illustrates the internal structure of a computer device according to an embodiment of this application. Detailed Implementation

[0042] 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. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0043] Figure 1The schematic diagram illustrates a process flow for determining wind turbine icing backup capacity according to an embodiment of this application, wherein the method can be applied to a processor or controller. Figure 1 As shown, a method for determining the icing protection capacity of a wind turbine includes the following steps:

[0044] Step 102: Obtain the predicted meteorological information of the wind turbine to be predicted within the prediction period;

[0045] Step 104: Determine the wind turbine parameters, capture coefficient, and freezing coefficient of the wind turbine to be predicted based on the predicted meteorological information. The capture coefficient represents the proportion of water droplets captured by the blades of the wind turbine to be predicted, which is positively correlated with the relative velocity of the water droplets. The freezing coefficient represents the freezing proportion of the captured water droplets, which is related to the air temperature and wind speed.

[0046] Step 106: Determine the icing index of the wind turbine to be predicted based on the preset collision coefficient, capture coefficient, freezing coefficient and wind turbine parameters;

[0047] Step 108: Determine the probability of the wind turbine to be shut down during the forecast period based on the icing index;

[0048] Step 110: Determine the wind power icing and de-emergence probability of the wind turbine to be predicted during the prediction period based on the downtime probability and the operation probability of each wind farm operation and maintenance personnel performing downtime operation on the wind turbine to be predicted.

[0049] Step 112: Determine the icing reduction reserve capacity of the wind turbine to be predicted within the predicted time period based on the downtime probability and the wind power icing reduction reserve probability.

[0050] The wind turbine to be predicted refers to the specific wind turbine generator unit for which icing prediction needs to be performed. Each wind turbine has its unique physical characteristics (such as blade size, height, and materials), which affect icing behavior. In a wind farm, wind turbines may face different icing risks due to different locations (such as high altitude or proximity to water sources). This solution will perform personalized analysis for each individual "to be predicted" wind turbine. First, in this embodiment, the processor will acquire the predicted meteorological information of the wind turbine to be predicted within the prediction time period. Here, the prediction time period refers to a period of time in the future, such as the next 12 hours. The predicted meteorological information is usually input in time series form. The predicted meteorological information of the wind turbine to be predicted within the prediction time period can be obtained through numerical weather prediction (NWP) models or meteorological station data. Furthermore, meteorological information is dynamic and requires high precision to ensure accurate prediction. For example, when using numerical weather prediction (NWP) models, the terrain influence of the wind turbine location needs to be considered. If meteorological data is missing, the solution can use interpolation to supplement the missing meteorological data or use data from nearby stations. In icing forecasting, the predicted meteorological information includes air temperature, wind speed, and liquid water content (LWC, which represents the amount of water droplets in the air that can be used for icing).

[0051] In one embodiment, the method further includes: inputting predicted meteorological information into a wind turbine icing prediction model to output the predicted temperature at the hub height of the wind turbine to be predicted based on the wind turbine icing prediction model; and determining the wind turbine parameters of the wind turbine to be predicted based on the predicted meteorological information when the predicted temperature is within a preset temperature range and the relative humidity of the environment where the wind turbine to be predicted is located is greater than a preset humidity threshold.

[0052] This embodiment defines the icing triggering conditions. The expression is as follows:

[0053] Icing trigger condition =

[0054] Where T is the predicted air temperature at the wheel hub height, and RH is the relative humidity.

[0055] As can be seen, in the above specific embodiments, the preset temperature range is set to [-10]. ,2 The preset humidity threshold is set to 85%. When the icing trigger condition is equal to 1, it means that the next step can be carried out, which is to determine the wind turbine parameters based on the predicted meteorological information. If the icing trigger condition is equal to 0, the next step is not carried out.

[0056] Furthermore, the processor can transform the predicted meteorological information into wind turbine parameters for the wind turbine to be predicted. These parameters include air temperature, wind speed, liquid water content, relative velocity of water droplets, and the effective cross-sectional area of ​​water droplet collisions with the wind turbine. Specifically, air temperature and wind speed can be directly extracted from the meteorological information. Air temperature can be used to assess freezing conditions, and wind speed can be used to calculate collision energy. Liquid water content (LWC) can be derived from the predicted meteorological information. LWC is related to relative humidity and cloud parameters and can be estimated using formulas. For example, RH is relative humidity. is the air density, and 'a' is an empirical coefficient. And... The higher the wind speed, the greater the risk of icing. The relative velocity of water droplets can be calculated based on wind speed. Since water droplets move with the air, their relative velocity is approximately equal to the wind speed, but the size of the water droplets and the movement of the blades must be taken into account. Therefore, in a specific embodiment, the relative velocity U of the water droplets is calculated according to formula (1):

[0057] (1)

[0058] in, This refers to wind speed. , Let R be the blade angular velocity of the wind turbine to be predicted, and R be the blade radius of the wind turbine to be predicted. The angle between the wind direction and the plane of blade rotation.

[0059] The effective cross-sectional area of ​​the water droplet impact on the fan can be calculated based on the fan design parameters and wind speed. This area A is the effective "target" area of ​​the blades in the wind. Specifically, it can be calculated using the following formula: ,in denoted by the radius of curvature of the leading edge of the blade, in meters, and D, the diameter of the water droplet.

[0060] Furthermore, after determining the fan parameters of the fan to be predicted, the processor can determine the capture coefficient of the fan based on the relative velocity of the water droplets. The capture coefficient represents the proportion of water droplets captured by the fan blades and is positively correlated with the relative velocity of the water droplets. This is because the higher the relative velocity, the greater the inertia of the water droplets, making them more likely to collide with the blades, thus resulting in a higher capture coefficient. Simultaneously, the processor can also determine the freezing coefficient of the fan based on the air temperature, wind speed, and liquid water content. The freezing coefficient represents the proportion of captured water droplets that freeze and is related to air temperature and wind speed.

[0061] In one specific embodiment, determining the capture coefficient of the wind turbine to be predicted based on the relative velocity of water droplets includes determining the capture coefficient according to formula (2). :

[0062] (2)

[0063] Where k is an empirical coefficient, and its value ranges from [value range missing]. U is the relative velocity of the water droplet.

[0064] In a specific embodiment, determining the freezing coefficient of the wind turbine to be predicted based on the air temperature, wind speed, and liquid water content of the wind turbine includes determining the freezing coefficient according to formula (3). :

[0065] (3)

[0066] Where T refers to the predicted air temperature at the height of the wind turbine hub. Freezing is more complete at lower temperatures, so the freezing coefficient approaches 1. Increased wind speed accelerates heat dissipation, and the correction factor can be multiplied by [missing value]. .

[0067] Then, the processor can determine the icing index of the wind turbine to be predicted based on the preset collision coefficient, capture coefficient, freezing coefficient, and turbine parameters. The icing index represents the icing rate or risk. Specifically, in one embodiment, determining the icing index of the wind turbine to be predicted based on the preset collision coefficient, capture coefficient, freezing coefficient, and turbine parameters includes determining the icing index I according to formula (4):

[0068] (4)

[0069] in, To preset the collision coefficient, The capture coefficient, The freezing coefficient is... U represents the liquid water content, U represents the relative velocity of the water droplets, and A represents the effective cross-sectional area of ​​the water droplets colliding with the fan. Indicates the time interval The cumulative amount of ice accumulation within.

[0070] Among them, the preset collision coefficient These are fixed coefficients based on the blade shape, such as 0.8 for the straight section and 1.2 for the leading edge. It can be represented as:

[0071] .

[0072] After calculating the icing index of the wind turbine to be predicted, the processor can determine the icing reserve capacity of the wind turbine during the prediction period based on the icing index. Icing reserve capacity represents the reduced power generation capacity of the wind turbine to be predicted due to icing.

[0073] This method integrates historical icing records of wind turbines, real-time meteorological monitoring data, and numerical weather prediction results to form a multi-dimensional feature dataset. It uses an icing index model to predict icing risk and combines it with an operational status model to predict downtime. Finally, it quantifies the reserve capacity. Compared with existing technologies, this method significantly improves the efficiency and accuracy of obtaining the capacity of wind turbines that are out of service due to icing, and can provide a more reliable basis for the scheduling and operation of the power system.

[0074] In one embodiment, determining the icing decommissioning capacity of the wind turbine to be predicted within the predicted time period based on the icing index includes: determining the outage probability of the wind turbine to be predicted within the predicted time period based on the icing index; determining the wind power icing decommissioning probability of the wind turbine to be predicted within the predicted time period based on the outage probability and the operation probability of each wind farm maintenance personnel performing an outage operation on the wind turbine to be predicted; and determining the icing decommissioning capacity of the wind turbine to be predicted within the predicted time period based on the outage probability and the wind power icing decommissioning probability.

[0075] The downtime probability refers to the likelihood that a wind turbine will be forced to shut down due to severe icing within the predicted time period. A higher icing index results in greater blade load, poorer aerodynamic performance, and a higher probability of forced shutdown. Specifically, the processor can determine the downtime probability of the wind turbine within the predicted time period based on the icing index, including determining the downtime probability FF according to formula (5):

[0076] (5)

[0077] Where k is the slope parameter, a larger value of k indicates a faster increase in icing rate, and I is the icing index of the wind turbine to be predicted. The base threshold.

[0078] Then, the processor can determine the probability of wind turbines being de-energized due to icing within the predicted time period based on the downtime probability and the operational probability of each wind farm maintenance worker performing a downtime operation on the predicted turbine. The operational probability refers to the conditional probability (range 0-1) of maintenance workers actively performing a downtime operation, i.e., the likelihood of personnel actually taking action given the known downtime probability. The wind turbine de-energization probability is the total probability (range 0-1) of the turbine ultimately being de-energized within the predicted time period. This probability combines the effects of passive equipment downtime and active personnel operation, allowing for a direct calculation of the actual probability of the turbine being de-energized. For example, if... If maintenance personnel might overlook this, then... ;like In this case, the operations and maintenance department will initiate an emergency response. The probability of wind power icing and subsequent backup is... This is the total probability of a shutdown event occurring. .

[0079] Furthermore, the processor can determine the icing reserve capacity of the wind turbine to be predicted within the prediction period based on the outage probability and the wind power icing reserve de-probability. In a specific embodiment, determining the icing reserve capacity of the wind turbine to be predicted within the prediction period based on the outage probability and the wind power icing reserve de-probability includes: when the outage probability is greater than the wind power icing reserve de-probability, determining the icing reserve capacity as the generating capacity of the wind turbine to be predicted; when the outage probability is less than or equal to the wind power icing reserve de-probability, determining the icing reserve capacity as zero. That is, the calculation expression for the icing reserve capacity of a single wind turbine to be predicted is as follows:

[0080]

[0081] in, Let be the capacity of the i-th wind turbine. The wind farm's icing shutdown reserve capacity C is the sum of the individual icing shutdown shutdown reserve capacities of multiple turbines.

[0082]

[0083] Furthermore, such as Figure 2 As shown, in one embodiment, the method further includes: after determining the wind power icing de-emergence probability of the wind turbine to be predicted within the prediction period based on the shutdown probability and the operation probability of each wind farm operation and maintenance personnel to perform shutdown operation on the wind turbine to be predicted, the wind power icing de-emergence probability is corrected based on the wind power icing de-emergence probability, the probability of manually initiating shutdown operation under the current icing index, and the probability of manually initiating shutdown operation under the icing shutdown threshold.

[0084] In other words, accurate prediction data can be collected and combined with wind farm feedback information to form a wind power icing shutdown database, including calculated icing indices and manual shutdown logs. Furthermore, the wind power icing shutdown probability threshold can be adjusted, using the following formula:

[0085]

[0086] In the formula, t is the icing shutdown threshold, and H is the number of manual correction events. This means that the manually adjusted wind power icing de-estimation probability threshold is considered. P(t|H) is iteratively optimized using historical data, and then the manually adjusted wind power icing de-estimation probability threshold can be used. Replace the previously calculated Pt, thereby continuously improving prediction accuracy based on the obtained data. For example... Figure 3 As shown, it can be seen that the probability of manual shutdown increases significantly with the increase of ice thickness.

[0087] This method achieves high-precision prediction of icing-induced shutdown capacity by constructing a three-layer technical system of "data-driven - model prediction - dynamic correction". Specifically, it achieves this through (1) multi-source data fusion: integrating historical icing records of wind turbines, real-time meteorological monitoring data and numerical weather forecast results to form a multi-dimensional feature dataset; (2) dual-model cascade prediction: predicting icing risk through the icing index model and predicting downtime by combining the operation status model, and finally quantifying the shutdown capacity; (3) Bayesian dynamic correction: iteratively optimizing the shutdown probability threshold based on operation and maintenance feedback and historical data to continuously improve prediction accuracy.

[0088] Figure 1 This is a flowchart illustrating a method for determining wind turbine icing backup capacity in one embodiment. It should be understood that, although... Figure 1 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise explicitly stated herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0089] In one embodiment, an apparatus for determining the icing back-off capacity of a wind turbine is provided, comprising:

[0090] The memory is configured to store instructions;

[0091] The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the method for determining wind turbine icing back-off capacity according to any of the preceding embodiments.

[0092] This application provides a storage medium storing a program that, when executed by a processor, implements the method described above for determining the wind turbine icing backup capacity.

[0093] This application provides a processor for running a program, wherein the program executes the above-described method for determining the wind turbine icing backup capacity.

[0094] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor A01, a network interface A02, memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computing and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database stores data related to wind turbine icing. The network interface A02 communicates with external terminals via a network connection. When executed by the processor A01, the computer program B02 implements a method for determining wind turbine icing backup capacity.

[0095] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0096] This application provides a computer (electronic) device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements the steps of any of the above methods for determining the wind turbine icing back-off capacity.

[0097] This application also provides a computer program product that, when executed on a data processing device, is adapted to perform a program that initializes a method step for determining the wind turbine icing back-off capacity.

[0098] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0099] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0100] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0101] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0102] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0103] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0104] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0105] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0106] The above are merely embodiments of this application and are not intended to limit the scope of 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 scope of the claims of this application.

Claims

1. A method for determining de-icing capacity of a wind turbine, characterized by, The method comprises: acquiring predicted meteorological information of a to-be-predicted wind turbine in a prediction time period; determining a wind turbine parameter, a capturing coefficient and a freezing coefficient of the to-be-predicted wind turbine according to the predicted meteorological information, wherein the capturing coefficient represents a proportion of water droplets captured by blades of the to-be-predicted wind turbine, and is positively correlated with a relative speed of water droplets, and the freezing coefficient represents a freezing proportion of the captured water droplets, and is correlated with air temperature and wind speed; determining an icing index of the to-be-predicted wind turbine according to a preset collision coefficient, the capturing coefficient, the freezing coefficient and the wind turbine parameter; determining a shutdown probability of the to-be-predicted wind turbine in the prediction time period according to the icing index; According to the shutdown probability, an operation probability of each wind farm maintenance personnel to perform a shutdown operation on the to-be-predicted wind turbine, a wind power icing retreat standby probability of the to-be-predicted wind turbine in the prediction time period is determined, wherein the operation probability refers to a conditional probability that the maintenance personnel actively performs a shutdown operation, and the wind power icing retreat standby probability refers to a total probability that the wind turbine finally exits operation in the prediction time period, ; determining an icing retreat preparation capacity of the to-be-predicted wind turbine in the prediction time period according to the shutdown probability and a wind power icing retreat preparation probability; wherein determining the icing retreat preparation capacity of the to-be-predicted wind turbine in the prediction time period according to the shutdown probability and the wind power icing retreat preparation probability comprises: determining the icing retreat preparation capacity as a power generation capacity of the to-be-predicted wind turbine in a case where the shutdown probability is greater than the wind power icing retreat preparation probability; and determining the icing retreat preparation capacity as zero in a case where the shutdown probability is less than or equal to the wind power icing retreat preparation probability; wherein determining the shutdown probability of the to-be-predicted wind turbine in the prediction time period according to the icing index comprises: determining the shutdown probability FF according to the following formula: Wherein, k is a slope parameter, the greater the value of k indicates the faster the icing speed grows, I is the icing index of the wind turbine to be predicted, is a basic threshold value.

2. The method for determining de-rate capacity of an iced wind turbine according to claim 1, wherein, The method further comprises: after determining the wind power icing retreat preparation probability of the to-be-predicted wind turbine in the prediction time period according to the shutdown probability and an operation probability of each wind farm operator performing a shutdown operation on the to-be-predicted wind turbine, correcting the wind power icing retreat preparation probability based on the wind power icing retreat preparation probability, a probability of manually starting a shutdown operation under a current icing index, and a probability of manually starting a shutdown operation under an icing shutdown threshold.

3. The method for determining de-rate capacity of an iced wind turbine of claim 1, wherein, determining the wind turbine parameter, the capturing coefficient and the freezing coefficient of the to-be-predicted wind turbine according to the predicted meteorological information comprises: inputting the predicted meteorological information into a wind turbine icing prediction model to output a predicted air temperature at a hub height of the to-be-predicted wind turbine according to the wind turbine icing prediction model; in a case where the predicted air temperature is within a preset air temperature range and a relative humidity of an environment where the to-be-predicted wind turbine is located is greater than a preset humidity threshold, determining a wind turbine parameter of the to-be-predicted wind turbine according to the predicted meteorological information, the wind turbine parameter comprising air temperature, wind speed, liquid water content, water droplet relative speed and water droplet collision wind turbine effective cross-sectional area.

4. The method for determining de-rate capacity of an iced wind turbine according to claim 3, wherein, The water droplet relative speed U is calculated according to formula (1): （1） wherein, is the wind speed, , is the blade angular velocity of the wind turbine to be predicted, R is the blade radius of the wind turbine to be predicted, is the angle between the wind direction and the blade rotation plane.

5. The method for determining de-rate capacity of an iced wind turbine of claim 3, wherein, determining the capture coefficient according to equation (2) : （2） wherein k is an empirical coefficient, and the value range is 0.1-0.3, and U is the water droplet relative speed.

6. The method for determining de-rate capacity of an iced wind turbine of claim 3, wherein, determining the freezing coefficient according to equation (3) : （3） wherein T refers to the predicted air temperature at the hub height of the to-be-predicted wind turbine.

7. The method for determining de-rate capacity of an iced wind turbine of claim 3, wherein, determining the icing index of the to-be-predicted wind turbine according to the preset collision coefficient, the capturing coefficient, the freezing coefficient and the wind turbine parameter comprises determining the icing index I according to formula (4): （4） wherein, is the preset collision coefficient, is the capture coefficient, is the freeze coefficient, is the liquid water content, U is the water droplet relative velocity, A is the water droplet collision fan effective cross-sectional area, represents the ice accumulation amount in the time interval .

8. An apparatus for determining de-icing capacity of a wind turbine, characterized in that, comprising: a memory configured to store instructions; a processor configured to call the instructions from the memory and implement the method for determining de-rating capacity of an iced wind turbine according to any one of claims 1 to 7 when executing the instructions.

9. A machine-readable storage medium having stored thereon instructions, the instructions being executable by a machine to cause the machine to perform operations comprising: The instructions, when executed by a processor, cause the processor to be configured to perform the method for determining de-rating capacity of an iced wind turbine according to any one of claims 1 to 7.

Images