Control method and device of wind turbine generator, electronic equipment and storage medium

Abstract

The application provides a wind turbine control method and device, electronic equipment and storage medium, wherein the method comprises: obtaining meteorological data of a wind farm area; performing weather prediction based on the meteorological data to obtain a first weather prediction result; in response to the first weather prediction result being abnormal weather, obtaining remote sensing image data and historical abnormal weather image data of the wind farm area; based on the remote sensing image data and the historical abnormal weather image data, obtaining a second weather prediction result; and in response to the second weather prediction result being abnormal weather, controlling wind turbines in the wind farm based on the meteorological data. The technical scheme of the embodiment of the application can avoid the impact of sudden severe weather on the safe operation of the wind farm.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of wind power generation, and in particular to a wind turbine control method and device, an electronic device, and a storage medium. BACKGROUND

[0002] Global climate warming has greatly increased the frequency of abnormal weather such as low temperature and strong wind, and wind power generation has a strong dependence on weather conditions. If appropriate control measures are not taken in time for wind turbines when abnormal weather occurs, the safe operation of the wind turbines may be affected. SUMMARY

[0003] The present application aims to at least partially solve one of the technical problems in the related art.

[0004] To this end, a first object of the present application is to provide a wind turbine control method, comprising: obtaining meteorological data of a wind farm area; performing weather prediction based on the meteorological data to obtain a first weather prediction result; in response to the first weather prediction result being abnormal weather, obtaining remote sensing image data and historical abnormal weather image data of the wind farm area; based on the remote sensing image data and the historical abnormal weather image data, obtaining a second weather prediction result; and in response to the second weather prediction result being abnormal weather, controlling wind turbines in the wind farm based on the meteorological data.

[0005] In an implementation manner, the weather prediction based on the meteorological data to determine whether abnormal weather is likely to occur comprises: inputting the meteorological data into a pre-trained weather prediction model to obtain the first weather prediction result; and wherein the weather prediction model has previously learned the corresponding relationship between meteorological data and weather types.

[0006] In an optional implementation manner, the weather prediction model is obtained by pre-training through the following steps: obtaining historical abnormal meteorological data corresponding to an abnormal weather type; taking the abnormal weather type as a data label of the historical abnormal meteorological data corresponding to the abnormal weather type; training an initial model based on the historical abnormal meteorological data and the data label to obtain the weather prediction model; and wherein the initial model is a long short-term memory model.

[0007] In an implementation manner, the obtaining the second weather prediction result based on the remote sensing image data and the historical severe weather image data comprises: performing data unification processing on the remote sensing image data to obtain weather image data; inputting the weather image data and the historical severe weather image data into a pre-trained image similarity analysis model to obtain an image similarity of the weather image data and the historical severe weather image data; wherein the image similarity analysis model has learned the ability to obtain the similarity between two images in advance; and in response to the image similarity being greater than or equal to a preset similarity threshold, determining that the second weather prediction result is abnormal weather.

[0008] In an optional implementation manner, the historical severe weather image data is multiple, and the inputting the weather image data and the historical severe weather image data into the pre-trained image similarity analysis model to obtain the image similarity of the weather image data and the historical severe weather image data comprises: inputting each of the historical severe weather image data and the weather image data into the image similarity analysis model respectively to obtain a candidate image similarity corresponding to each of the historical severe weather image data; and obtaining a maximum one of the multiple candidate image similarities as the image similarity.

[0009] In an implementation manner, the controlling the wind turbine generator in the wind farm based on the meteorological data comprises: obtaining a predicted abnormal weather type based on the meteorological data; determining a target component that is likely to have a running risk in the wind turbine generator of the wind farm based on the predicted abnormal weather type; and performing corresponding control on the target component.

[0010] In an optional implementation manner, the obtaining the predicted abnormal weather type based on the meteorological data comprises: determining a prediction weight value corresponding to the meteorological data; and performing weather prediction based on the prediction weight value and the meteorological data to obtain the predicted abnormal weather type.

[0011] A second object of the present application is to provide a control device of a wind turbine generator, comprising: a first obtaining module configured to obtain meteorological data of a wind farm region; a first processing module configured to perform weather prediction based on the meteorological data to obtain a first weather prediction result; a second obtaining module configured to, in response to the first weather prediction result being abnormal weather, obtain remote sensing image data and historical abnormal weather image data of the wind farm region; a second processing module configured to obtain a second weather prediction result based on the remote sensing image data and the historical abnormal weather image data; and a control module configured to, in response to the second weather prediction result being abnormal weather, control a wind turbine generator in the wind farm based on the meteorological data.

[0012] In an implementation manner, the first processing module is specifically configured to input the meteorological data into a pre-trained weather prediction model to obtain the first weather prediction result; and the weather prediction model has learned a corresponding relationship between meteorological data and weather types in advance.

[0013] In an optional implementation manner, the weather prediction model is obtained by pre-training through the following steps: obtaining historical abnormal meteorological data corresponding to an abnormal weather type; taking the abnormal weather type as a data label of the historical abnormal meteorological data corresponding to the abnormal weather type; training an initial model based on the historical abnormal meteorological data and the data label to obtain the weather prediction model; and the initial model is a long short-term memory model.

[0014] In an implementation manner, the second processing module is specifically configured to perform data unification processing on the remote sensing image data to obtain weather image data; input the weather image data and the historical severe weather image data into a pre-trained image similarity analysis model to obtain an image similarity between the weather image data and the historical severe weather image data; the image similarity analysis model has learned an ability to obtain the similarity between two images in advance; and in response to the image similarity being greater than or equal to a preset similarity threshold, determining that the second weather prediction result is an abnormal weather.

[0015] In an optional implementation manner, the second processing module is specifically configured to input each of the historical severe weather image data and the weather image data into the image similarity analysis model to obtain a candidate image similarity corresponding to each of the historical severe weather image data; and obtain a maximum one of a plurality of the candidate image similarities as the image similarity.

[0016] In an implementation manner, the control module is specifically configured to obtain a predicted abnormal weather type based on the meteorological data; determine a target component that is likely to have an operation risk in the wind turbine generator of the wind farm based on the predicted abnormal weather type; and control the target component accordingly.

[0017] In an optional implementation manner, the control module is specifically configured to determine a predicted weight value corresponding to the meteorological data; and obtain the predicted abnormal weather type based on the predicted weight value and the meteorological data.

[0018] A third object of the present application is to provide an electronic device comprising at least one processor; and a memory communicatively connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to the first aspect.

[0019] A fourth object of the present application is to provide a computer-readable storage medium storing instructions that, when executed, cause the method according to the first aspect to be implemented.

[0020] A fifth object of the present application is to provide a computer program product comprising a computer program that, when executed by a processor, implements the steps of the method according to the first aspect.

[0021] The wind turbine control method, device, electronic device and storage medium provided by the present application can perform weather prediction based on meteorological data of a wind farm area. A first weather prediction result is obtained, and when the first weather prediction result is abnormal weather, a second weather prediction result is obtained based on remote sensing meteorological data and historical abnormal weather image data, so that when the second weather prediction result is abnormal weather, the wind turbines in the wind farm are controlled based on the meteorological data. The sudden severe weather can be avoided to affect the safe operation of the wind farm.

[0022] Additional aspects and advantages of the present application will be in part apparent and in part pointed out hereinafter. BRIEF DESCRIPTION OF DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and be readily appreciated from the following description, taken in conjunction with the accompanying drawings, in which:

[0024] Figure 1 is a flowchart of a wind turbine control method provided by an embodiment of the present application;

[0025] Figure 2 is a flowchart of another wind turbine control method provided by an embodiment of the present application;

[0026] Figure 3 is a flowchart of a weather prediction model construction and training process provided by an embodiment of the present application;

[0027] Figure 4 is a flowchart of another wind turbine control method provided by an embodiment of the present application;

[0028] Figure 5 is a flowchart of another wind turbine control method provided by an embodiment of the present application;

[0029] Figure 6 is a schematic diagram of a control scheme of a wind turbine provided by an embodiment of the present application;

[0030] Figure 7 is a structural schematic diagram of a control device of a wind turbine provided by an embodiment of the present application;

[0031] Figure 8 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0032] Embodiments of the present application are described in detail below with reference to the accompanying drawings, in which the same or similar notations used throughout the drawings and the specific description denote the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, and cannot be understood as limiting the present application.

[0033] A control method and device of a wind turbine of an embodiment of the present application are described below with reference to the accompanying drawings.

[0034] Figure 1 is a flow schematic diagram of a control method of a wind turbine provided by an embodiment of the present application. As shown in the figure, the method can include but is not limited to the following steps: Figure 1

[0035] Step S101: Obtain meteorological data of a wind farm area.

[0036] For example, first meteorological data of the wind farm area is obtained by a meteorological monitoring device pre-set at the location of the wind farm and the surrounding area, and second meteorological data of the wind farm area is obtained through other channels (for example, meteorological data monitored by a meteorological bureau and other meteorological monitoring platforms), and the first meteorological data and the second meteorological data are collected as the meteorological data of the wind farm area.

[0037] In some embodiments of the present application, the first meteorological data collected by the meteorological monitoring device pre-set at the location of the wind farm and the surrounding area can be obtained in a public network-based manner through an MQTT (Message Queuing Telemetry Transport) protocol.

[0038] In the embodiments of the present application, the meteorological data includes at least one of the following: wind speed, wind direction, precipitation, electric field, temperature, humidity, air pressure, cloud cover, and geological data.

[0039] Step S102: Perform weather prediction based on the meteorological data to obtain a first weather prediction result. ​

[0040] For example, based on the meteorological data, a weather forecast is performed to obtain a first weather forecast result of whether the weather of the wind farm area in a future period of time is normal weather or abnormal weather.

[0041] Step S103: In response to the first weather forecast result being abnormal weather, remote sensing image data of the wind farm area and historical abnormal weather image data are obtained.

[0042] For example, in response to the first weather forecast result being that abnormal weather is likely to occur in the wind farm area in a future period of time, remote sensing image data of the wind farm area is obtained by a meteorological satellite, and historical abnormal weather image data collected by the meteorological satellite when the wind farm area has abnormal weather in the past is obtained.

[0043] Step S104: Based on the remote sensing image data and the historical abnormal weather image data, a second weather forecast result is obtained.

[0044] For example, the remote sensing image data and the historical abnormal weather image data are compared to obtain a comparison result, and the second weather forecast result is determined according to the comparison result.

[0045] Step S105: In response to the second weather forecast result being abnormal weather, wind turbines in the wind farm are controlled based on meteorological data.

[0046] For example, in response to the second weather forecast result being that abnormal weather is likely to occur in the wind farm area in a future period of time, the type of abnormal weather that is likely to occur is predicted based on the meteorological data, to determine problems that are likely to occur in the operation of the wind turbines when the abnormal weather occurs, so that the wind turbines in the wind farm are controlled in a targeted manner according to the above problems.

[0047] It should be noted that in the embodiments of the present application, the terms "wind turbine", "wind power generator", "wind power generator set" and the like can be replaced with each other; the terms "abnormal weather", "severe weather", "extreme weather" and the like can be replaced with each other.

[0048] In the embodiments of the present application, the above-mentioned abnormal weather type can include but is not limited to at least one of the following: strong wind, low temperature, icing, thunderstorm and sandstorm.

[0049] By implementing the embodiments of the present application, weather prediction can be performed based on meteorological data of a wind farm area. A first weather forecast result is obtained, and in response to the first weather forecast result being abnormal weather, a second weather forecast result is obtained based on remote sensing meteorological data and historical abnormal weather image data, so that in response to the second weather forecast result being abnormal weather, wind turbines in the wind farm are controlled based on meteorological data. The influence of sudden severe weather on the safe operation of the wind farm can be avoided.

[0050] In an implementation manner, the first weather prediction result can be obtained based on a pre-trained weather prediction model in combination with the obtained meteorological data. As an example, please refer to Figure 2 is a flowchart of another method for controlling a wind turbine generator provided by an embodiment of the present application. As shown in Figure 2 , the method can include, but is not limited to, the following steps:

[0051] Step S201: Obtain meteorological data of a wind farm area.

[0052] In an embodiment of the present application, step S201 can be implemented by any of the embodiments of the present application, and the present application does not limit this and will not be repeated.

[0053] Step S202: Input the meteorological data into a pre-trained weather prediction model to obtain a first weather prediction result.

[0054] The weather prediction model has learned the corresponding relationship between the meteorological data and the weather type in advance.

[0055] In an embodiment of the present application, the weather type includes normal weather and abnormal weather.

[0056] For example, the meteorological data is input into the pre-trained weather prediction model, and the output result of the weather prediction model is obtained as the first weather prediction result.

[0057] In an alternative implementation manner, the weather prediction model is pre-trained by the following steps: obtaining historical abnormal meteorological data corresponding to an abnormal weather type; taking the abnormal weather type as a data label of the historical abnormal meteorological data corresponding to the abnormal weather type; training an initial model based on the historical abnormal meteorological data and the data label to obtain the weather prediction model; wherein the initial model is a long short-term memory model.

[0058] For example, historical abnormal meteorological data corresponding to different abnormal weather types in a period of time (for example, 2 years) is obtained, and the historical abnormal meteorological data is preprocessed and corrected; each abnormal weather type is taken as a data label of the historical abnormal meteorological data corresponding to the abnormal weather type; the model parameters of an LSTM (Long Short-Term Memory) neural network model are initialized, and the historical abnormal meteorological data and the corresponding data label are taken as training data to repeatedly train the initialized model multiple times, and the model loss value is obtained based on each training to perform back propagation to optimize the model until a preset stopping condition is reached, and the model training is completed to obtain the weather prediction model. As an example, please refer to Figure 3 , Figure 3is a flowchart of a construction and training process of a weather prediction model provided by an embodiment of the present application.

[0059] Step S203: In response to the first weather prediction result being abnormal weather, remote sensing image data and historical abnormal weather image data of the wind farm region are acquired.

[0060] In an embodiment of the present application, step S203 can be implemented in any of the embodiments of the present application, and the present application does not limit this and will not be repeated.

[0061] Step S204: Based on the remote sensing image data and the historical abnormal weather image data, a second weather prediction result is acquired.

[0062] In an embodiment of the present application, step S204 can be implemented in any of the embodiments of the present application, and the present application does not limit this and will not be repeated.

[0063] Step S205: In response to the second weather prediction result being abnormal weather, the wind turbine in the wind farm is controlled based on the meteorological data.

[0064] In an embodiment of the present application, step S205 can be implemented in any of the embodiments of the present application, and the present application does not limit this and will not be repeated.

[0065] By implementing the embodiments of the present application, the first weather prediction result can be acquired based on the pre-trained weather prediction model combined with the acquired meteorological data, and when the first weather prediction result is abnormal weather, the second weather prediction result can be acquired based on the remote sensing meteorological data and the historical abnormal weather image data, so that when the second weather prediction result is abnormal weather, the wind turbine in the wind farm is controlled based on the meteorological data. The impact of sudden severe weather on the safe operation of the wind farm can be avoided.

[0066] In an implementation manner, the similarity between the remote sensing image data and the historical abnormal weather image data can be acquired, and the second weather detection result can be determined based on the similarity. As an example, please refer to Figure 4 , Figure 4 is a flowchart of another method for controlling a wind turbine provided by an embodiment of the present application. As shown in Figure 4 , the method can include but is not limited to the following steps:

[0067] Step S401: Acquire meteorological data of a wind farm region.

[0068] In an embodiment of the present application, step S401 can be implemented in any of the embodiments of the present application, and the present application does not limit this and will not be repeated.

[0069] Step S402: performing weather prediction based on the meteorological data to obtain a first weather prediction result.

[0070] In the embodiments of the present application, step S402 can be implemented by any of the embodiments of the present application, and the present application does not limit this and will not be repeated.

[0071] Step S403: in response to the first weather prediction result being abnormal weather, obtaining remote sensing image data and historical abnormal weather image data of the wind farm area.

[0072] In the embodiments of the present application, step S403 can be implemented by any of the embodiments of the present application, and the present application does not limit this and will not be repeated.

[0073] Step S404: performing data unification processing on the remote sensing image data to obtain weather image data.

[0074] Specifically, the obtained remote sensing image data of the wind farm area is subjected to data unification processing to perform image correction, image enhancement, etc. on the remote sensing image data, and weather image data is extracted from the data after unification processing.

[0075] Step S405: inputting the weather image data and the historical severe weather image data into a pre-trained image similarity analysis model to obtain an image similarity of the weather image data and the historical severe weather image data.

[0076] In the embodiments of the present application, the image similarity analysis model has learned the ability to obtain the similarity between two images in advance.

[0077] For example, the weather image data and the historical severe weather image data are inputted as input data into the pre-trained image similarity analysis model to obtain the image similarity of the weather image data and the historical severe weather image data outputted by the model.

[0078] In some embodiments of the present application, the image similarity analysis model can be a twin neural network model.

[0079] In an alternative implementation, the historical severe weather image data is multiple, the weather image data and the historical severe weather image data are inputted into the pre-trained image similarity analysis model to obtain the image similarity of the weather image data and the historical severe weather image data, including: inputting each historical severe weather image data and the weather image data into the image similarity analysis model respectively to obtain a candidate image similarity corresponding to each historical severe weather image data; obtaining the maximum one of the multiple candidate image similarities as the image similarity.

[0080] For example, the weather image data and each historical severe weather image data are input as a set of input data into the image similarity analysis model respectively to obtain a candidate image similarity of the weather image data and each historical severe weather image data; and the maximum one of the obtained multiple candidate image similarities is obtained as the image similarity.

[0081] Step S406: In response to the image similarity being greater than or equal to the preset similarity threshold, determining that the second weather prediction result is abnormal weather.

[0082] For example, in response to the image similarity between the weather image data and the historical severe weather image data being greater than or equal to a preset similarity threshold (for example, 90%), it is determined that the second weather prediction result is abnormal weather.

[0083] In some embodiments of the present application, in response to the image similarity between the weather image data and the historical severe weather image data being less than a preset similarity threshold, it is determined that the second weather prediction result is normal weather.

[0084] Step S407: In response to the second weather prediction result being abnormal weather, controlling the wind turbine generators in the wind farm based on the meteorological data.

[0085] In the embodiments of the present application, step S407 can be implemented by any one of the various embodiments of the present application, and the present application does not limit this, and will not be repeated here.

[0086] By implementing the embodiments of the present application, weather prediction can be performed based on the meteorological data of the wind farm area. When the first weather prediction result is abnormal weather, the similarity between the remote sensing image data and the historical abnormal weather image data can be obtained, and the second weather prediction result can be obtained based on the similarity. When the second weather prediction result is abnormal weather, the wind turbine generators in the wind farm are controlled based on the meteorological data. The impact of sudden severe weather on the safe operation of the wind farm can be avoided.

[0087] In an implementation manner, the type of abnormal weather that may occur in the wind farm area can be determined according to the meteorological data, so as to control the wind turbine generators in the wind farm based on the type of abnormal weather that may occur. As an example, please refer to Figure 5 , Figure 5 is another flowchart of a method for controlling wind turbine generators provided by the embodiments of the present application. As shown in Figure 5 , the method can include but is not limited to the following steps:

[0088] Step S501: Obtain meteorological data of a wind farm area.

[0089] In the embodiments of the present application, step S501 can be implemented in any of the embodiments of the present application, and the embodiments of the present application do not limit this and will not be repeated.

[0090] Step S502: weather prediction based on meteorological data to obtain a first weather prediction result.

[0091] In the embodiments of the present application, step S502 can be implemented in any of the embodiments of the present application, and the embodiments of the present application do not limit this and will not be repeated.

[0092] Step S503: in response to the first weather prediction result being abnormal weather, obtaining remote sensing image data and historical abnormal weather image data of the wind farm area.

[0093] In the embodiments of the present application, step S503 can be implemented in any of the embodiments of the present application, and the embodiments of the present application do not limit this and will not be repeated.

[0094] Step S504: based on the remote sensing image data and the historical abnormal weather image data, obtaining a second weather prediction result.

[0095] In the embodiments of the present application, step S504 can be implemented in any of the embodiments of the present application, and the embodiments of the present application do not limit this and will not be repeated.

[0096] Step S505: in response to the second weather prediction result being abnormal weather, obtaining a predicted abnormal weather type based on the meteorological data.

[0097] For example, in response to the second weather prediction result being abnormal weather, the type of abnormal weather that the wind farm area is likely to have based on the meteorological data is predicted as the predicted abnormal weather type.

[0098] In an optional implementation, obtaining a predicted abnormal weather type based on meteorological data includes: determining a prediction weight value corresponding to the meteorological data; and performing weather prediction based on the prediction weight value and the meteorological data to obtain the predicted abnormal weather type.

[0099] For example, according to the prediction weight value corresponding to each meteorological data, weather prediction is performed based on the corresponding meteorological data to obtain the predicted abnormal weather type.

[0100] In the embodiments of the present application, the prediction weight value corresponding to each meteorological data can be the same or different.

[0101] Step S506: determining a target component that is likely to have a risk of operation in the wind turbine of the wind farm based on the predicted abnormal weather type.

[0102] For example, it is determined that when the abnormal weather type corresponds to the occurrence of abnormal weather, there is a risk of operation of the target component in each component of the wind turbine of the wind farm.

[0103] As an example, taking gale weather as an example of the abnormal weather type. When typhoon weather occurs, the larger wind speed can cause the wind turbine to be cut off and stopped. The main effects of the gale on the wind turbine include: the yaw system is mechanically damaged; the blade is cracked or torn, the wind turbine collapses; and the anemometer is blown up. The yaw system, the blade, and the anemometer of the wind turbine can be determined as the target component.

[0104] As an example, taking low-temperature weather as an example of the abnormal weather type. Low temperature can cause the damping and other structural characteristics of the blade of the wind turbine to change, the vibration to increase, and the service life to be shortened; the lubrication effect is weakened, the gear box is worn, and the resistance is increased; when the wind turbine is subjected to impact load, brittle fracture can occur; the flowability of the hydraulic oil is reduced, the hydraulic system cannot work normally, the lubrication level of the yaw system of the wind turbine is reduced, or yaw failure is caused; the brake hydraulic system of the wind turbine can not work normally, the brake time is prolonged, the vibration is increased, and the safety performance of the wind turbine is affected; icing caused by low temperature causes the anemometer to be unable to measure the wind speed and direction normally. The blade, the gear box, the hydraulic system, the yaw system, and the anemometer of the wind turbine can be determined as the target component.

[0105] Step S507: Control the target component.

[0106] As an example, taking gale weather as an example of the abnormal weather type, and taking the yaw system, the blade, and the anemometer as the target component. The blade and the anemometer of the wind turbine can be locked.

[0107] As an example, taking low-temperature weather as an example of the abnormal weather type, and taking the blade, the gear box, the hydraulic system, the yaw system, and the anemometer as the target component. The pre-set warmers of the gear box and the hydraulic system can be started, and the working states of the blade, the yaw system, and the anemometer can be monitored to stop the operation of the above components in time when needed.

[0108] In some embodiments of the present application, operation warning information including the predicted abnormal weather type and the related information of the target component can also be generated, and the operation warning information can be pushed to the operation and maintenance personnel of the wind farm through various channels to remind the operation and maintenance personnel to take corresponding protective measures. For example, the operation warning information can be pushed to the terminal device of the operation and maintenance personnel through a short message or other ways.

[0109] By implementing the embodiments of the present application, weather prediction can be performed based on meteorological data of a wind farm area. A first weather prediction result is obtained, and when the first weather prediction result is abnormal weather, a second weather prediction result is obtained based on remote sensing meteorological data and historical abnormal weather image data, so that when the second weather prediction result is abnormal weather, a predicted abnormal weather type can be obtained by combining the meteorological data according to a predetermined weight value, thereby controlling wind turbines in the wind farm based on the predicted abnormal weather type. The sudden bad weather can be avoided to affect the safe operation of the wind farm.

[0110] Please refer to Figure 6 , Figure 6 is a schematic diagram of a control scheme of a wind turbine provided by the embodiments of the present application. As shown in Figure 6 , in the technical scheme, multi-source meteorological data of a wind farm area can be obtained through various data sources, and the obtained multi-source meteorological data is analyzed to predict abnormal weather based on the multi-source meteorological data. When it is predicted that abnormal weather may occur in the wind farm area, a meteorological remote sensing satellite is called to obtain remote sensing meteorological data, and historical abnormal weather image data of the wind farm area is obtained. The remote sensing meteorological data is preprocessed, image corrected and image enhanced, and the like, to extract weather image data. The weather image data and the historical abnormal weather image data are analyzed for similarity, and the similarity between the obtained weather image data and the historical abnormal weather image data is used to predict abnormal weather. When abnormal weather is predicted, meteorological prediction parameter factors corresponding to different meteorological data are determined based on a pre-established wind turbine meteorological influence model analysis library, to predict weather conditions in a future time period. An abnormal weather warning is generated and sent based on the weather conditions in the future time period, to notify wind farm operation and maintenance personnel to take appropriate protective measures.

[0111] Please refer to Figure 7 , Figure 7 is a structural schematic diagram of a control device of a wind turbine provided by the embodiments of the present application. As shown in Figure 7 , the device 700 includes: a first obtaining module 701 configured to obtain meteorological data of a wind farm area; a first processing module 702 configured to perform weather prediction based on the meteorological data, to obtain a first weather prediction result; a second obtaining module 703 configured to, in response to the first weather prediction result being abnormal weather, obtain remote sensing image data and historical abnormal weather image data of the wind farm area; a second processing module 704 configured to obtain a second weather prediction result based on the remote sensing image data and the historical abnormal weather image data; and a control module 705 configured to, in response to the second weather prediction result being abnormal weather, control wind turbines in the wind farm based on the meteorological data.

[0112] In an implementation manner, the first processing module 702 is specifically configured to input the meteorological data into a pre-trained weather prediction model to obtain a first weather prediction result; and the weather prediction model has learned a corresponding relationship between the meteorological data and a weather type in advance.

[0113] In an optional implementation manner, the weather prediction model is obtained by pre-training through the following steps: obtaining historical abnormal meteorological data corresponding to an abnormal weather type; taking the abnormal weather type as a data label of the historical abnormal meteorological data corresponding to the abnormal weather type; and training an initial model based on the historical abnormal meteorological data and the data label to obtain the weather prediction model; and the initial model is a long short-term memory model.

[0114] In an implementation manner, the second processing module 704 is specifically configured to perform data unification processing on the remote sensing image data to obtain weather image data; input the weather image data and historical severe weather image data into a pre-trained image similarity analysis model to obtain an image similarity between the weather image data and the historical severe weather image data; the image similarity analysis model has learned an ability to obtain a similarity between two images in advance; and in response to the image similarity being greater than or equal to a preset similarity threshold, determining that the second weather prediction result is abnormal weather.

[0115] In an optional implementation manner, the second processing module 704 is specifically configured to input each historical severe weather image data and the weather image data into the image similarity analysis model respectively to obtain a candidate image similarity corresponding to each historical severe weather image data; and obtain a maximum one of the plurality of candidate image similarities as the image similarity.

[0116] In an implementation manner, the control module 705 is specifically configured to obtain a predicted abnormal weather type based on the meteorological data; determine a target component that is likely to have a running risk in the wind turbine generator of the wind farm based on the predicted abnormal weather type; and control the target component accordingly.

[0117] In an optional implementation manner, the control module 705 is specifically configured to determine a prediction weight value corresponding to the meteorological data; and perform weather prediction based on the prediction weight value and the meteorological data to obtain the predicted abnormal weather type.

[0118] Through the device of the embodiment of the present application, weather prediction can be performed based on meteorological data of a wind farm area. A first weather prediction result is obtained, and when the first weather prediction result is abnormal weather, a second weather prediction result is obtained based on remote sensing meteorological data and historical abnormal weather image data, so that when the second weather prediction result is abnormal weather, the wind turbine generator in the wind farm is controlled based on the meteorological data. The influence of sudden severe weather on the safe operation of the wind farm can be avoided.

[0119] It should be noted that the above explanation of the embodiment of the control method for a wind turbine generator set is also applicable to the control device for the wind turbine generator set of this embodiment, and will not be repeated here.

[0120] In order to implement the above embodiment, the present application also proposes an electronic device. Figure 8 , Figure 8 Schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 8 As shown, the electronic device 800 includes: a processor 801, and a memory 802 communicatively connected to the processor 801; the memory 802 stores computer-executable instructions; the processor 801 executes the computer-executable instructions stored in the memory to implement the method provided in the aforementioned embodiment.

[0121] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0122] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0123] In the descriptions of the foregoing embodiments, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are mutually inconsistent.

[0124] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0125] Any processes or methods described in the flowcharts or otherwise described herein can be understood as representing modules, segments, or portions of code that include one or more executable instructions for implementing specific logical functions or steps in the processes. The scope of preferred embodiments of the present application encompasses other implementations in which the steps are performed in a different order, including substantially simultaneously, or in reverse order, according to the functions involved, as will be understood by those skilled in the art of the embodiments described herein.

[0126] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a list of executable instructions for implementing the logic function, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor- containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be a more specific example (non-exhaustive list) including the following: an electronic connection having one or more wires (electronic apparatus), a portable computer diskette (magnetic apparatus), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium can even be paper or other suitable medium on which the program can be printed, as the program can be electronically obtained, for example, by optically scanning the paper or other medium, then

[0127] It should be understood that portions of the present application can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As in another embodiment, if implemented in hardware, any of the following technologies known in the art or their combinations can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0128] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiment methods can be completed by programs instructing related hardware, and the programs can be stored in a computer readable storage medium. When the program is executed, it includes one of the steps of the method embodiment or a combination thereof.

[0129] In addition, each functional unit in each embodiment of the present application can be integrated into one processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The integrated module can be realized in the form of hardware or in the form of a software functional module. When the integrated module is realized in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0130] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and cannot be understood as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above-mentioned embodiments within the scope of the present application.

Claims

1. A control method for a wind turbine generator system, characterized in that: include: Obtain meteorological data for the wind farm area; Performing weather forecasting based on the meteorological data to obtain a first weather forecast result; In response to the first weather forecast result being abnormal weather, acquiring remote sensing image data and historical abnormal weather image data of the wind farm area; Obtaining a second weather forecast result based on the remote sensing image data and the historical abnormal weather image data; In response to the second weather forecast result being abnormal weather, controlling the wind turbines in the wind farm based on the meteorological data; The performing weather forecast based on the meteorological data to obtain a first weather forecast result includes: Inputting the meteorological data into a pre-trained weather prediction model to obtain the first weather prediction result; wherein the weather prediction model has pre-learned the corresponding relationship between the meteorological data and the weather type; The weather prediction model is pre-trained by the following steps: Obtain historical abnormal meteorological data corresponding to abnormal weather types; Using the abnormal weather type as a data label for historical abnormal meteorological data corresponding to the abnormal weather type; Training an initial model based on the historical abnormal meteorological data and the data labels to obtain the weather forecast model; wherein the initial model is a long short-term memory model; The obtaining of a second weather forecast result based on the remote sensing image data and the historical abnormal weather image data includes: Performing data unification processing on the remote sensing image data to obtain weather image data; Inputting the weather image data and the historical abnormal weather image data into a pre-trained image similarity analysis model to obtain image similarity between the weather image data and the historical abnormal weather image data; wherein the image similarity analysis model has been pre-learned to obtain the ability to obtain similarity between two images; In response to the image similarity being greater than or equal to a preset similarity threshold, determining that the second weather forecast result is abnormal weather; There are a plurality of historical abnormal weather image data, and inputting the weather image data and the historical abnormal weather image data into a pre-trained image similarity analysis model to obtain image similarity between the weather image data and the historical abnormal weather image data includes: Inputting each of the historical abnormal weather image data and the weather image data into the image similarity analysis model respectively to obtain the candidate image similarity corresponding to each of the historical abnormal weather image data; The largest one among the plurality of candidate image similarities is obtained as the image similarity.

2. The method according to claim 1, wherein The controlling of the wind turbines in the wind farm based on the meteorological data includes: Obtaining a predicted abnormal weather type based on the meteorological data; determining target components of the wind turbines in the wind farm that may have operational risks based on the predicted abnormal weather type; The target component is controlled accordingly.

3. The method according to claim 2, wherein The obtaining of a predicted abnormal weather type based on the meteorological data includes: Determining a prediction weight value corresponding to the meteorological data; Perform weather forecasting based on the forecast weight value and the meteorological data to obtain the forecast abnormal weather type.

4. A control device for a wind turbine generator system for implementing the method according to any one of claims 1 to 3, characterized in that: include: A first acquisition module is used to acquire meteorological data of the wind farm area; A first processing module, configured to perform weather forecasting based on the meteorological data and obtain a first weather forecast result; a second acquisition module, configured to acquire remote sensing image data and historical abnormal weather image data of the wind farm area in response to the first weather forecast result being abnormal weather; A second processing module is used to obtain a second weather forecast result based on the remote sensing image data and the historical abnormal weather image data; a control module, configured to control the wind turbines in the wind farm based on the meteorological data in response to the second weather forecast result being abnormal weather; The first processing module is specifically configured to: Inputting the meteorological data into a pre-trained weather prediction model to obtain the first weather prediction result; wherein the weather prediction model has pre-learned the corresponding relationship between the meteorological data and the weather type; The weather prediction model is pre-trained by the following steps: Obtain historical abnormal meteorological data corresponding to abnormal weather types; Using the abnormal weather type as a data label for historical abnormal meteorological data corresponding to the abnormal weather type; Training an initial model based on the historical abnormal meteorological data and the data labels to obtain the weather forecast model; wherein the initial model is a long short-term memory model; The second processing module is specifically configured to: Performing data unification processing on the remote sensing image data to obtain weather image data; Inputting the weather image data and the historical abnormal weather image data into a pre-trained image similarity analysis model to obtain image similarity between the weather image data and the historical abnormal weather image data; wherein the image similarity analysis model has been pre-learned to obtain the ability to obtain similarity between two images; In response to the image similarity being greater than or equal to a preset similarity threshold, determining that the second weather forecast result is abnormal weather; There are a plurality of historical abnormal weather image data, and the second processing module is specifically used to: Inputting each of the historical abnormal weather image data and the weather image data into the image similarity analysis model respectively to obtain the candidate image similarity corresponding to each of the historical abnormal weather image data; The largest one among the plurality of candidate image similarities is obtained as the image similarity.

5. An electronic device, characterized in that: include: a processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 3 when executed by a processor.

Images