Wind turbine generator control method, device and equipment and computer readable storage medium
The method uses data decomposition and neural network prediction to enhance wind turbine control by forecasting wind conditions at neighboring turbines, addressing delays and inaccuracies in current monitoring systems.
Patent Information
- Application Number
- CN202510726031.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-03
- Publication Date
- 2025-07-15
AI Technical Summary
The wind speed and wind direction monitoring of offshore wind turbines is inaccurate and timely, resulting in lagging and untimely control operations, making it difficult to meet the needs of refined operations.
By obtaining the meteorological data of the first wind turbine in multiple wind turbines, decompose it to obtain characteristic components and trend components, and inputting the target neural network model, we predict the meteorological data of the second wind turbine in multiple wind turbines for precise control.
In advance prediction and precise control of wind turbines are achieved, the problems of lag in meteorological data and untimely control are avoided, and the refined operation of wind turbines is ensured.
Smart Images
Figure CN120312486A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of wind power, and particularly to the field of wind turbine control technology. Background Art
[0002] Offshore wind power has developed rapidly. During the operation of offshore wind turbines, accurate monitoring of wind speed and direction is crucial for the efficient operation and safety control of the turbines. However, currently, each wind turbine monitors the wind speed and direction by itself and then performs corresponding control operations through its own controller. Since the wind vane and anemometer are installed behind the nacelle of the wind turbine, the monitored wind speed and direction may be inaccurate and untimely. Therefore, when the wind turbine performs control operations based on the wind speed and direction it monitors itself, there are problems such as monitoring lag and untimely control, making it difficult to meet the requirements of refined operation. Summary of the Invention
[0003] The present disclosure provides a wind turbine control method, device, equipment, and storage medium.
[0004] According to a first aspect of the present disclosure, a wind turbine control method is provided. The method includes:
[0005] Obtain meteorological data at the location of a first wind turbine among multiple wind turbines; wherein, the meteorological data includes wind direction data and wind speed data;
[0006] Decompose the meteorological data at the location of the first wind turbine to obtain a target component of the first wind turbine, wherein the target component includes a characteristic component and a trend component;
[0007] Input the target component into a target neural network model to predict meteorological data at the location of a second wind turbine among the multiple wind turbines, wherein, with the oncoming wind direction as a reference, the first wind turbine is located in front of the second wind turbine;
[0008] Control the second wind turbine according to the meteorological data at the location of the second wind turbine.
[0009] As described above in the aspect and any possible implementation manner, a further implementation manner is provided. The decomposing the meteorological data at the location of the first wind turbine to obtain a target component of the first wind turbine includes:
[0010] Decompose the meteorological data at the location of the first wind turbine to obtain multiple decomposed components;
[0011] Calculate the entropy value of each of the multiple decomposed components respectively;
[0012] Determine the decomposition components with entropy values higher than the preset entropy value threshold among the multiple decomposition components as feature components;
[0013] Determine the decomposition components with entropy values not higher than the preset entropy value threshold among the multiple decomposition components as trend components.
[0014] In the above-mentioned aspect and any possible implementation manner, a further implementation manner is provided. The inputting the target component into the target neural network model includes:
[0015] Decompose the feature components to obtain multiple modal components;
[0016] Input the multiple modal components and the trend components into the target neural network model.
[0017] In the above-mentioned aspect and any possible implementation manner, a further implementation manner is provided. Before controlling the second wind turbine according to the meteorological data of the location where the second wind turbine is located, the method further includes:
[0018] If there are at least two first wind turbines, obtain the meteorological data of the location where the second wind turbine is predicted by each first wind turbine;
[0019] Integrate the meteorological data of the location where the second wind turbine is predicted by each first wind turbine to obtain the final meteorological data of the location where the second wind turbine is located.
[0020] In the above-mentioned aspect and any possible implementation manner, a further implementation manner is provided. The controlling the second wind turbine according to the meteorological data of the location where the second wind turbine is located includes:
[0021] If the meteorological data of the location where the second wind turbine is located is that the wind speed of the second wind turbine increases, increase the pitch angle of the second wind turbine;
[0022] If the meteorological data of the location where the second wind turbine is located is that the wind speed of the second wind turbine decreases, decrease the pitch angle of the second wind turbine;
[0023] Control the yaw system of the second wind turbine according to the wind direction data in the meteorological data of the location where the second wind turbine is located.
[0024] In the above-mentioned aspect and any possible implementation manner, a further implementation manner is provided. The method further includes:
[0025] If any one of the multiple wind turbines fails, determine the associated wind turbines related to the first wind turbine from the multiple wind turbines according to the wind direction.
[0026] Obtain the wind speed data and wind direction data of the associated wind turbine
[0027] Determine the wind speed data and wind direction data of any one of the wind turbines according to the wind speed data and wind direction data of the associated wind turbine
[0028] In the above aspects and any possible implementation manners, a further implementation manner is provided. The determining, according to the wind direction of the incoming wind, the associated wind turbines related to the first wind turbine from the plurality of wind turbines includes:
[0029] Determine each adjacent wind turbine adjacent to any one of the wind turbines from the plurality of wind turbines according to the wind direction of the incoming wind and the positions of the plurality of wind turbines
[0030] Calculate the correlation coefficient between any one of the wind turbines and each adjacent wind turbine according to the correlation coefficient method
[0031] Select the wind turbines with a correlation coefficient higher than a preset coefficient from each adjacent wind turbine as the associated wind turbines
[0032] The determining the wind speed data and wind direction data of any one of the wind turbines according to the wind speed data and wind direction data of the associated wind turbine includes:
[0033] Assign a wind speed weight coefficient and a wind direction weight coefficient to the associated wind turbine according to the correlation coefficient of the associated wind turbine
[0034] Determine the wind speed data and wind direction data of any one of the wind turbines according to the wind speed data and wind direction data of the associated wind turbine and the wind speed weight coefficient and wind direction weight coefficient of the associated wind turbine
[0035] According to a second aspect of the present disclosure, a wind turbine control device is provided. The device includes: an acquisition module, configured to acquire meteorological data at the location of a first wind turbine among a plurality of wind turbines; wherein, the meteorological data includes wind direction data and wind speed data
[0036] A decomposition module, configured to decompose the meteorological data at the location of the first wind turbine to obtain a target component of the first wind turbine, wherein the target component includes a feature component and a trend component
[0037] A prediction module, configured to input the target component into a target neural network model to predict the meteorological data at the location of a second wind turbine among the plurality of wind turbines, wherein, with the wind direction of the incoming wind as a reference, the first wind turbine is located in front of the second wind turbine
[0038] A control module for controlling the second wind turbine according to the meteorological data at the location of the second wind turbine.
[0039] According to a third aspect of the present disclosure, an electronic device is provided. The electronic device includes: a memory and a processor, a computer program is stored on the memory, and when the processor executes the program, the method as described above is implemented.
[0040] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.
[0041] In the present disclosure, by obtaining the meteorological data at the location of the first wind turbine in front among multiple wind turbines, and decomposing the meteorological data at the location of the first wind turbine to obtain the target component of the first wind turbine, and then inputting the target component into the target neural network model, the meteorological data at the location of the second wind turbine behind among the multiple wind turbines can be accurately predicted. Compared with the second wind turbine measuring the wind speed and direction by itself, it obviously realizes early prediction. Thus, according to the meteorological data at the location of the second wind turbine, the second wind turbine can be accurately controlled in advance, avoiding the problems of lag and untimely control of the meteorological data at the location of the second wind turbine. Moreover, using this control method can still obtain the meteorological data at the location of the second wind turbine when the second wind turbine fails, so as to achieve refined operation.
[0042] It should be understood that the content described in the summary of the invention is not intended to limit the key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Combined with the drawings and referring to the following detailed description, the above and other features, advantages and aspects of the embodiments of the present disclosure will become more obvious. The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. In the drawings, the same or similar reference numerals represent the same or similar elements, where:
[0044] Figure 1 Shows a flowchart of a wind turbine control method according to an embodiment of the present disclosure;
[0045] Figure 2 Shows a flowchart of another wind turbine control method according to an embodiment of the present disclosure;
[0046] Figure 3 Shows a replacement schematic diagram when a wind turbine fails according to an embodiment of the present disclosure;
[0047] Figure 4 The block diagram of a wind turbine control device according to an embodiment of the present disclosure is shown.
[0048] Figure 5 The block diagram of an exemplary electronic device capable of implementing the embodiments of the present disclosure is shown. Detailed implementation manners
[0049] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are some but not all of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the scope of protection of the present disclosure.
[0050] In addition, the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after.
[0051] Figure 1 The flowchart of a wind turbine control method 100 according to an embodiment of the present disclosure is shown. Method 100 may include:
[0052] Step 110: Obtain meteorological data at the location of the first wind turbine among multiple wind turbines; wherein, the meteorological data includes wind direction data and wind speed data;
[0053] Install a data acquisition device on the first wind turbine to collect meteorological data such as wind direction and wind speed at its location in real time, ensuring the comprehensiveness and timeliness of the data.
[0054] Step 120: Decompose the meteorological data at the location of the first wind turbine to obtain the target components of the first wind turbine, wherein the target components include characteristic components and trend components;
[0055] Step 130: Input the target components into a target neural network model to predict the meteorological data at the location of the second wind turbine among the multiple wind turbines, wherein, with the oncoming wind direction as a reference, the first wind turbine is located in front of the second wind turbine;
[0056] As Figure 4 shown, with the oncoming wind direction as a reference, if the first wind turbines are turbine B and turbine C, then the second wind turbine is turbine A.
[0057] Step 150, control the second wind turbine according to the meteorological data at the location of the second wind turbine. There can be multiple or only one first wind turbine, and there can also be multiple or only one second wind turbine.
[0058] By obtaining the meteorological data at the location of the first wind turbine located in the front among multiple wind turbines, decomposing the meteorological data at the location of the first wind turbine to obtain the target components of the first wind turbine, and then inputting the target components into the target neural network model, the meteorological data at the location of the second wind turbine located in the back among the multiple wind turbines can be accurately predicted. Compared with the second wind turbine measuring the wind speed and direction by itself, it obviously realizes early prediction. Thus, according to the meteorological data at the location of the second wind turbine, the second wind turbine can be precisely controlled in advance, avoiding the problems of lag and untimely control of the meteorological data at the location of the second wind turbine. Moreover, using this control method can still obtain the meteorological data at its location when the second wind turbine fails, thereby realizing refined operation.
[0059] In some embodiments, the decomposing the meteorological data at the location of the first wind turbine to obtain the target components of the first wind turbine includes:
[0060] Decompose the meteorological data at the location of the first wind turbine to obtain multiple decomposed components;
[0061] Calculate the entropy values of the multiple decomposed components respectively;
[0062] Before decomposition, the quartile + DBSCAN method can be used to clean the data, effectively removing outliers and noise, ensuring the accuracy of the data, and providing a reliable basis for subsequent analysis.
[0063] Determine the decomposed components with entropy values higher than the preset entropy threshold among the multiple decomposed components as feature components;
[0064] Feature components represent detailed features, such as a sudden change in wind speed or direction at a certain time point, and trend components represent the overall change trend.
[0065] Determine the decomposed components with entropy values not higher than the preset entropy threshold among the multiple decomposed components as trend components.
[0066] The CEEMDAN method is used to adaptively decompose the preprocessed meteorological data, decomposing the complex signal into multiple relatively simple components, calculating the entropy values of each component respectively. Components with high entropy values usually have higher complexity, while components with low entropy values are relatively simple. Therefore, all components can be divided into two groups according to the entropy values. The components with high entropy values are reconstructed as feature components, covering the complex features of the data; the components with low entropy values are reconstructed to restore the original trend of the data and become trend components, reflecting the overall change trend of the data.
[0067] In some embodiments, inputting the target component into the target neural network model includes:
[0068] Decompose the feature component to obtain multiple modal components;
[0069] Input the multiple modal components and the trend component into the target neural network model.
[0070] Use VMD to decompose the feature component to obtain several modal components with different center frequencies, improving the analyzability of the signal. Then, use the LSTM deep learning model to predict each modal component and the trend component respectively to obtain the meteorological data at the location of the second wind turbine.
[0071] In some embodiments, before controlling the second wind turbine according to the meteorological data at the location of the second wind turbine, the method further includes:
[0072] If there are at least two first wind turbines, obtain the meteorological data at the location of the second wind turbine predicted by each first wind turbine;
[0073] Integrate the meteorological data at the location of the second wind turbine predicted by each first wind turbine to obtain the final meteorological data at the location of the second wind turbine.
[0074] There can be multiple first wind turbines. In this case, each first wind turbine can predict the meteorological data at the location of the second wind turbine, so that multiple meteorological data at the location of the second wind turbine can be obtained. Therefore, the meteorological data at the location of the second wind turbine predicted by each first wind turbine can be integrated to ensure the accuracy of the final meteorological data at the location of the second wind turbine.
[0075] The integration method can be as follows:
[0076] Calculate the average value of the meteorological data at the location of the second wind turbine predicted by each first wind turbine to obtain the final meteorological data; or
[0077] Assign weight coefficients to the meteorological data at the locations of the first wind turbines according to the distances between the first wind turbines and the second wind turbines. The closer the distance, the larger the weight coefficient. Then, perform weighted summation on the meteorological data at the locations of the second wind turbines predicted by each first wind turbine to obtain the final meteorological data.
[0078] In addition, it should be noted that: if there are multiple second wind turbines, the meteorological data at the locations of each second wind turbine are integrated according to the above integration method.
[0079] In some embodiments, controlling the second wind turbine according to the meteorological data at the location of the second wind turbine includes:
[0080] If the meteorological data at the location of the second wind turbine is that the wind speed of the second wind turbine increases, increase the pitch angle of the second wind turbine;
[0081] If the meteorological data at the location of the second wind turbine is that the wind speed of the second wind turbine decreases, decrease the pitch angle of the second wind turbine;
[0082] Control the yaw system of the second wind turbine according to the wind direction data in the meteorological data at the location of the second wind turbine.
[0083] When the predicted wind speed increases, gradually increase the pitch angle to improve the wind energy capture efficiency of the second wind turbine; when the predicted wind speed decreases, correspondingly decrease the pitch angle to avoid overloading the second wind turbine.
[0084] Based on the predicted wind direction change, control the yaw system of the second wind turbine in advance so that the impeller of the second wind turbine always faces the incoming wind direction. Through accurate wind direction prediction and timely yaw control, reduce the impact of wind direction deviation on the power generation efficiency of the second wind turbine and reduce the mechanical load and fatigue damage of the second wind turbine.
[0085] In some embodiments, the method further includes:
[0086] If any one of the multiple wind turbines fails, determine the associated wind turbines related to the first wind turbine from the multiple wind turbines according to the incoming wind direction;
[0087] Obtain the wind speed data and wind direction data of the associated wind turbines;
[0088] Determine the wind speed data and wind direction data of any one of the wind turbines according to the wind speed data and wind direction data of the associated wind turbines.
[0089] If any one of the multiple wind turbines fails, then according to the wind direction, associated wind turbines related to the first wind turbine are determined from the multiple wind turbines, and then according to the wind speed data and wind direction data of the associated wind turbines, the wind speed data and wind direction data of any one of the wind turbines are automatically determined. In this way, substitution can be achieved according to the data of the associated wind turbines when a wind turbine fails, so as to perform fault compensation in a timely manner and ensure the stable operation of the wind turbines.
[0090] As Figure 2 shown, in some embodiments, the determining, according to the wind direction, of the associated wind turbines related to the first wind turbine from the multiple wind turbines includes:
[0091] Determining, according to the wind direction and the respective positions of the multiple wind turbines, the adjacent wind turbines adjacent to any one of the wind turbines from the multiple wind turbines;
[0092] Calculating the correlation coefficients between any one of the wind turbines and the adjacent wind turbines according to the correlation coefficient method;
[0093] The correlation coefficient method may be the Pearson correlation coefficient method.
[0094] The calculation method may be as follows: Using the Pearson correlation coefficient method to calculate the historical meteorological data of any one of the wind turbines and the historical meteorological data of the adjacent wind turbines, the correlation coefficients between any one of the wind turbines and the adjacent wind turbines can be obtained.
[0095] Selecting, from the adjacent wind turbines, the wind turbines with correlation coefficients higher than a preset coefficient as the associated wind turbines;
[0096] The larger the correlation coefficient, the stronger the correlation between the two wind turbines. Therefore, the wind turbines with stronger correlation and correlation coefficients higher than the preset coefficient can be selected from the adjacent wind turbines as the associated wind turbines.
[0097] The determining, according to the wind speed data and wind direction data of the associated wind turbines, of the wind speed data and wind direction data of any one of the wind turbines includes:
[0098] Assigning a wind speed weight coefficient and a wind direction weight coefficient to the associated wind turbines according to the correlation coefficients of the associated wind turbines;
[0099] Determining the wind speed data and wind direction data of any one of the wind turbines according to the wind speed data and wind direction data of the associated wind turbines and the wind speed weight coefficient and wind direction weight coefficient of the associated wind turbines.
[0100] After selecting the associated wind turbines using the correlation coefficient method, the wind speed weight coefficient and the wind direction weight coefficient can be assigned to the associated wind turbines according to the correlation coefficients of the associated wind turbines. Then, based on the wind speed data and wind direction data of the associated wind turbines and the wind speed weight coefficient and wind direction weight coefficient of the associated wind turbines, the wind speed data and wind direction data of any one of the wind turbines can be accurately calculated, as Figure 3 shown.
[0101] The following combines Figure 3 to illustrate the principle of predicting the faulty wind turbine using the wind speed and wind direction of the associated wind turbines when a certain wind turbine fails as shown in Figure 2 :
[0102] For example, assume that the faulty wind turbine (the wind turbine with a damaged anemometer and / or wind vane) is A, and the adjacent wind turbines B and C in its incoming wind direction have strong correlations (that is, wind turbines B and C are the wind turbines with large correlation coefficients with wind turbine A). The wind speed and wind direction data of unit B are V B , D B , and the wind speed and wind direction data of unit C are V C , D C . Set the wind speed weight coefficients to be and respectively, and satisfy . Set the wind direction weight coefficients to be and respectively, and also satisfy . Finally, the wind speed data of the faulty wind turbine A is , and the wind direction data is . Transmit V A and D A to the faulty wind turbine A to control the faulty wind turbine A.
[0103] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present disclosure is not limited by the described action sequence, because according to the present disclosure, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present disclosure.
[0104] The above is the introduction of the method embodiments. The following further illustrates the solution of the present disclosure through device embodiments.
[0105] Figure 4 shows a block diagram of a wind turbine control device 400 according to an embodiment of the present disclosure. As Figure 4 shown, the device 400 includes:
[0106] An acquisition module 410 is configured to acquire meteorological data at the location of a first wind turbine among a plurality of wind turbines; wherein, the meteorological data includes wind direction data and wind speed data;
[0107] A decomposition module 420 is configured to decompose the meteorological data at the location of the first wind turbine to obtain a target component of the first wind turbine, wherein the target component includes a characteristic component and a trend component;
[0108] A prediction module 430 is configured to input the target component into a target neural network model to predict meteorological data at the location of a second wind turbine among the plurality of wind turbines, wherein, with the incoming wind direction as a reference, the first wind turbine is located in front of the second wind turbine;
[0109] A control module 440 is configured to control the second wind turbine according to the meteorological data at the location of the second wind turbine.
[0110] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the described modules can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.
[0111] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a non-transitory computer-readable storage medium storing computer instructions.
[0112] Figure 5 FIG. shows a schematic block diagram of an electronic device 500 that can be used to implement the embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0113] The device 800 includes a computing unit 801, which can execute various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other through a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.
[0114] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as a keyboard, mouse, etc.; output unit 807, such as various types of displays, speakers, etc.; storage unit 808, such as a disk, optical disc, etc.; and communication unit 809, such as a network card, modem, wireless communication transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.
[0115] Computing unit 801 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of computing unit 801 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Computing unit 801 executes the various methods and processes described above, such as method 100. For example, in some embodiments, method 100 can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by computing unit 801, one or more steps of method 100 described above can be executed. Alternatively, in other embodiments, computing unit 801 can be configured to execute method 100 in any other suitable manner (e.g., by means of firmware).
[0116] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), systems-on-a-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor, that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.
[0117] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowchart and / or block diagram are implemented. The program codes can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.
[0118] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0119] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0120] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.
[0121] The computing system can include a client and a server. The client and the server are generally remote from each other and typically interact via a communication network. The client-server relationship is created by computer programs that run on respective computers and have a client-server relationship with each other. The server can be a cloud server, can also be a server of a distributed system, or a server that incorporates a blockchain.
[0122] It should be understood that the various forms of the processes shown above can be used, steps can be reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this is not limited herein.
[0123] The above specific embodiments do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.
Claims
1. A control method for a wind turbine unit, characterized in that Including: Obtain meteorological data at the location of a first wind turbine among multiple wind turbines; wherein, the meteorological data includes wind direction data and wind speed data; Decompose the meteorological data at the location of the first wind turbine to obtain the target components of the first wind turbine, where the target components include characteristic components and trend components; Input the target components into a target neural network model to predict the meteorological data at the location of a second wind turbine among the multiple wind turbines, where, with the oncoming wind direction as a reference, the first wind turbine is located in front of the second wind turbine; Control the second wind turbine according to the meteorological data at the location of the second wind turbine.
2. The method according to claim 1, wherein The decomposing the meteorological data at the location of the first wind turbine to obtain the target components of the first wind turbine includes: Decompose the meteorological data at the location of the first wind turbine to obtain multiple decomposed components; Calculate the entropy value of each of the multiple decomposed components respectively; Determine the decomposed components with entropy values higher than a preset entropy value threshold among the multiple decomposed components as characteristic components; Determine the decomposed components with entropy values not higher than the preset entropy value threshold among the multiple decomposed components as trend components.
3. The method according to claim 1, characterized in that The inputting the target components into a target neural network model includes: Decompose the characteristic components to obtain multiple modal components; Input the multiple modal components and the trend components into the target neural network model.
4. The method according to claim 1, wherein Before controlling the second wind turbine according to the meteorological data at the location of the second wind turbine, the method further includes: If there are at least two first wind turbines, obtain the meteorological data at the location of the second wind turbine predicted by each first wind turbine; Integrate the meteorological data at the location of the second wind turbine predicted by each first wind turbine to obtain the final meteorological data at the location of the second wind turbine.
5. The method according to claim 1, wherein The controlling the second wind turbine according to the meteorological data at the location of the second wind turbine includes: If the meteorological data at the location of the second wind turbine is that the wind speed of the second wind turbine increases, increase the pitch angle of the second wind turbine; If the meteorological data at the location of the second wind turbine is that the wind speed of the second wind turbine decreases, decrease the pitch angle of the second wind turbine; Control the yaw system of the second wind turbine according to the wind direction data in the meteorological data at the location of the second wind turbine.
6. The method according to any one of claims 1 to 5, characterized in that The method further includes: If any one of the multiple wind turbines fails, determine the associated wind turbines related to the first wind turbine from the multiple wind turbines according to the oncoming wind direction; Obtain the wind speed data and wind direction data of the associated wind turbines; Determine the wind speed data and wind direction data of the any one wind turbine according to the wind speed data and wind direction data of the associated wind turbines.
7. The method according to claim 6, characterized in that, Determining associated wind turbine generators related to the first wind turbine generator from the multiple wind turbine generators according to the wind direction incoming includes: Determining, from the multiple wind turbine generators, each adjacent wind turbine generator adjacent to any one of the wind turbine generators according to the wind direction incoming and the positions of the multiple wind turbine generators; Calculating the correlation coefficient between any one of the wind turbine generators and each adjacent wind turbine generator according to the correlation coefficient method; Selecting, from the adjacent wind turbine generators, the wind turbine generators with a correlation coefficient higher than a preset coefficient as the associated wind turbine generators; Determining the wind speed data and wind direction data of any one of the wind turbine generators according to the wind speed data and wind direction data of the associated wind turbine generators includes: Assigning a wind speed weight coefficient and a wind direction weight coefficient to the associated wind turbine generators according to the correlation coefficient of the associated wind turbine generators; Determining the wind speed data and wind direction data of any one of the wind turbine generators according to the wind speed data and wind direction data of the associated wind turbine generators and the wind speed weight coefficient and wind direction weight coefficient of the associated wind turbine generators.
8. A wind turbine control device, characterized in that Including: An acquisition module, configured to acquire meteorological data at the location of a first wind turbine generator among multiple wind turbine generators; wherein, the meteorological data includes wind direction data and wind speed data; A decomposition module, configured to decompose the meteorological data at the location of the first wind turbine generator to obtain a target component of the first wind turbine generator, wherein the target component includes a characteristic component and a trend component; A prediction module, configured to input the target component into a target neural network model to predict the meteorological data at the location of a second wind turbine generator among the multiple wind turbine generators, wherein, with the wind direction incoming as a reference, the first wind turbine generator is located in front of the second wind turbine generator; A control module, configured to control the second wind turbine generator according to the meteorological data at the location of the second wind turbine generator.
9. An electronic device, characterized in that, Including: A memory and a processor, wherein a computer program is stored on the memory, and the processor implements the method according to any one of claims 1-7 when executing the program.
10. A computer-readable storage medium, characterized in that when the instructions in the storage medium are executed by a processor corresponding to an electronic device, the electronic device can implement the wind turbine generator control method according to any one of claims 1-7.