An intelligent control system, method, medium and device for a wind turbine generator system

Abstract

The present invention discloses an intelligent control system, method, medium and equipment for a wind turbine generator set. The system includes: a wind measurement module for acquiring wind speed and wind direction data and transmitting the data to a main control module; an operation status monitoring module for recording the operation status data of the wind turbine generator set and transmitting the operation status data to the main control module; the main control module learns the input operation status data through a neural network algorithm and a deep learning model, calculates optimal control parameters in combination with the wind speed and wind direction data and preset design data, controls the wind turbine generator set to perform independent pitch control actions according to the optimal control parameters, and adjusts the stall state and clearance state of the wind turbine generator set during operation; the present invention uses the operation status data of the wind turbine generator set as input, performs learning and judgment through a neural network algorithm and a deep learning model, changes the control parameters of the wind turbine generator set during operation, does not require the addition of additional sensors, and improves the economy of the entire machine.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of stall and clearance control of wind turbine generators, in particular to a wind turbine generator intelligent control system, method, medium and equipment. BACKGROUND

[0002] The wind turbine generator is a power machine that captures wind energy through a wind wheel. The wind energy drives the wind wheel to rotate through a transmission system to drive the generator to work and generate electricity. In order to capture more wind energy and reduce the cost of electricity, the large-scale and lightweight of the wind turbine generator has become the only way for the development of wind power technology. Due to the demand for large-scale and lightweight of the wind turbine generator, the lightweight and height increase of the tower and the lightweight and length increase of the blade will reduce the stiffness and increase the deformation, which increases the risk of stall operation and blade tower scanning of the wind turbine generator. For the stall problem of the wind turbine generator, there is no good solution in the field, and the divergence of the stall problem will affect the power generation and safety of the unit.

[0003] The main solutions to the blade tower scanning of the wind turbine generator in the prior art are: 1) laser range finder for clearance distance measurement, which emits a laser beam from the nacelle and measures the distance of the blade by detecting the echo. The laser range finder is used for clearance distance measurement, which has the advantages of simple result, low cost, strong anti-interference ability and suitability for outdoor operation, but the measurement performance is greatly affected by weather and environment, and the measurement performance decreases in rain, fog and dust environment; 2) clearance measurement method based on image ranging, which calculates the clearance distance by shooting a picture of the blade deformation. The camera performance and image processing algorithm are required to be high, and the measurement performance decreases at night and in low visibility environment. SUMMARY

[0004] The present application aims to overcome the shortcomings of the prior art and provides a wind turbine generator intelligent control system, method, medium and equipment. The system can calculate the operating state data of the wind turbine generator, control the wind turbine generator to perform independent variable pitch action according to the calculation result, adjust the stall state and clearance state of the wind turbine generator during operation, and effectively solve the above-mentioned problems in the prior art, providing convenience for more users.

[0005] The purpose of the present application is achieved by the following technical scheme: a wind turbine generator intelligent control system, comprising:

[0006] A wind measurement module is installed at the center of the hub of the wind turbine generator for obtaining wind speed and wind direction data and transmitting them to the main control module;

[0007] An operating state monitoring module is used to record the operating state data of the wind turbine generator and transmit the operating state data to the main control module;

[0008] The main control module learns the input operating state data through a neural network algorithm and a deep learning model, calculates optimal control parameters in combination with wind speed and wind direction data and preset design data, and controls the wind turbine generator to perform independent pitch action according to the optimal control parameters, so as to adjust the stall state and the clearance state of the wind turbine generator during operation.

[0009] Further, the main control module comprises an operating state analysis module and an operating state control module.

[0010] Further, the operating state analysis module comprises:

[0011] The learning of the input operating state data through the neural network algorithm and the deep learning model comprises: stall state learning and judgment of wind speed-power, clearance state learning and judgment of wind speed-load, and clearance state learning and judgment of wind shear-independent pitch;

[0012] The stall state learning and judgment of wind speed-power inputs the operating state data and the wind speed-power designed for the wind turbine generator into the deep learning model, obtains an importance value through parameter comparison training and learning to determine the control instruction of the pitch action, optimizes the control instruction in combination with other control instructions of the wind turbine generator, and outputs the operating state control instruction of the wind turbine generator;

[0013] The clearance state learning and judgment of wind speed-load inputs the operating state data and the wind speed-load designed for the wind turbine generator into the deep learning model, obtains an importance value through parameter comparison training and learning to determine the control instruction of the pitch action, optimizes the control instruction in combination with other control instructions of the wind turbine generator, and outputs the operating state control instruction of the wind turbine generator;

[0014] The clearance state learning and judgment of wind shear-independent pitch calculates, through the wind speed and the wind direction data, that when the wind shear is less than 0, the azimuth angle of the wind wheel is parallel to the tower, and realizes the pitch action in advance through independent pitch.

[0015] Further, the deep learning model is updated to correct the deviation between the design data and the measured data, to adjust the deviation level, the load deviation level, the angle between the blade and the tower, and the corresponding pitch rate, to realize the optimization of the control parameters, and to calculate the optimal control parameters.

[0016] Further, the stall state learning and judgment of wind speed-power comprises:

[0017] Based on the comparison between the design data of the wind turbine generator set and the measured operating state data, the power in the measured operating state data adopts the inverter online data of the wind turbine generator set, when the wind speed is the same, if the deviation value of the wind speed-power corresponding relationship exceeds the deviation level, it proves that the stall problem occurs, when the deviation level is A, it is light stall, the pitch rate is 0.5° / s; when the deviation level is B, it is light stall, the pitch rate is 1° / s; when the deviation level is C, it is light stall, the pitch rate is 2° / s; when the deviation level is D, it is light stall, the pitch rate is 3° / s; when the deviation level is S, it is light stall, the pitch rate is 5° / s, and the wind turbine generator set is in the state of waiting and idling;

[0018] The deviation value of the deviation level is calculated as follows:

[0019]

[0020] When 10%≤deviation value<15%, the deviation level is A; when 15%≤deviation value<20%, the deviation level is B; when 20%≤deviation value<30%, the deviation level is C; when 30%≤deviation value<50%, the deviation level is D; and when the deviation value is ≥50%, the deviation level is S.

[0021] Further, the wind speed-load clearance state learning judgment comprises:

[0022] Based on the comparison between the design data of the wind turbine generator set and the measured operating state data, the load in the measured operating state data adopts the independent pitch load sensor data of the wind turbine generator set, when the wind speed is the same, if the deviation of the wind speed-load corresponding relationship exceeds the load deviation level, it proves that there is a tower scanning risk; when the load deviation level is A-load, it is normal deviation, the pitch rate is ±0.1° / s, when the test load>design load, the pitch rate is 0.1° / s; when the test load<design load, the pitch rate is-0.1° / s; when the load deviation level is B-load, it is light deviation, the pitch rate is ±0.5° / s, when the test load>design load, the pitch rate is 0.5° / s; when the test load<design load, the pitch rate is-0.5° / s; when the load deviation level is C-load, it is moderate deviation, the pitch rate is ±1° / s, when the test load>design load, the pitch rate is 1° / s; when the test load<design load, the pitch rate is-1° / s; when the load deviation level is D-load, it is heavy deviation, the pitch rate is ±2° / s, when the test load>design load, the pitch rate is 2° / s; when the test load<design load, the pitch rate is-2° / s; when the load deviation level is S-load, it is extreme deviation, the pitch rate is 3° / s, and the wind turbine generator set is in the state of waiting and idling;

[0023] The deviation of the load deviation level is calculated as follows: the deviation value is calculated as follows:

[0024]

[0025] When 5%≤ deviation value<10%, the load deviation level is A-load; when 10%≤ deviation value<20%, the load deviation level is B-load; when 20%≤ deviation value<30%, the load deviation level is C-load; when 30%≤ deviation value<50%, the load deviation level is D-load; and when deviation value≥50%, the load deviation level is S-load.

[0026] Further, the wind shear-independent variable pitch clearance state learning judgment comprises:

[0027] When the wind shear is calculated by wind speed and wind direction data is less than 0, it is judged that the wind wheel azimuth is parallel to the tower, and the pre-pitching action is realized by independent variable pitch; when the wind shear is-0.2<wind shear≤-0.05, the variable pitch rate is 0.5° / s when the blade and the tower are at an angle of 30°; when the wind shear is-0.4<wind shear≤-0.2, the variable pitch rate is 1° / s when the blade and the tower are at an angle of 60°; when the wind shear is-0.6<wind shear≤-0.4, the variable pitch rate is 1.5° / s when the blade and the tower are at an angle of 90°; when the wind shear is-1<wind shear≤-0.6, the variable pitch rate is 2° / s when the blade and the tower are at an angle of 90°; and when the wind shear is greater than or equal to-1, the variable pitch rate is 3° / s when the blade and the tower are at an angle of 90°.

[0028] Further, the wind measurement module comprises a 3D scanning radar, and the operating state data comprises instantaneous wind speed, average wind speed, instantaneous wind direction, average wind direction, generator speed, generator torque, variable pitch angle, yaw angle, wind wheel azimuth and frequency converter on-grid power.

[0029] An intelligent control method of a wind turbine generator system, which is realized by calling a wind measurement module, an operating state monitoring module and a main control module in the intelligent control system of the wind turbine generator system through a processor.

[0030] A non-transitory computer readable medium storing instructions, which, when executed by a processor, perform the intelligent control method of the wind turbine generator system.

[0031] A computing device comprising a processor and a memory for storing a processor-executable program, wherein the processor, when executing the program stored in the memory, realizes the intelligent control method of the wind turbine generator system.

[0032] Compared with the prior art, the present application has the following advantages and beneficial effects:

[0033] 1、The wind turbine and the operating state data of the wind farm are used as inputs, the neural network algorithm and the deep learning model are used for learning and judgment, the control parameters during the operation of the wind turbine are changed, no additional sensors are needed, the cost of the whole machine is saved, and the economy of the whole machine is improved.

[0034] 2、The wind speed-power stall state learning judgment is performed by the neural network algorithm, the control parameter adjustment is performed, the stall problem in the operation process is avoided, and the power generation and safety of the unit are ensured.

[0035] 3、The wind speed-load stall state learning judgment is performed by the neural network algorithm, the control parameter adjustment is performed, the tower scanning problem caused by too low clearance in the operation process is avoided, and the safety of the unit is ensured.

[0036] 4、The 3D scanning radar and the independent variable pitch technology are combined, the control parameter adjustment is performed, the adverse effect of negative wind shear on the clearance is avoided, and the safety of the unit is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 It is the architecture diagram of the wind turbine intelligent control system.

[0038] Figure 2 It is the installation structure schematic diagram of the wind turbine intelligent control system.

[0039] Figure 3 It is the flow chart of the wind speed-power stall state learning judgment.

[0040] Figure 4 It is the flow chart of the wind speed-load clearance state learning judgment. DETAILED DESCRIPTION

[0041] The application will be further described below in combination with specific embodiments.

[0042] Embodiment 1

[0043] Referring to Figures 1 to 2 The wind turbine intelligent control system provided by the embodiment includes:

[0044] The wind measuring module 2 is installed at the center position of the hub 4 of the wind turbine, the wind measuring module 2 includes a 3D scanning radar, the influence of the wind wheel wake is avoided, and the wind speed and direction data are obtained and transmitted to the main control module 3;

[0045] The running state monitoring module 1 is used for recording the running state data of the wind turbine generator set and transmitting the running state data to the main control module 3; wherein the running state data includes instantaneous wind speed, average wind speed, instantaneous wind direction, average wind direction, generator speed, generator torque, variable pitch angle, yaw angle, wind wheel azimuth angle and frequency converter grid-connected power;

[0046] The main control module 3 is installed in the hub 4, learns the running state data input by the running state monitoring module 1 through a recurrent neural network, calculates optimal control parameters in combination with the wind speed and wind direction data input by the wind measurement module 2 and the preset design data, and controls the wind turbine generator set to perform independent variable pitch action according to the optimal control parameters, so as to adjust the stall state and clearance state of the wind turbine generator set during operation.

[0047] Further, the main control module 3 includes a running state analysis module 301 and a running state control module 302, wherein:

[0048] The running state analysis module 301 is responsible for learning the running state data of the wind turbine generator set by using a recurrent neural network, and calculating and outputting optimal control parameters to the running state control system in combination with the actual wind speed and wind direction data and the simulation design data;

[0049] The running state control module 302 controls the variable pitch action of the wind turbine generator set, and adjusts the stall problem and the clearance problem of the wind turbine generator set during operation through independent variable pitch.

[0050] Further, the running state analysis module 301 includes:

[0051] The input running state data is learned through a neural network algorithm and a deep learning model, including: stall state learning judgment of wind speed-power, clearance state learning judgment of wind speed-load and clearance state learning judgment of wind shear-independent variable pitch; the deviation between the design data and the measured data is corrected by updating the deep learning model, and the deviation level, the load deviation level, the blade and tower angle and the corresponding variable pitch rate are adjusted, so as to optimize the control parameters and calculate the optimal control parameters.

[0052] Further, the stall state learning judgment of wind speed-power inputs the running state data and the wind speed-power designed for the wind turbine generator set into the deep learning model, and obtains an importance value through parameter comparison training learning to determine the control instruction of the variable pitch action, and the control instruction of the variable pitch action is optimized in combination with the torque control and yaw control instructions of the wind turbine generator set, and the wind turbine generator set running state control instruction is output, specifically as follows:

[0053] Referring to Figure 3As shown, based on the comparison between the wind turbine design data and the measured operating state data, the power in the measured operating state data uses the frequency converter on-grid data of the wind turbine, when the wind speed is the same, the wind speed-power corresponding relationship deviation value exceeds the deviation level, it proves that the stall problem occurs, when the deviation level is A, it is light stall, the pitch rate is 0.5° / s; when the deviation level is B, it is light stall, the pitch rate is 1° / s; when the deviation level is C, it is light stall, the pitch rate is 2° / s; when the deviation level is D, it is light stall, the pitch rate is 3° / s; when the deviation level is S, it is light stall, the pitch rate is 5° / s, and the propeller standby idling is performed;

[0054] The deviation value of the deviation level is calculated as follows:

[0055]

[0056] When 10%≤deviation value<15%, the deviation level is A; when 15%≤deviation value<20%, the deviation level is B; when 20%≤deviation value<30%, the deviation level is C; when 30%≤deviation value<50%, the deviation level is D; and when deviation value≥50%, the deviation level is S.

[0057] Further, the wind speed-load headroom state learning judgment inputs the operating state data and the wind speed-load of the wind turbine design into a deep learning model, obtains an importance value through parameter comparison training and learning to determine the control instruction of the pitch action, optimizes the processing in combination with the torque control and yaw control instructions of the wind turbine, and outputs the wind turbine operating state control instruction, which is specifically as follows:

[0058] Referring to Figure 4As shown, based on the comparison between the wind turbine generator set design data and the measured operating state data, the load in the measured operating state data uses the independent variable pitch load sensor data of the wind turbine generator set, when the wind speed is the same, if the deviation of the wind speed-load corresponding relationship exceeds the load deviation level, it proves that there is a tower scanning risk; when the load deviation level is A, the load is normal deviation, the variable pitch rate is ±0.1° / s, when the test load> design load, the variable pitch rate is 0.1° / s; when the test load< design load, the variable pitch rate is-0.1° / s; when the load deviation level is B, the load is light deviation, the variable pitch rate is ±0.5° / s, when the test load> design load, the variable pitch rate is 0.5° / s; when the test load< design load, the variable pitch rate is-0.5° / s; when the load deviation level is C, the load is moderate deviation, the variable pitch rate is ±1° / s, when the test load> design load, the variable pitch rate is 1° / s; when the test load< design load, the variable pitch rate is-1° / s; when the load deviation level is D, the load is heavy deviation, the variable pitch rate is ±2° / s, when the test load> design load, the variable pitch rate is 2° / s; when the test load< design load, the variable pitch rate is-2° / s; when the load deviation level is S, the load is extreme deviation, the variable pitch rate is 3° / s, and the wind turbine generator set is parked and idles;

[0059] The deviation of the load deviation level is calculated as follows:

[0060]

[0061] When 5%≤deviation value<10%, the load deviation level is A; when 10%≤deviation value<20%, the load deviation level is B; when 20%≤deviation value<30%, the load deviation level is C; when 30%≤deviation value<50%, the load deviation level is D; and when deviation value≥50%, the load deviation level is S.

[0062] Further, the clearance state learning judgment of the wind shear-independent variable pitch is calculated by the wind speed and wind direction data, when the wind shear<0, it is judged that the wind wheel azimuth angle is parallel to the tower, and the independent variable pitch is realized to realize the advance pitch-in action;

[0063] When the wind shear is less than 0, the azimuth of the wind wheel is determined to be parallel to the blade 5 and the tower 6, and the pre-pitching action is realized by independent pitch control; when the wind shear is between -0.2 and -0.05, the pitch rate is 0.5° / s when the angle between the blade 5 and the tower 6 is 30°; when the wind shear is between -0.4 and -0.2, the pitch rate is 1° / s when the angle between the blade 5 and the tower 6 is 60°; when the wind shear is between -0.6 and -0.4, the pitch rate is 1.5° / s when the angle between the blade 5 and the tower 6 is 90°; when the wind shear is between -1 and -0.6, the pitch rate is 2° / s when the angle between the blade 5 and the tower 6 is 90°; and when the wind shear is greater than -1, the pitch rate is 3° / s when the angle between the blade 5 and the tower 6 is 90°.

[0064] Embodiment 2

[0065] The embodiment discloses an intelligent control method of a wind turbine generator system, which is realized by calling a wind measurement module, an operation state monitoring module and a main control module in the intelligent control system of the wind turbine generator system by a processor.

[0066] Embodiment 3

[0067] The embodiment discloses a non-transitory computer readable medium storing instructions, which, when executed by a processor, perform the steps of the intelligent control method of the wind turbine generator system according to the embodiment 2.

[0068] The non-transitory computer readable medium in the embodiment can be a disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), a U disk, a mobile hard disk or the like.

[0069] Embodiment 4

[0070] The embodiment discloses a computing device, which comprises a processor and a memory for storing a program executable by the processor, and the processor realizes the intelligent control method of the wind turbine generator system according to the embodiment 2 when executing the program stored in the memory.

[0071] The computing device in the embodiment can be a desktop computer, a notebook computer, a smart phone, a PDA handheld terminal, a tablet computer, a programmable logic controller (PLC) or other terminal devices with a processor function.

[0072] The above-described embodiments are only preferred embodiments of the present application, and are not intended to limit the scope of the present application. Any changes made in the shape, principle, and the like of the present application should be included in the scope of the present application.

Claims

1. An intelligent control system for a wind turbine generator set, characterized in that: include: The wind measurement module is installed at the center of the wind turbine hub to obtain wind speed and direction data and transmit them to the main control module; The operation status monitoring module is used to record the operation status data of the wind turbine generator set and transmit the operation status data to the main control module; The main control module uses neural network algorithms and deep learning models to learn the input operating status data, combines wind speed and direction data with preset design data to calculate the optimal control parameters, and controls the wind turbine to perform independent pitch control according to the optimal control parameters, adjusting the stall state and clearance state of the wind turbine during operation; The main control module includes an operation status analysis module and an operation status control module; The operating status analysis module includes: The input operating status data is learned through neural network algorithms and deep learning models, including: learning and judging the stall state of wind speed-power, learning and judging the clearance state of wind speed-load, and learning and judging the clearance state of wind shear-independent pitch; The wind speed-power stall state learning judgment inputs the operating state data and the wind speed-power designed for the wind turbine generator set into a deep learning model, obtains an importance value through parameter comparison training and learning to determine the control instruction of the pitch action, combines it with other preset control instructions of the wind turbine generator set for optimization processing, and outputs the wind turbine generator set operating state control instruction; The wind speed-load clearance state learning judgment inputs the operating state data and the wind speed-load designed for the wind turbine generator set into a deep learning model, obtains an importance value through parameter comparison training and learning to determine the control instruction of the pitch action, combines it with other preset control instructions of the wind turbine generator set for optimization processing, and outputs the wind turbine generator set operating state control instruction; The wind shear-independent pitch control clearance state learning judgment is calculated by wind speed and wind direction data. When the wind shear is less than 0, it is judged that the wind rotor azimuth is parallel to the tower, and the independent pitch control is used to achieve early retraction of the blades. By further updating the deep learning model, correcting the deviation between the design data and the measured data, debugging the deviation level, load deviation level, blade and tower angle, and corresponding propeller rate, the control parameters are optimized and the optimal control parameters are calculated.

2. The intelligent control system for a wind turbine generator set according to claim 1, characterized in that: The wind speed-power stall state learning judgment includes: Based on the comparison between the design data of the wind turbine generator set and the measured operating status data, the power in the measured operating status data adopts the inverter online data of the wind turbine generator set. When the wind speed is the same, after the deviation value of the wind speed-power correspondence exceeds the deviation level, it proves that a stall problem has occurred. When the deviation level is A, it is a mild stall, and the pitch rate is 0.5° / s; when the deviation level is B, it is a mild stall, and the pitch rate is 1° / s; when the deviation level is C, it is a mild stall, and the pitch rate is 2° / s; when the deviation level is D, it is a mild stall, and the pitch rate is 3° / s; when the deviation level is S, it is a mild stall, and the pitch rate is 5° / s for feathering standby idling; The deviation value of the deviation level is calculated as follows: When 10%≤deviation value<15%, the deviation grade is A; when 15%≤deviation value<20%, the deviation grade is B; when 20%≤deviation value<30%, the deviation grade is C; when 30%≤deviation value<50%, the deviation grade is D; when the deviation value ≥50%, the deviation grade is S.

3. The intelligent control system for a wind turbine generator set according to claim 1, characterized in that: The wind speed-load clearance state learning judgment includes: Based on the comparison between the design data of the wind turbine generator set and the measured operating status data, the load in the measured operating status data adopts the independent pitch load sensor data of the wind turbine generator set. When the wind speed is the same, after the deviation of the wind speed-load correspondence exceeds the load deviation level, it proves that there is a tower sweep risk; when the load deviation level is A-load, it is a normal deviation, the pitch rate is ±0.1° / s, when the test load is greater than the design load, the pitch rate is 0.1° / s; when the test load is less than the design load, the pitch rate is -0.1° / s; when the load deviation level is B-load, it is a slight deviation, the pitch rate is ±0.5° / s, when the test load is greater than the design load, the pitch rate is Rate 0.5° / s; when the test load is less than the design load, the pitch rate is -0.5° / s; when the load deviation level is C-load, which is a moderate deviation, the pitch rate is ±1° / s; when the test load is greater than the design load, the pitch rate is 1° / s; when the test load is less than the design load, the pitch rate is 1° / s; when the load deviation level is D-load, which is a severe deviation, the pitch rate is ±2° / s; when the test load is greater than the design load, the pitch rate is 2° / s; when the test load is less than the design load, the pitch rate is 2° / s; when the load deviation level is S-load, which is an extreme deviation, the pitch rate is 3° / s, and the wind turbine is in feathering standby idling; The deviation calculation of the load deviation level is as follows: Deviation value calculation: When 5% ≤ deviation value < 10%, the load deviation level is A-load; when 10% ≤ deviation value < 20%, the load deviation level is B-load; when 20% ≤ deviation value < 30%, the load deviation level is C-load; when 30% ≤ deviation value < 50%, the load deviation level is D-load; when the deviation value ≥ 50%, the load deviation level is S-load.

4. The intelligent control system for a wind turbine generator set according to claim 1, characterized in that: The wind shear-independent pitch control clearance state learning judgment includes: When the wind shear is less than 0 calculated through wind speed and direction data, the rotor azimuth is judged to be parallel to the tower, and the pitch retraction action is realized in advance by independent pitch control; when -0.2<wind shear≤-0.05, when the angle between the blade and the tower is 30°, the pitch retraction is carried out at a rate of 0.5° / s; when -0.4<wind shear≤-0.2, when the angle between the blade and the tower is 60°, the pitch retraction is carried out at a rate of 1° / s; when -0.6<wind shear≤-0.4, when the angle between the blade and the tower is 90°, the pitch retraction is carried out at a rate of 1.5° / s; when -1<wind shear≤-0.6, when the angle between the blade and the tower is 90°, the pitch retraction is carried out at a rate of 2° / s; when wind shear ≥-1, when the angle between the blade and the tower is 90°, the pitch retraction is carried out at a rate of 3° / s.

5. The intelligent control system for a wind turbine generator set according to claim 1, characterized in that: The wind measurement module includes a 3D scanning radar, and the operating status data includes instantaneous wind speed, average wind speed, instantaneous wind direction, average wind direction, generator speed, generator torque, pitch angle, yaw angle, wind wheel azimuth and inverter grid power.

6. A wind turbine generator intelligent control method, characterized in that: The method is implemented by a processor calling a wind measurement module, an operation status monitoring module and a main control module in the intelligent control system of a wind turbine generator set according to any one of claims 1 to 5.

7. A non-transitory computer-readable medium storing instructions, characterized in that: When the instructions are executed by a processor, the wind turbine generator intelligent control method according to claim 6 is executed.

8. A computing device comprising a processor and a memory for storing a program executable by the processor, characterized in that: When the processor executes the program stored in the memory, the wind turbine generator set intelligent control method according to claim 6 is implemented.

Images