Pitch angle compensation method, apparatus, medium, and product for wind turbine blades

Abstract

The present application provides a kind of wind turbine blade pitch angle compensation method, equipment, medium and product, method includes: according to sampling period real-time acquisition generator real-time speed data;According to real-time speed data, calculate real-time speed deviation and real-time speed deviation change rate;According to real-time speed deviation and real-time speed deviation change rate, query optimal compensation variable pitch rate table, find corresponding optimal compensation variable pitch rate;If compensation variable pitch rate is greater than set threshold, then compensation variable pitch rate is converted into compensation pitch angle, trigger wind turbine anti overspeed function, make wind turbine adjust the angle of retraction according to compensation pitch angle.The present application judges whether wind turbine faces the problem of excessive generator speed by current generator real-time speed deviation and real-time speed deviation change rate, gives optimal compensation pitch angle command wind turbine to increase the angle of retraction, which can effectively prevent wind turbine overspeed and keep generator speed stable.

Description

Technical Field

[0001] This invention relates to the field of wind power generation, and in particular to a method, device, medium, and product for compensating the pitch angle of wind turbine blades. Background Technology

[0002] Currently, when wind turbines operate above rated wind speed, they primarily maintain stable generator speed by controlling the pitch angle, ensuring smooth operation and stable power output. Common pitch angle control methods adjust the pitch angle based on the error between the real-time monitored generator speed and the setpoint. However, wind turbines are significantly affected by the external environment, exhibiting strong randomness and uncertainty in operation. Under certain complex terrain or extreme weather conditions, high turbulence and drastic wind speed changes can occur. In such situations, due to the significant inertia of the pitch angle control system, the adjustment of the pitch angle exhibits a lag, potentially causing the generator speed to exceed the control system's safety protection value, triggering overspeed shutdown of the wind turbine. Summary of the Invention

[0003] Based on the above problems, this invention proposes a method, device, medium, and product for compensating the pitch angle of wind turbine blades. This invention solves the problems of existing pitch angle control methods for wind turbines, which suffer from insufficient response to drastic wind speed changes, leading to excessive generator speed fluctuations; difficulty in effectively preventing overspeed shutdown under extreme conditions; potential for large ultimate loads during overspeed shutdown, increasing the risk of damage to the wind turbine; and the limited and simplistic judgment conditions of existing overspeed prevention pitch angle control, which cannot effectively and flexibly cope with complex environments and wind turbine operating conditions. This invention determines whether the wind turbine is facing excessive generator speed by considering both the current real-time generator speed deviation and the rate of change of the real-time speed deviation (i.e., the magnitude of the speed and the rate of increase in speed). It provides an optimal compensation pitch angle command in advance, allowing the wind turbine to increase the pitch angle, effectively preventing overspeed and maintaining stable generator speed.

[0004] This invention proposes a method for compensating the pitch angle of wind turbine blades, comprising:

[0005] Real-time generator speed data is collected according to the sampling period.

[0006] Calculate the real-time speed deviation and the rate of change of the real-time speed deviation based on the real-time speed data;

[0007] The optimal compensation pitch rate is found by consulting the table of optimal compensation pitch rates based on the real-time speed deviation and the rate of change of real-time speed deviation.

[0008] If the compensated pitch rate is greater than the set threshold, the compensated pitch rate will be converted into the compensated pitch angle, triggering the overspeed protection function of the wind turbine, which will then adjust the pitch angle according to the compensated pitch angle.

[0009] Furthermore, the calculation of real-time speed deviation based on real-time speed data includes:

[0010] Formula for calculating speed deviation: E t =(S t -S0) / S0;

[0011] Among them, E t Let S be the rotational speed deviation at time t. t Let S be the rotational speed at time t, and S0 be the rated speed of the generator.

[0012] In addition, the formula for calculating the rate of change of rotational speed deviation is as follows:

[0013] Among them, Edot t Let er be the rate of change of rotational speed deviation at time t. t Let t be the difference between the rotational speed and the rated rotational speed at time t, and T be the sampling interval period.

[0014] Furthermore, the process of establishing the optimal compensation pitch rate table includes:

[0015] Collect historical data on generator speed and pitch angle pitch rate, and calculate the corresponding speed deviation and speed deviation change rate based on the historical speed data;

[0016] Create a scatter plot of rotational speed deviation versus pitch angle pitch rate;

[0017] Establish a scatter plot of the rate of change of rotational speed deviation versus pitch angle pitch rate;

[0018] Based on the scatter plot of speed deviation - pitch angle pitch rate, select multiple speed deviations that meet the conditions as the horizontal header of the table.

[0019] Based on the scatter plot of the speed deviation change rate versus pitch angle pitch rate, select multiple speed deviation change rates that meet the conditions as the vertical column headers.

[0020] The optimal compensation pitch rate is calculated using an improved particle swarm optimization algorithm based on the speed deviation and the rate of change of speed deviation, and then the optimal compensation pitch rate is entered into the optimal compensation pitch rate table.

[0021] Furthermore, the calculation of the optimal compensation pitch rate using an improved particle swarm optimization algorithm based on the speed deviation and the rate of change of speed deviation includes:

[0022] Build neural network models by training with historical data;

[0023] The rotational speed deviation E of the fan at time t t , the rate of change of rotational speed deviation Edot t , and the pitch angle change rate are input into the neural network model, and the E t+1 and Edot t+1 at time t+1 are output as the subsequent optimization targets;

[0024] Taking the minimum values of E t+1 and Edot t+1 at time t+1 as the goal, the improved particle swarm optimization algorithm is used to find the E t , Edot t corresponding optimal compensation pitch rate R t , and the improved particle swarm optimization algorithm introduces system entropy on the basis of the original particle swarm optimization algorithm.

[0025] In addition, the method of querying the optimal compensation pitch rate table according to the real-time rotational speed deviation and the real-time rate of change of rotational speed deviation to find the corresponding optimal compensation pitch rate includes:

[0026] When the optimal compensation pitch rate cannot be directly queried according to the real-time rotational speed deviation and the real-time rate of change of rotational speed deviation, the interpolation look-up table method is used to calculate the corresponding optimal compensation pitch rate,

[0027] Let the current real-time rotational speed deviation be E t (E1 < E t < E2), and the real-time rate of change of rotational speed deviation be Edot t (Edot2 < Edot t < Edot3). The compensation pitch rate R corresponding to the current moment is calculated according to the following formula tt :

[0028]

[0029] where the subscript naming method is: Edot t is the rate of change of rotational speed deviation at time t, E t is the rotational speed deviation at time t, and R 2t is the compensation pitch rate corresponding to Edot2 and E t .

[0030] In addition, the method of converting the compensation pitch rate to the compensation pitch angle includes:

[0031] P t = R t × T

[0032] where P t is the compensation pitch angle at time t, R t is the compensation pitch rate, and T is the sampling interval period.

[0033] The present invention also proposes an electronic device, comprising:

[0034] At least one processor; and,

[0035] A memory communicatively connected to at least one of the processors; wherein,

[0036] The memory stores instructions executable by at least one of the processors, which enable the at least one processor to perform the pitch angle compensation method for wind turbine blades as described in any of the preceding claims.

[0037] The present invention also proposes a storage medium that stores computer instructions, which, when executed by a computer, are used to perform the pitch angle compensation method for wind turbine blades as described in any of the preceding claims.

[0038] The present invention also proposes a computer program product, including a computer program / instruction that, when executed by a processor, implements the pitch angle compensation method for wind turbine blades as described in any of the preceding claims.

[0039] This invention addresses several shortcomings of existing wind turbine control methods that rely on pitch angle control. Firstly, these methods often fail to respond quickly enough to drastic wind speed changes, leading to excessive generator speed fluctuations. Secondly, they struggle to effectively prevent overspeed shutdown under extreme conditions, potentially causing significant ultimate loads and increasing the risk of damage to the wind turbine. Thirdly, existing overspeed prevention methods rely on limited and simplistic pitch angle control criteria, which cannot effectively and flexibly address complex environments and wind turbine operating conditions. This invention determines whether the wind turbine is facing excessive generator speed by analyzing both the real-time generator speed deviation and the rate of change of that deviation (i.e., the magnitude of the speed and the rate of increase in speed). It proactively provides an optimal compensation pitch angle command to increase the pitch angle, effectively preventing overspeed and maintaining stable generator speed. Attached Figure Description

[0040] Figure 1 A flowchart of a method for compensating the pitch angle of wind turbine blades according to an embodiment of the present invention;

[0041] Figure 2 A flowchart illustrating the process of establishing an optimal compensation pitch rate table according to an embodiment of the present invention;

[0042] Figure 3 This is a scatter plot of rotational speed deviation versus pitch angle and pitch rate provided in one embodiment of the present invention.

[0043] Figure 4 A scatter plot of rotational speed deviation versus pitch angle pitch rate provided for another embodiment of the present invention;

[0044] Figure 5 A scatter plot of rotational speed deviation versus pitch angle pitch rate provided for another embodiment of the present invention;

[0045] Figure 6 This is a schematic diagram of the hardware structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0046] The present invention will be further described in detail below with reference to specific embodiments and accompanying drawings. This description is intended only to illustrate specific embodiments of the invention and does not constitute any limitation on the invention. The scope of protection of the invention is defined by the claims.

[0047] Reference Figure 1 This invention proposes a method for compensating the pitch angle of wind turbine blades, comprising:

[0048] In step S001, real-time generator speed data is collected according to the sampling period;

[0049] In step S002, the real-time speed deviation and the rate of change of real-time speed deviation are calculated based on the real-time speed data;

[0050] In step S003, the optimal compensation pitch rate table is queried based on the real-time speed deviation and the real-time speed deviation change rate to find the corresponding optimal compensation pitch rate.

[0051] In step S004, if the compensated pitch rate is greater than the set threshold, the compensated pitch rate is converted into the compensated pitch angle, triggering the overspeed protection function of the wind turbine, so that the wind turbine adjusts the pitch angle according to the compensated pitch angle.

[0052] The main problems with existing control methods for wind turbines that use pitch angle control are:

[0053] 1. The response to drastic changes in wind speed is not fast enough, which can easily cause excessive fluctuations in generator speed.

[0054] 2. It is difficult to effectively prevent overspeed shutdown under extreme operating conditions.

[0055] 3. Overspeed shutdown may generate a large ultimate load, increasing the risk of damage to the wind turbine.

[0056] 4. Existing overspeed prevention pitch angle control judgment conditions are relatively simple and limited, and cannot effectively and flexibly cope with complex environments and wind turbine operating conditions.

[0057] This invention proposes a method for compensating the blade pitch angle of wind turbines, solving the technical problems existing in the prior art. This invention determines whether the wind turbine is facing excessive generator speed by considering both the real-time generator speed deviation and the rate of change of the real-time speed deviation (i.e., the magnitude of the speed and the rate of increase in speed). It provides an optimal compensation pitch angle command in advance, instructing the wind turbine to increase the blade angle, effectively preventing overspeeding and maintaining stable generator speed.

[0058] Compared with existing overspeed control, this invention analyzes the operating status of wind turbines from two aspects: real-time speed deviation and real-time speed deviation change rate (i.e., speed magnitude and speed increase change rate). It has better adaptability and inclusiveness to complex wind turbine operating states. At the same time, it optimizes different compensation pitch angles for different wind turbine operating states to achieve overspeed control, which greatly enhances the control effect and avoids unnecessary or insufficient control.

[0059] In step S001, real-time generator speed data is collected according to the sampling period;

[0060] For example, real-time generator speed data of wind turbines can be collected at a sampling period of 10-20ms. Optionally, pitch angle and pitch rate data can be collected simultaneously for later use.

[0061] In step S002, the real-time speed deviation and the rate of change of real-time speed deviation are calculated based on the real-time speed data;

[0062] Alternatively, the following formula can be used for calculation:

[0063] Formula for calculating speed deviation: E t =(S t -S0) / S0;

[0064] Among them, E t Let S be the rotational speed deviation at time t. t Let S be the rotational speed at time t, and S0 be the rated speed of the generator.

[0065] Formula for calculating the rate of change of rotational speed deviation:

[0066] Among them, Edot t Let er be the rate of change of rotational speed deviation at time t. t Let t be the difference between the rotational speed and the rated rotational speed at time t, and T be the sampling interval period.

[0067] In step S003, the optimal compensation pitch rate table is queried based on the real-time speed deviation and the real-time speed deviation change rate to find the corresponding optimal compensation pitch rate.

[0068] Reference Figure 2 The process of establishing the optimal compensation pitch rate table includes:

[0069] Step S201: Collect historical data of generator speed and pitch angle pitch rate, and calculate the speed deviation and speed deviation change rate corresponding to the speed based on the historical speed data.

[0070] By collecting historical data, the speed deviation and the rate of change of speed deviation are calculated.

[0071] Step S202: Establish a scatter plot of rotational speed deviation versus pitch angle and pitch rate, referring to... Figure 3-5 ;

[0072] Based on the scatter plot of speed deviation versus pitch angle and pitch rate, identify representative points corresponding to the speed deviations to serve as table headers. The selection is based on the density and dispersion of the scatter plot. Dense scatter plots indicate that the turbine frequently operates at that speed deviation; in this case, higher accuracy is required for subsequent table lookups, so multiple points should be selected as table headers in densely packed areas. Points with low density represent infrequent operating conditions or error points; therefore, only a few representative points need to be selected as table headers.

[0073] Step S203: Establish a scatter plot of the rate of change of rotational speed deviation versus pitch angle pitch rate;

[0074] Step S204: Select multiple speed deviations that meet the conditions as the horizontal header of the table based on the scatter plot of speed deviation - pitch angle pitch rate.

[0075] Step S205: Select multiple speed deviation change rates that meet the conditions as the header of the longitudinal table based on the scatter plot of the speed deviation change rate - pitch angle pitch rate.

[0076] Since the speed deviation and the rate of change of speed deviation correspond to the same operating conditions, they have a natural correspondence and do not require additional alignment time.

[0077] Step S206: Calculate the optimal compensation pitch rate using an improved particle swarm optimization algorithm based on the speed deviation and the rate of change of speed deviation, and fill the optimal compensation pitch rate into the optimal compensation pitch rate table.

[0078] The optimal compensation pitch rate is calculated using an improved particle swarm optimization algorithm based on the speed deviation and the rate of change of speed deviation, including:

[0079] Build neural network models by training with historical data;

[0080] The speed deviation E of the fan at time t t Rotational speed deviation change rate Edot tThe pitch angle and pitch rate are input into the neural network model, and the output is E at time t+1. t+1 And Edot t+1 As a target for subsequent optimization;

[0081] At time t+1, E t+1 And Edot t+1 Minimizing the value is the optimization objective; the improved particle swarm optimization algorithm is used to find E at time t. t Edot t The corresponding optimal compensation pitch rate R t The improved particle swarm algorithm introduces system entropy on the basis of the original particle swarm algorithm.

[0082] By incorporating the concept of system entropy into the original particle swarm optimization algorithm, we can better identify and improve the algorithm if it encounters local optima. In the improved algorithm, during the population iteration process, when the number of times a particle stops updating its optimal value exceeds a threshold, an active position update mechanism is implemented. This increases the disorder and system entropy, causing the particle to move in the opposite direction of its historical position vector to re-optimize. This avoids local optima.

[0083] In step S003, by first establishing an optimal compensation pitch rate table and then looking it up when compensation is actually needed, the time to obtain the optimal compensation pitch rate is greatly shortened. If the optimal compensation pitch rate is calculated on-site, the acquisition time will increase, work efficiency will be reduced, and the compensation response will be slower.

[0084] In step S004, if the compensated pitch rate is greater than the set threshold, the compensated pitch rate is converted into the compensated pitch angle, triggering the overspeed protection function of the wind turbine, so that the wind turbine adjusts the pitch angle according to the compensated pitch angle.

[0085] If the compensated pitch rate is ≥1.2 deg / s, the overspeed protection function of the wind turbine is triggered; if it is less than 1.2 deg / s, the function is not triggered, and the compensated pitch rate is set to 0. Here, the threshold value is set to 1.2 deg / s.

[0086] The formula for converting the compensated pitch rate to the compensated pitch angle is:

[0087] P t =R t ×T

[0088] Where P t R is the pitch angle compensated at time t. t To compensate for the pitch rate, T is the sampling interval period.

[0089] In one embodiment, calculating the real-time speed deviation based on real-time speed data includes:

[0090] Formula for calculating speed deviation: E t =(S t -S0) / S0;

[0091] Among them, E t Let S be the rotational speed deviation at time t. t Let S be the rotational speed at time t, and S0 be the rated speed of the generator.

[0092] Calculating the speed deviation prepares for subsequent table lookup.

[0093] In one embodiment, the formula for calculating the rate of change of rotational speed deviation is:

[0094] Among them, Edot t Let er be the rate of change of rotational speed deviation at time t. t Let t be the difference between the rotational speed and the rated rotational speed at time t, and T be the sampling interval period.

[0095] Calculating the rate of change of rotational speed deviation prepares for subsequent table lookup.

[0096] Reference Figure 2 In one embodiment, the process of establishing the optimal compensation pitch rate table includes:

[0097] Step S201: Collect historical data of generator speed and pitch angle pitch rate, and calculate the speed deviation and speed deviation change rate corresponding to the speed based on the historical speed data.

[0098] Step S202: Establish a scatter plot of rotational speed deviation versus pitch angle and pitch rate, referring to... Figure 3-5 ;

[0099] Step S203: Establish a scatter plot of the rate of change of rotational speed deviation versus pitch angle pitch rate;

[0100] Step S204: Select multiple speed deviations that meet the conditions as the horizontal header of the table based on the scatter plot of speed deviation - pitch angle pitch rate.

[0101] Step S205: Select multiple speed deviation change rates that meet the conditions as the header of the longitudinal table based on the scatter plot of the speed deviation change rate - pitch angle pitch rate.

[0102] Since the speed deviation and the rate of change of speed deviation correspond to the same operating conditions, they have a natural correspondence and do not require additional alignment time.

[0103] Step S206: Calculate the optimal compensation pitch rate using an improved particle swarm optimization algorithm based on the speed deviation and the rate of change of speed deviation, and fill the optimal compensation pitch rate into the optimal compensation pitch rate table.

[0104] This process calculates the optimal compensation pitch rate, preparing for real-time compensation of the pitch angle.

[0105] In one embodiment, the step of calculating the optimal compensated pitch rate using an improved particle swarm optimization algorithm based on the speed deviation and the rate of change of the speed deviation includes:

[0106] Build neural network models by training with historical data;

[0107] The speed deviation E of the fan at time t t Rotational speed deviation change rate Edot t The pitch angle and pitch rate are input into the neural network model, and the output is E at time t+1. t+1 And Edot t+1 As a target for subsequent optimization;

[0108] At time t+1, E t+1 And Edot t+1 Minimizing the value is the optimization objective; the improved particle swarm optimization algorithm is used to find E at time t. t Edot t The corresponding optimal compensation pitch rate R t The improved particle swarm algorithm introduces system entropy on the basis of the original particle swarm algorithm.

[0109] By incorporating the concept of system entropy into the original particle swarm optimization algorithm, we can better identify and improve the algorithm if it encounters local optima. In the improved algorithm, during the population iteration process, when the number of times a particle stops updating its optimal value exceeds a threshold, an active position update mechanism is implemented. This increases the disorder and system entropy, causing the particle to move in the opposite direction of its historical position vector to re-optimize. This avoids local optima.

[0110] In the above process, the constructed neural network model first determines the direction of optimization and gives E at time t+1. t+1 And Edot t+1 The optimal value is then found. The improved particle swarm optimization algorithm is used to find the optimal parameters needed at time t to achieve the optimal value, based on the optimal value. Only with the optimal parameters can the optimal value at time t+1 be guaranteed.

[0111] In one embodiment, the step of querying the optimal compensation pitch rate table based on the real-time speed deviation and the rate of change of the real-time speed deviation to find the corresponding optimal compensation pitch rate includes:

[0112] When the optimal compensation pitch rate cannot be directly found based on the real-time speed deviation and the rate of change of the real-time speed deviation, an interpolation lookup table method is used to calculate the corresponding optimal compensation pitch rate.

[0113] Let the current real-time rotational speed deviation be E t (E1 < E t < E2), and the rate of change of the real-time rotational speed deviation be Edot t (Edot2 < Edot t < Edot3), the corresponding compensation pitch rate R at the current moment is obtained according to the following formula tt :

[0114]

[0115] where the subscript naming method is: Edot t is the rate of change of the rotational speed deviation at time t, E t is the rotational speed deviation at time t, R 2t is the compensation pitch rate corresponding to Edot2 and E t correspondingly.

[0116] Since the values in the optimal compensation pitch rate table are obtained by sampling and cannot cover all the values corresponding to the rotational speed deviation and the rate of change of the rotational speed deviation, when the optimal compensation pitch rate cannot be directly queried according to the real-time rotational speed deviation and the real-time rate of change of the rotational speed deviation, the interpolation look-up table method is used to calculate the corresponding optimal compensation pitch rate, thereby obtaining the compensation pitch rate.

[0117] For example, the optimal compensation pitch rate table is shown in the following table:

[0118]

[0119] In one of the embodiments, the conversion of the compensation pitch rate to the compensation pitch angle includes:

[0120] P t = R t × T

[0121] where P t is the compensation pitch angle at time t, R t is the compensation pitch rate, and T is the sampling interval period.

[0122] After obtaining the compensation pitch angle, the pitch angle of the wind turbine can be compensated.

[0123] Referring to Figure 6 , the present invention also proposes a schematic diagram of the hardware structure of an electronic device, including:

[0124] At least one processor 301; and,

[0125] A memory 302 communicatively connected to at least one of the processors 301; wherein,

[0126] The memory 302 stores instructions that can be executed by at least one processor, which enables the at least one processor to perform the pitch angle compensation method for wind turbine blades as described above.

[0127] Figure 6 Take processor 301 as an example.

[0128] The electronic device is preferably a vehicle controller. The electronic device may also include an input device 303 and a display device 304.

[0129] The processor 301, memory 302, input device 303 and display device 304 can be connected by a bus or other means. The figure shows an example of connection by bus.

[0130] The memory 302, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the wind turbine blade pitch angle compensation method in the embodiments of this application, for example, Figure 1 The method flow is shown. The processor 301 executes various functional applications and data processing by running non-volatile software programs, instructions, and modules stored in the memory 302, thereby realizing the blade pitch angle compensation method of the wind turbine in the above embodiment.

[0131] Memory 302 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the wind turbine blade pitch angle compensation method, etc. Furthermore, memory 302 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 302 may optionally include memory remotely located relative to processor 301, and this remote memory may be connected via a network to the apparatus performing the wind turbine blade pitch angle compensation method. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0132] The input device 303 can receive user clicks and generate signal inputs related to user settings and function control of the wind turbine blade pitch angle compensation method. The display device 304 may include a display screen or other display equipment.

[0133] One or more modules are stored in the memory 302, and when run by one or more processors 301, the pitch angle compensation method for wind turbine blades in any of the above method embodiments is executed.

[0134] This invention proposes a method for compensating the pitch angle of wind turbine blades, solving the technical problems existing in the prior art. This invention determines whether the wind turbine is facing excessive generator speed by considering both the real-time generator speed deviation and the rate of change of the real-time speed deviation (i.e., the magnitude of the speed and the rate of increase in speed). It provides an optimal compensation pitch angle command in advance, instructing the wind turbine to increase the pitch angle, effectively preventing overspeeding and maintaining stable generator speed.

[0135] One embodiment of the present invention provides a storage medium that stores computer instructions, which, when executed by a computer, are used to perform all the steps of the pitch angle compensation method for wind turbine blades as described above.

[0136] In the context of this disclosure, a storage medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. The storage medium can be a machine-readable signal medium or a machine-readable storage medium. Optionally, the storage medium can be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), compact disc ROM (CD-ROM), magnetic tape, floppy disk, and optical data storage device.

[0137] This invention proposes a method for compensating the pitch angle of wind turbine blades, solving the technical problems existing in the prior art. This invention determines whether the wind turbine is facing excessive generator speed by considering both the real-time generator speed deviation and the rate of change of the real-time speed deviation (i.e., the magnitude of the speed and the rate of increase in speed). It provides an optimal compensation pitch angle command in advance, instructing the wind turbine to increase the pitch angle, effectively preventing overspeeding and maintaining stable generator speed.

[0138] The above description is merely the principle and preferred embodiment of the present invention. It should be noted that, for those skilled in the art, several other modifications can be made based on the principle of the present invention, and these modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for compensating the pitch angle of wind turbine blades, characterized in that, include: Real-time generator speed data is collected according to the sampling period. Calculate the real-time speed deviation and the rate of change of the real-time speed deviation based on the real-time speed data; The optimal compensation pitch rate is found by consulting the table of optimal compensation pitch rates based on the real-time speed deviation and the rate of change of real-time speed deviation. If the compensated pitch rate is greater than the set threshold, the compensated pitch rate will be converted into the compensated pitch angle, triggering the overspeed protection function of the wind turbine, so that the wind turbine can adjust the pitch angle according to the compensated pitch angle. The process of establishing the optimal compensation pitch rate table includes: Collect historical data on generator speed and pitch angle pitch rate, and calculate the corresponding speed deviation and speed deviation change rate based on the historical speed data; Create a scatter plot of rotational speed deviation versus pitch angle pitch rate; Establish a scatter plot of the rate of change of rotational speed deviation versus pitch angle pitch rate; Based on the scatter plot of speed deviation - pitch angle pitch rate, select multiple speed deviations that meet the conditions as the horizontal header of the table. Based on the scatter plot of the speed deviation change rate versus pitch angle pitch rate, select multiple speed deviation change rates that meet the conditions as the vertical column headers. The optimal compensation pitch rate is calculated using an improved particle swarm optimization algorithm based on the speed deviation and the rate of change of speed deviation, and then the optimal compensation pitch rate is entered into the optimal compensation pitch rate table.

2. The method for compensating the pitch angle of wind turbine blades according to claim 1, characterized in that, The calculation of real-time speed deviation based on real-time speed data includes: Formula for calculating speed deviation: ; in, Let t be the rotational speed deviation. Let be the rotational speed at time t. This is the generator's rated speed.

3. The method for compensating the pitch angle of wind turbine blades according to claim 1, characterized in that, Formula for calculating the rate of change of rotational speed deviation: in, Let be the rate of change of rotational speed deviation at time t. Let t be the difference between the rotational speed and the rated rotational speed at time t, and T be the sampling interval period.

4. The method for compensating the pitch angle of wind turbine blades according to claim 3, characterized in that, The calculation of the optimal compensation pitch rate using an improved particle swarm optimization algorithm based on the speed deviation and the rate of change of speed deviation includes: Build neural network models by training with historical data; The speed deviation of the fan at time t Speed ​​deviation change rate The pitch angle and pitch rate are input into the neural network model, and the output at time t+1 is... and As a target for subsequent optimization; At time t+1 and With the goal of minimizing the value, the improved particle swarm optimization algorithm is used to find the value at time t. , The corresponding optimal compensation pitch rate The improved particle swarm algorithm introduces system entropy on the basis of the original particle swarm algorithm.

5. The method for compensating the pitch angle of wind turbine blades according to claim 1, characterized in that, The step of querying the optimal compensation pitch rate table based on the real-time speed deviation and the rate of change of the real-time speed deviation to find the corresponding optimal compensation pitch rate includes: When the optimal compensation pitch rate cannot be directly found based on the real-time speed deviation and the rate of change of the real-time speed deviation, an interpolation lookup table method is used to calculate the corresponding optimal compensation pitch rate. Let the current real-time speed deviation be... ( The real-time speed deviation change rate is ( The compensated pitch rate at the current moment can be calculated using the following formula. : The naming convention for subscripts is as follows: Let be the rate of change of rotational speed deviation at time t. Let t be the rotational speed deviation. for and The corresponding compensation pitch rate.

6. The method for compensating the pitch angle of wind turbine blades according to claim 1, characterized in that, The step of converting the compensated pitch rate into the compensated pitch angle includes: in The compensation pitch angle at time t, To compensate for pitch rate, The sampling interval period.

7. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to at least one of the processors; wherein, The memory stores instructions executable by at least one of the processors, which enable the at least one processor to perform the pitch angle compensation method for wind turbine blades as described in any one of claims 1 to 6.

8. A storage medium, characterized in that, The storage medium stores computer instructions, which, when executed by the computer, are used to perform the pitch angle compensation method for wind turbine blades as described in any one of claims 1 to 6.

9. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the pitch angle compensation method for wind turbine blades as described in any one of claims 1 to 6.

Images