WO2019127974A1

WO2019127974A1 - Method and apparatus for optimizing loads of wind turbine

Info

Publication number: WO2019127974A1
Application number: PCT/CN2018/082347
Authority: WO
Inventors: 马羽龙; 彭柳; 赵树椿
Original assignee: 新疆金风科技股份有限公司
Priority date: 2017-12-25
Filing date: 2018-04-09
Publication date: 2019-07-04
Also published as: CN109962493A

Abstract

A method for optimizing the loads of a wind turbine, comprising: obtaining at least one control parameter of a wind turbine; obtaining load values at multiple positions of the wind turbine; quantifying the load values at the multiple positions into individual assessment values; determining whether the assessment values satisfy a predetermined condition; if the assessment values do not satisfy the predetermined condition, optimizing the at least one control parameter by using a predetermined optimization algorithm; and if the assessment values satisfy the predetermined condition, using the at least one control parameter as a final control parameter. By using the method and apparatus, multiple loads of a wind turbine can be quantified, and on the basis of quantified values, the controller parameters of the wind turbine are optimized by using an optimization algorithm, to obtain an optimized load result.

Description

Method and apparatus for optimizing the load of a wind turbine

Technical field

The present application relates generally to the field of wind power generation technology and, more particularly, to a method and apparatus for optimizing the load of a wind turbine.

Background technique

The design of a wind turbine is usually started from the load calculation. To do this, it is necessary to establish a mathematical model of the wind turbine and determine the control strategy. The adjustment of the parameters related to the control strategy will obviously affect the results of the load calculation.

In the design stage, because the wind turbine is a complex system, the designer adjusts the parameters of the controller model for a certain load index, which may cause unpredictable fluctuations of other multiple load indicators, so it is difficult to get relatively convenient and convenient. Parameters.

Summary of the invention

According to an aspect of an embodiment of the present application, a method for optimizing a load of a wind power generator is provided, the method comprising the steps of: acquiring at least one control parameter of a wind power generator, wherein the plurality of wind power generator sets The load of the position is affected by the at least one control parameter; acquiring a load value of the plurality of positions of the wind turbine set corresponding to the at least one control parameter; loading the plurality of positions using a predetermined evaluation model The value is quantized into a single evaluation value; determining whether the evaluation value satisfies a predetermined condition; when the evaluation value does not satisfy the predetermined condition, the predetermined optimization algorithm is used to optimize the at least one control parameter based on the evaluation value to update the at least one control parameter, And performing the step of acquiring at least one control parameter of the wind power generator again, wherein the optimization problem of optimizing the control parameter is such that the evaluation value corresponding to the updated control parameter satisfies a predetermined condition; when the evaluation value satisfies the predetermined condition Determining the acquired at least one control parameter as a final System parameters.

According to another aspect of an embodiment of the present application, there is provided an apparatus for optimizing a load of a wind power generator, the apparatus comprising: a control parameter acquisition module that acquires at least one control parameter of a wind power generator, wherein the wind power generation The load of the plurality of positions of the unit is affected by the at least one control parameter; the load acquisition module acquires a load value of the plurality of positions of the wind power generator corresponding to the at least one control parameter; a load quantization module, The load value of the plurality of locations is quantized into a single evaluation value using a predetermined evaluation model; the evaluation value judging module judges whether the evaluation value satisfies a predetermined condition; and the control parameter update module uses a predetermined optimization algorithm when the evaluation value does not satisfy the predetermined condition Updating the at least one control parameter based on the evaluation value to update the at least one control parameter, and the control parameter obtaining module acquires the at least one control parameter again, wherein the optimization problem of optimizing the control parameter is such that after updating The evaluation value corresponding to the control parameter satisfies the predetermined a condition; a control parameter providing module that provides the acquired at least one control parameter as a final control parameter when the evaluation value satisfies a predetermined condition.

According to another aspect of an embodiment of the present application, there is provided a computer readable storage medium storing a computer program that, when executed by a processor, implements the method for optimizing a load of a wind turbine.

According to another aspect of an embodiment of the present application, there is provided a control system for a wind power generator set, the control system comprising: a processor; a memory storing a computer program, when the computer program is executed by the processor, implementing the above A method for optimizing the load of a wind turbine.

The method and apparatus for optimizing the load of a wind power generator according to an embodiment of the present application can quantify multiple loads of the wind power generator and optimize the parameters of the wind turbine generator controller model based on the quantized values using an optimization algorithm. To help get optimized load results.

DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings to be used in the embodiments of the present application will be briefly described below.

1 shows a flow chart of a method for optimizing a load of a wind power plant according to an embodiment of the present application;

2 is a block diagram showing the structure of an apparatus for optimizing the load of a wind power generator according to an embodiment of the present application.

Detailed ways

1 shows a flow chart of a method for optimizing the load of a wind turbine according to an embodiment of the present application.

Referring to FIG. 1, in step S10, at least one control parameter of the wind turbine may be acquired, and loads of the plurality of locations of the wind turbine are affected by the at least one control parameter. According to one embodiment, control parameters affecting the loads of the plurality of locations of the wind turbine and related to the control strategy of the wind turbine may be obtained as at least one control parameter. As an example, a control parameter of a predetermined controller model of the wind turbine may be obtained as at least one control parameter. It should be noted that when the control parameter of the predetermined controller model is acquired as the at least one control parameter, the acquired at least one control parameter may be a control parameter of the same controller model, or may be a control parameter of different multiple controller models. This application does not limit this. As an example, for a particular load optimization, the predetermined controller model may be a pitch controller model, a torque controller model, or a filter model. The optimization may take into account multiple loads among the fatigue load and the ultimate load at various locations of the wind turbine. For example, the load at a plurality of positions may include a fatigue load of a bending moment Mx in a first direction of the bottom of the tower, a fatigue load of a bending moment My in the second direction of the bottom of the tower, and a fatigue load of a bending moment My in the second direction of the blade root. The ultimate load of the bending moment My in the second direction of the tower bottom and the ultimate load of the bending moment My in the second direction of the blade root. It should be understood that the loads at multiple locations may be two or more of the above loads, as well as other types of loads.

In some embodiments of the present application, the predetermined controller model may be a pitch controller model for the above loads. For example, the control parameters of the pitch controller model can be KPPS and KIPS. However, this is merely an example, and the application is not limited thereto.

In step S10, preferably, acquiring the control parameter may refer to acquiring the current value of the control parameter. As an example, any value within the range of values of the control parameter can be obtained as the current value. As an example, the range of values of the control parameters can be set in advance according to experience.

In some embodiments of the present application, the method illustrated in FIG. 1 may also include the step of initializing at least one control parameter. As an example, a control parameter of a predetermined controller model may be initialized, and an initialization value of the control parameter may be acquired as a current value.

In step S20, load values of a plurality of locations of the wind turbine set corresponding to at least one control parameter may be acquired.

As described above, the load at a plurality of positions in one embodiment of the present application may be the fatigue load of the bottom Mx, the fatigue load of the bottom My, the fatigue load of the blade root My, the ultimate load of the bottom My, and the limit of the blade root My. Load. As an example, the overall model of the wind turbine may be simulated based on the current value of the acquired control parameters to obtain the plurality of load values corresponding to the control parameters.

In some embodiments of the present application, the whole machine model of the wind power generator is simulated based on the acquired at least one control parameter, and the value of the predetermined operating parameter of the wind power generator set is also obtained. This will be described in more detail below.

In step S30, the plurality of load values are quantized into a single evaluation value using a predetermined evaluation model.

Based on the purpose of optimizing the load, a plurality of load values may be quantized to an evaluation value associated with the minimum load using a predetermined evaluation model to perform subsequent optimization based thereon. For example, the predetermined evaluation model may be various functions capable of implementing the evaluation function of an embodiment, and the quantized evaluation value is a value of the function. For example, the predetermined evaluation model may be a fitness function. As an example, the predetermined evaluation model may be the product of the sum of the plurality of loads (eg, the accumulated value) and the constraint value. As another example, the predetermined evaluation model may be a product of a weighted sum (eg, an accumulated weighting value) of the plurality of loads respectively weighted and a constraint value. For example, respective weights may be applied to a plurality of loads in the evaluation model according to different degrees of attention to the plurality of loads, and different weights may be applied to the plurality of loads in consideration of different magnitudes between the plurality of loads, but the application is not limited thereto. this.

The constraint values as described above may reflect constraints for predetermined operational parameters that need to be met for normal operation of the wind turbine. Preferably, the constraint value can be determined based on constraints required for the predetermined operational parameters to be met by the normal operation of the wind turbine.

As an example, the predetermined operational parameter may include at least one of a generator rotational speed and a cabin vibration acceleration, but the application is not limited thereto. For example, the constraints described above may include the generator speed being within a predetermined range of generator speeds and the cabin vibration acceleration being within a predetermined range of cabin vibration acceleration.

As described above, the value of the predetermined operational parameter can be obtained by simulation based on the current value of the acquired at least one control parameter in step S20. Therefore, the constraint value can be determined by judging whether the value of the predetermined operational parameter obtained by the simulation satisfies the above constraint condition.

In some embodiments of the present application, the determining the constraint value according to the constraint condition for the predetermined operational parameter that is required to be met by the normal operation of the wind power generator may include: setting the constraint value to a predetermined value when the predetermined operational parameter satisfies the constraint condition; When the predetermined operational parameter does not satisfy the constraint, the constraint value is set to a value greater than the predetermined value. For example, the predetermined value can be set in advance. Here, when the predetermined operating parameter does not satisfy the constraint condition (ie, the predetermined operating parameter has an abnormality), the constraint value may be determined to be greater than the predetermined value according to the degree to which the abnormality of the predetermined operating parameter can be accepted (or the magnitude of the abnormality). degree.

For example, when the generator rotational speed obtained by simulation according to the current value of the control parameter exceeds a predetermined range of the generator rotational speed, the constraint value may be set to a value greater than a predetermined value, thereby increasing the sum of the load values as the quantized evaluation values. The product of the constraint value. However, this is merely an example, and the case where the predetermined control parameter of the present application does not satisfy the constraint and the setting of the constraint value are not limited thereto.

In step S40, it is judged whether or not the evaluation value satisfies the predetermined condition.

When the evaluation value does not satisfy the predetermined condition, in step S50, the control parameter is updated based on the evaluation value to update the control parameter using the predetermined optimization algorithm, and returns to step S10 to acquire the control parameter again. Here, the optimization problem of optimizing the control parameters is such that the evaluation value corresponding to the updated control parameter (that is, the evaluation value obtained by the steps S20 and S30 for the updated control parameter) satisfies the predetermined condition.

In some embodiments of the present application, the predetermined condition may mean that the evaluation value reaches a minimum value. For example, the predetermined condition may mean that the evaluation value corresponding to the acquired at least one control parameter reaches a minimum value. Preferably, when the obtained at least one control parameter is less than a predetermined threshold from the previous one (ie, when the step S10 is performed in the last iteration of the current method), the evaluation value may be determined to be reached. Minimum value.

The control parameters can be optimized based on the quantized evaluation values to update the control parameters using various existing optimization algorithms. For example, the optimization algorithm used may be a genetic algorithm or a simplex method, but the application is not limited thereto.

For example, when the quantized evaluation value does not satisfy the predetermined condition (that is, the quantized evaluation value does not reach the minimum value), in step S50, in the predetermined optimization algorithm, the evaluation value corresponding to the acquired at least one control parameter may be The minimum values of all the previous evaluation values are compared, and based on the comparison result, according to the correspondence relationship between the evaluation values and the control parameters, the optimization direction and the amplitude at which the control parameters are to be adjusted next are determined, thereby updating the control parameters. Then, returning to step S10, the at least one control parameter is acquired again.

It should be noted that the number of predetermined thresholds may be set for the number of the at least one control parameter. For example, the difference between the first control parameters (eg, KPPS) acquired twice before and after may be referred to as a first difference, and the difference between the second control parameters (eg, KIPS) acquired twice before and after may be referred to as a second difference. As an example, a first predetermined threshold and a second predetermined threshold may be set for the first difference and the second difference, respectively. As another example, the same predetermined threshold may be set for the first difference and the second difference. It should be understood that the number of control parameters and predetermined thresholds is not limited thereto.

In step S60, when the evaluation value satisfies the predetermined condition, the acquired at least one control parameter is taken as the final control parameter.

For example, when it is determined in step S40 that the evaluation value reaches the minimum value (that is, the difference between the control parameters acquired twice before and after is less than a predetermined threshold), it indicates that the at least one control parameter acquired this time may be considered as the final result of the optimization result. The control parameters can be used in the design, simulation and actual operation of subsequent wind turbines to conveniently and efficiently optimize the corresponding loads.

Table 1 shows an example of comparing the loads of the above-described plurality of positions before and after the method as described in FIG. 1 and the values of the control parameters.

Table 1

It can be seen from Table 1 that, for the loads of the above multiple positions, the optimization algorithm is used to update the control parameters of the pitch controller model, so that the fatigue load of the bottom Mx, the fatigue load of the bottom of the tower My, the fatigue load of the blade root My, The ultimate load of the bottom of My Tower has been reduced to some extent. Although the ultimate load of the blade root My is slightly higher than that before the optimization, the load of the wind turbine is generally optimized from the system point of view.

As shown in FIG. 2, the apparatus for optimizing the load of a wind power generator according to an embodiment of the present application includes: a control parameter acquisition module 10, a load acquisition module 20, a load quantization module 30, an evaluation value judgment module 40, and a control parameter update module. 50 and control parameter providing module 60.

The control parameter obtaining module 10 acquires at least one control parameter of the wind power generator set, and the loads of the plurality of positions of the wind power generator set are affected by the at least one control parameter. In some embodiments of the present application, control parameters related to the control strategy of the wind turbine (ie, for setting the control strategy) may be obtained as at least one control parameter. As an example, a control parameter of a predetermined controller model of the wind turbine may be obtained as at least one control parameter. Here, the control parameter of the predetermined controller model is a control parameter of the wind turbine associated with a plurality of loads of the wind turbine, the plurality of loads being affected by the control parameter. It should be noted that when the control parameter obtaining module 10 acquires the control parameter of the predetermined controller model as the at least one control parameter, the acquired at least one control parameter may be the control parameter of the same controller model, or may be different controllers. The control parameters of the model are not limited in this application.

As an example, for a particular load optimization, the predetermined controller model may be a pitch controller model, a torque controller model, or a filter model.

In some embodiments of the present application, the control parameter acquisition module 10 may obtain the current value of the control parameter. As an example, the control parameter acquisition module 10 may obtain any value within the range of values of the control parameter as the current value.

In some embodiments of the present application, the apparatus may further include an initialization module (not shown) for initializing the at least one control parameter. For example, the initialization module can initialize control parameters of a predetermined controller model. As an example, the control parameter acquisition module may obtain an initialization value of the control parameter as the current value.

In some embodiments of the present application, the load acquisition module 20 may acquire load values for a plurality of locations of the wind turbine set corresponding to the at least one control parameter. As an example, the load acquisition module 20 may simulate a complete machine model of the wind turbine based on the current value of the acquired at least one control parameter, thereby obtaining load values for the plurality of locations corresponding to the at least one control parameter.

In some embodiments of the present application, the load acquisition module 20 may also simulate the overall model of the wind turbine based on the acquired at least one control parameter to obtain a value of a predetermined operational parameter of the wind turbine.

In some embodiments of the present application, the load quantification module 30 quantizes the plurality of load values into a single evaluation value using a predetermined evaluation model.

Based on the purpose of optimizing the load, the load quantification module 30 may quantize the plurality of load values into one of the evaluation values associated with the minimum load using a predetermined evaluation model to perform subsequent optimizations based thereon. For example, the predetermined evaluation model may be various functions capable of implementing the evaluation function in some embodiments of the present application, and the quantized evaluation value is a value of the function. For example, the predetermined evaluation model may be a fitness function. As an example, the predetermined evaluation model may be the product of the sum of the plurality of loads (eg, the accumulated value) and the constraint value. As another example, the predetermined evaluation model may be a product of a weighted sum (eg, an accumulated weighting value) of the plurality of loads respectively weighted to the constraint value. For example, the load quantification module 30 may apply respective weights to a plurality of loads in the evaluation model according to different degrees of attention to the plurality of loads, and may also apply respective weights to the plurality of loads in consideration of different magnitudes between the plurality of loads, but This application is not limited to this.

The constraint values as described above may reflect constraints for predetermined operational parameters that need to be met for normal operation of the wind turbine. Preferably, the load quantification module 30 may determine the constraint value based on constraints for the predetermined operational parameters that need to be met for normal operation of the wind turbine.

As described above, the value of the predetermined operational parameter of the wind turbine can be simulated by the load acquisition module 20 based on the acquired at least one control parameter. Therefore, the constraint value can be determined by the load quantization module 30 by determining whether the value of the simulated predetermined operational parameter satisfies the above constraint.

In some embodiments of the present application, the step of determining the constraint value by the load quantification module 30 may include: when the predetermined operational parameter satisfies the constraint condition, the load quantization module 30 sets the constraint value to a predetermined value; when the predetermined operational parameter does not satisfy the constraint condition The load quantization module 30 sets the constraint value to a value greater than a predetermined value. For example, the predetermined value may be preset by the load quantization module 30. Here, when the predetermined operational parameter does not satisfy the constraint condition (ie, there is an abnormality in the predetermined operational parameter), the load quantization module 30 may determine the constraint value according to the degree to which the abnormality of the predetermined operational parameter can be accepted (or the magnitude of the abnormality). A degree greater than a predetermined value.

For example, when the load quantification module 30 determines that the generator rotational speed obtained by simulation according to the current value of the control parameter exceeds a predetermined range of the generator rotational speed, the load quantization module 30 may set the constraint value to a value greater than a predetermined value, thereby increasing the The product of the weighted value of the quantized evaluation value and the product of the constraint value. However, this is merely an example, and the application is not limited thereto.

In some embodiments of the present application, the evaluation value determination module 40 determines whether the evaluation value satisfies a predetermined condition.

In some embodiments of the present application, when the evaluation value does not satisfy the predetermined condition, the control parameter update module 50 updates the control parameter based on the evaluation value to update the control parameter using a predetermined optimization algorithm, and the control parameter acquisition module 10 acquires the control parameter again. . Here, the optimization problem of optimizing the control parameters is such that the evaluation value corresponding to the updated control parameter satisfies a predetermined condition.

In some embodiments of the present application, the predetermined condition may mean that the evaluation value reaches a minimum value. For example, the predetermined condition may mean that the evaluation value quantized by the load quantization module 30 corresponding to the at least one control parameter acquired by the control parameter acquisition module 10 reaches a minimum value. Preferably, when the difference between the at least one control parameter acquired by the control parameter obtaining module 10 and the at least one control parameter acquired previously is less than a predetermined threshold, the evaluation value determining module 40 may determine that the evaluation value reaches a minimum value.

The control parameter update module 50 may optimize the control parameters based on the quantized evaluation values using existing various optimization algorithms to update the control parameters. For example, the optimization algorithm used by the control parameter update module 50 may be a genetic algorithm or a simplex method, but the application is not limited thereto.

For example, when the evaluation value quantized by the load quantization module 30 does not satisfy the predetermined condition (ie, the quantized evaluation value does not reach the minimum value), the control parameter update module 50 may select at least one acquired by the control parameter acquisition module 10 in the predetermined optimization algorithm. The evaluation value quantized by the load quantization module 30 corresponding to the control parameter is compared with the minimum value of all the previous evaluation values, and based on the comparison result, according to the correspondence relationship between the evaluation value and the control parameter, it is determined that the control parameter is next The direction and magnitude of the adjustment are optimized to update the control parameters. Then, again, the control parameter acquisition module 10 acquires the at least one control parameter, the load acquisition module 20 acquires the load values of the plurality of locations corresponding to the at least one control parameter, and the load quantization module 30 uses the predetermined evaluation model to the plurality of locations. The load value of the position is quantized into a single evaluation value, and the evaluation value judging module 40 judges whether the evaluation value satisfies a predetermined condition. When the evaluation value does not satisfy the predetermined condition, the control parameter update module 50 uses the predetermined optimization algorithm to calculate the at least one control parameter based on the evaluation value. optimize.

It should be noted that the evaluation value judging module 40 may set the number of predetermined thresholds for the number of the at least one control parameter. For example, the difference between the first control parameters acquired twice before and after may be referred to as the first difference, and the difference between the second control parameters acquired twice before and after may be referred to as the second difference. As an example, a first predetermined threshold and a second predetermined threshold may be set for the first difference and the second difference, respectively. As another example, the same predetermined threshold may be set for the first difference and the second difference. It should be understood that the number of control parameters and predetermined thresholds is not limited thereto.

In some embodiments of the present application, when the evaluation value judging module 40 judges that the evaluation value satisfies the predetermined condition, the control parameter providing module 60 provides at least one control parameter acquired by the control parameter obtaining module 10 as the final control parameter.

For example, when the evaluation value judging module 40 judges that the evaluation value reaches the minimum value (that is, the difference between the control parameters acquired twice before and after the control parameter acquisition module 10 is less than a predetermined threshold), it indicates that the at least one control parameter acquired this time can be considered as It is the final control parameter as an optimization result. At this time, the control parameter providing module 60 can provide the control parameters for design, simulation, and actual operation of the subsequent wind turbine to conveniently and efficiently optimize the corresponding load.

Embodiments of the present application also provide a control system. The control system includes a processor and a memory. The memory is used to store computer programs. The computer program is executed by a processor such that the processor executes a computer program for the method of optimizing the load of the wind turbine as described above.

Embodiments of the present application also provide a computer readable storage medium storing a computer program. The computer readable storage medium stores a computer program that, when executed by a processor, causes the processor to perform the method described above for optimizing the load of the wind turbine. The computer readable recording medium is any data storage device that can store data read by a computer system. Examples of the computer readable recording medium include read only memory, random access memory, read-only optical disk, magnetic tape, floppy disk, optical data storage device, and carrier wave (such as data transmission via the Internet via a wired or wireless transmission path).

The above method and apparatus for optimizing the load of a wind power generator using the embodiment of the present application can automatically update the control parameters based on the controller model of the wind turbine using an optimization algorithm, instead of based on the overall model of the wind turbine The linearized data analyzes the time domain and frequency domain and manually adjusts the control parameters, thereby greatly saving labor and resource costs in the design process of the wind turbine.

The above method and apparatus for optimizing the load of the wind power generator according to the embodiment of the present application can flexibly select a plurality of optimization algorithms, and the method and the device can be extended not only to the load but also to the power generation amount, the power curve, and the like. Optimization of various indicators and update of related control parameters.

While the present invention has been particularly shown and described with respect to the embodiments of the present invention, it will be understood by those skilled in the art Various changes.

Claims

A method for optimizing a load of a wind turbine, the method comprising the steps of:

Obtaining at least one control parameter of the wind turbine, wherein loads of the plurality of locations of the wind turbine are affected by the at least one control parameter;

Obtaining a load value of the plurality of locations of the wind turbine set corresponding to the at least one control parameter;

The load values of the plurality of locations are quantized into a single evaluation value using a predetermined evaluation model;

Determining whether the evaluation value satisfies a predetermined condition;

When the evaluation value does not satisfy the predetermined condition, the predetermined optimization algorithm is used, the at least one control parameter is optimized based on the evaluation value to update the at least one control parameter, and the acquiring at least one control parameter of the wind power generator is performed again step;

When the evaluation value satisfies a predetermined condition, the acquired at least one control parameter is taken as a final control parameter.
The method of claim 1 wherein said predetermined evaluation model is a fitness function.
The method of claim 1 wherein obtaining a load value for a plurality of locations of said wind turbine set corresponding to said at least one control parameter comprises: said said at least one control parameter based on said acquired The overall model of the wind turbine is simulated to obtain the load values of the plurality of locations and the values of the predetermined operational parameters of the wind turbine.
The method according to claim 3, wherein said predetermined evaluation model is a weighted sum and constraint of a product of a sum of load values of said plurality of positions and a value of a constraint value or a load value of said plurality of positions, respectively The product of the values.
The method of claim 4 wherein the constraint value is determined based on constraints required for predetermined operational parameters to be met by said wind turbine for normal operation.
The method of claim 5 wherein the step of determining the constraint value comprises:

When the predetermined operating parameter satisfies the constraint condition, the constraint value is set to a predetermined value;

When the predetermined operational parameter does not satisfy the constraint, the constraint value is set to a value greater than the predetermined value.
The method according to claim 1, wherein the predetermined condition means that the evaluation value reaches a minimum value.
The method of claim 7, wherein the evaluation value is determined to be at a minimum when a difference between the acquired at least one control parameter and the previously acquired at least one control parameter is less than a predetermined threshold.
The method of claim 6 wherein the predetermined operational parameter comprises at least one of a generator speed and a cabin vibration acceleration.
The method according to claim 1, wherein the load of the plurality of positions comprises a fatigue load of a bending moment of a first direction of the bottom of the tower, a fatigue load of a bending moment of a second direction of the tower bottom, and a second load of the blade root Two or more of the fatigue load of the direction bending moment, the ultimate load of the bending moment of the second direction of the tower bottom, and the ultimate load of the bending moment of the blade root in the second direction.
A device for optimizing the load of a wind turbine, the device comprising:

Controlling a parameter acquisition module, acquiring at least one control parameter of the wind power generator, wherein a load of the plurality of positions of the wind power generator is affected by the at least one control parameter;

a load acquisition module acquiring a load value of the plurality of locations of the wind power generator corresponding to the at least one control parameter;

a load quantification module that quantizes load values of the plurality of locations into a single evaluation value using a predetermined evaluation model;

The evaluation value judging module judges whether the evaluation value satisfies a predetermined condition;

Controlling a parameter update module, when the evaluation value does not satisfy the predetermined condition, using a predetermined optimization algorithm, optimizing the at least one control parameter based on the evaluation value to update the at least one control parameter, and the control parameter acquisition module acquiring the at least a control parameter;

The control parameter providing module provides the acquired at least one control parameter as a final control parameter when the evaluation value satisfies a predetermined condition.
The apparatus of claim 11 wherein said predetermined evaluation model is a fitness function.
The apparatus according to claim 11, wherein the load acquisition module simulates the whole machine model of the wind power generator based on the acquired at least one control parameter to obtain load values of the plurality of positions and the wind power generation The value of the scheduled operating parameters of the unit.
The apparatus according to claim 13, wherein said predetermined evaluation model is a weighted sum and constraint of a product of a sum of load values of said plurality of positions and a value of said constraint value or a load value of said plurality of positions, respectively The product of the values.
The apparatus of claim 14 wherein the load quantification module determines the constraint value based on constraints required for the predetermined operational parameter to be satisfied by the normal operation of the wind turbine.
The device according to claim 15, wherein

The load quantification module sets the constraint value to a predetermined value when the predetermined operational parameter satisfies the constraint condition;

The load quantization module sets the constraint value to a value greater than a predetermined value when the predetermined operational parameter does not satisfy the constraint.
The apparatus according to claim 11, wherein the predetermined condition means that the evaluation value reaches a minimum value.
The apparatus according to claim 17, wherein the evaluation value judging module determines that the evaluation value reaches a minimum value when a difference between the acquired at least one control parameter and the at least one control parameter acquired last time is less than a predetermined threshold value .
The apparatus of claim 16 wherein the predetermined operating parameter comprises at least one of a generator speed and a cabin vibration acceleration.
The apparatus according to claim 11, wherein the load of the plurality of positions comprises a fatigue load of a bending moment of a first direction of the tower bottom, a fatigue load of a bending moment of a second direction of the tower bottom, and a second root of the blade root Two or more of the fatigue load of the direction bending moment, the ultimate load of the bending moment of the second direction of the tower bottom, and the ultimate load of the bending moment of the blade root in the second direction.
A computer readable storage medium storing a computer program that, when executed by a processor, implements the method for optimizing a load of a wind turbine set according to any one of claims 1 to 10.
A control system for a wind power generator, the control system comprising:

processor;

The memory, stored with a computer program, when the computer program is executed by the processor, implements the method for optimizing the load of the wind turbine set according to any one of claims 1 to 10.