Power optimization method and system for inhibiting load of transmission system of wind turbine generator

Abstract

The invention discloses a power optimization method and system for inhibiting the load of a transmission system of a wind turbine generator, and the method comprises the steps: S1, obtaining the operation parameters of each wind turbine generator, and building a state-space equation of the wind turbine generator; s2, taking an electric power demand instruction as a boundary condition, taking upper and lower limits of active power output of a wind turbine generator and angular velocity and torsional torque of a transmission system as constraint conditions, and taking minimization of variable quantities of angular acceleration and torsional torque of the transmission system as a target function; solving an active power reference value of each wind turbine generator based on the wind turbine generator state-space equation; and S3, measuring the fatigue degree of the transmission system according to the historical operation data of each wind turbine generator set, calculating the corresponding weight according to the fatigue degree, and correcting the active power reference value according to the weight as a final active power instruction. Torsional vibration can be effectively restrained, fatigue damage of a transmission system is improved, and the safety and stability of grid-connected operation of the wind turbine generator are improved.

Description

Technical Field

[0001] The present invention mainly relates to the technical field of wind power generation, and particularly relates to a power optimization method and system for suppressing the load of a wind turbine drive system. Background Art

[0002] With the continuous growth of the global demand for clean energy, wind power generation, as an important way of renewable energy generation, is expanding rapidly. However, the safety and stability of wind turbines connected to the grid are facing increasingly severe challenges. As a key component for electromechanical energy conversion, the performance of the wind turbine drive system directly affects the operating efficiency and reliability of the wind turbine. Under harsh natural environments and time-varying operating conditions, the drive system is simultaneously subjected to the disturbance impacts of mechanical torque and electromagnetic torque, which will not only cause fatigue damage to the drive system, but may also trigger faults, thereby affecting the safety and stability of the wind turbine connected to the grid.

[0003] Currently, some measures have been taken in the industry to address the fatigue damage problem of the wind turbine drive system. For example, some wind turbines adopt complex drive chain structures and improve the drive efficiency and load-bearing capacity through multi-stage gear transmission. In addition, some technologies have tried to improve the reliability and anti-fatigue performance of the system by optimizing the structural design of the drive system, such as using short main shafts and compact designs. At the same time, some research has also analyzed the load transfer characteristics by establishing a rigid-flexible coupling dynamics model of the main drive system in order to find the basis for optimized design.

[0004] Although the existing technical solutions have improved the performance of the wind turbine drive system to a certain extent, there are still some deficiencies. First, although the complex drive chain structure can improve the drive efficiency, it also increases the complexity and failure risk of the system, especially in harsh operating environments. Second, most of the existing optimization design methods are based on static analysis and it is difficult to comprehensively consider the torque disturbance and fatigue damage during dynamic operation. In addition, most of the existing technical solutions focus on the structural optimization of the drive system, and there is insufficient research on the torsional vibration suppression strategy under the characteristics of machine-grid interaction, and the stability problem of the drive system during grid connection operation cannot be fundamentally solved. Summary of the Invention

[0005] Aiming at the technical problems existing in the prior art, the present invention provides a power optimization method and system for suppressing the load of a wind turbine drive system, which can effectively suppress torsional vibration, improve the fatigue damage of the drive system, and thus improve the safety and stability of the wind turbine connected to the grid.

[0006] To solve the above technical problems, the technical solution proposed by the present invention is as follows: A power optimization method for suppressing the load of a wind turbine drive system, comprising the steps of: S1. Obtain the operating parameters of each wind turbine and establish the state - space equation of the wind turbine; S2. Using the power demand instruction of the dispatching center as the boundary condition, taking the upper and lower limits of the active power output of the wind turbine, the angular velocity and torsional torque of the drive train as the constraint conditions, and minimizing the angular acceleration and change in torsional torque of the drive train as the objective function, solve the reference value of the active power of each wind turbine based on the state - space equation of the wind turbine; S3. Measure the fatigue degree of the drive train according to the historical operation data of each wind turbine, calculate the corresponding weight according to the fatigue degree of the drive train, and then correct the reference value of the active power according to the weight, and send it as the final active power instruction to each wind turbine.

[0007] Preferably, in step S1, the state - space equation of the wind turbine includes the dynamic equation of the wind turbine drive train and the power - torque state - space equation of the wind turbine; the establishment process of the dynamic equation of the wind turbine drive train is as follows: Model the generator as a mass block related to the mechanical inertia of the generator rotor, which are respectively the flexible blade mass block, the rigid blade - hub mass block and the generator mass block; among them, the flexible blade mass block concentrates the inertia of the flexible part of the blade; the rigid blade - hub mass block concentrates the inertia of the rigid part of the blade and the hub; the generator mass block concentrates the inertia of the generator; the stiffness and damping of the effective blade connect the flexible blade mass block and the rigid blade - hub mass block, and the total stiffness and damping of the low - speed shaft and the high - speed shaft connect the rigid blade - hub mass block and the generator mass block; the dynamic equation of the wind turbine drive train established based on the three mass blocks is:

[0008] Among them, , , are respectively the inertia of the flexible blade mass block, the rigid blade - hub mass block and the generator mass block; , , are the angular velocities of the flexible blade mass block, the rigid blade - hub mass block and the generator mass block; , , are the torsional angles of the flexible blade mass block, the rigid blade - hub mass block and the generator mass block; is the aerodynamic torque; is the generator torque; is the effective blade stiffness; is the effective blade damping; is the total stiffness of the low - high - speed shaft; is the total damping of the low - high - speed shaft; is the gearbox transmission ratio; is the torsional torque on the flexible part of the blade; is the torsional torque on the low-speed shaft.

[0009] Preferably, in step S1, the power-torque state-space equation of the wind turbine is: ; , , ; ; ; ; ; ; ; ; where, is the predicted quantity, is the state quantity, is the input quantity, is the output quantity, are all matrices; is the change in the pitch angle reference value, is the change in the pitch angle, is the change in the generator speed, is the change in the filtered generator speed, is the change in the active power reference value, are the change in the angular acceleration of the flexible blade mass, the rigid blade-hub mass, and the generator mass respectively, is the change in the torsional torque on the flexible part of the blade, is the change in the torsional torque on the low-speed shaft; , are all constants, is the equivalent mass of the blade and the generator, is the active power output at the current moment, is the generator efficiency, is the aerodynamic torque at the current moment, is the generator torque at the current moment, are all variables related to the twist angle and the angular velocity increment.

[0010] Preferably, in step S2, the angular acceleration of the transmission system is the angular acceleration of the flexible blade mass, the rigid blade-hub mass, and the generator mass; the change in the torsional torque is the change in the torsional torque on the flexible part of the blade and the change in the torsional torque on the low-speed shaft respectively.

[0011] Preferably, in step S2, the expression of the objective function is: ; in, is the total number of sampling steps within the prediction time range, is the sampling time, is the total number of wind turbines, The wind turbine group number, is the weight, Respectively Typhoon turbines in the The per unit value of the angular acceleration change of the flexible blade mass block, the rigid blade-hub mass block and the generator mass block at the sampling time, For the Typhoon turbines in the The per unit value of the torsional torque change on the flexible part of the blade at the sampling time, For the Typhoon turbines in the The per-unit value of the torsional torque change on the low-speed shaft at the sampling moment.

[0012] Preferably, in step S2, the constraint condition is expressed as: ; ; ; ; The underscore indicates the lower limit, and the overscore indicates the upper limit. For the The active power output of the typhoon generator set, is the power demand instruction of the dispatching center, For the Active power reference value of typhoon generator set, For the The maximum power that can be generated by the typhoon generator set is For the The corresponding angular velocity of the typhoon turbine, For the The corresponding torque of the typhoon turbine.

[0013] Preferably, in step S3, the historical operation data of the wind turbine generator set includes the change amount of the torsional torque on the flexible part of the blade and the change amount of the torsional torque on the low-speed shaft.

[0014] Preferably, in step S3, the fatigue level The expression is:

[0015] Among them, is the fatigue level of the typhoon wind turbine generator set; is the change amount of the torsional torque on the flexible part of the blade at the sampling moment, and is the change amount of the torsional torque on the low-speed shaft at the

[0016] Preferably, the weight has the following expression: .

[0017] The present invention also discloses a power optimization system for suppressing the load of the drive train of a wind turbine generator set, including a memory and a processor connected to each other. A computer program is stored on the memory, and when the computer program is run by the processor, it executes the steps of the method described above.

[0018] Compared with the prior art, the advantages of the present invention are as follows: By establishing a correlation model between the torque of the drive train of the wind turbine generator set and the power output, and integrating a detailed wind turbine generator set model into the active power optimization scheduling problem to describe the real dynamic response, the present invention achieves better dynamic performance; proposes a two-layer active power optimization scheduling method based on model predictive control to reduce the load of the drive train of the wind turbine generator set and improve the power flow of the wind farm; establishes a two-layer dynamic control framework for the wind farm. The lower-layer wind turbine generator set controller measures the cumulative fatigue damage of the drive train in real time, and the upper-layer wind farm controller corrects the issued power reference command according to the health status of each wind turbine generator set to achieve a more balanced fatigue load distribution. In summary, the present invention can effectively suppress torsional vibration under the characteristics of interaction between the machine and the grid, improve the fatigue damage of the drive train, and thus improve the safety and stability of the grid-connected operation of the wind turbine generator set. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flowchart of the power optimization method for suppressing the load of the drive train of the wind turbine generator set of the present invention in specific applications.

[0020] Figure 2 is a structural schematic diagram of the three-mass block model of the drive train in an embodiment of the present invention.

[0021] Figure 3 is a simulation diagram of the torsional torque of the low-speed drive shaft under different scheduling methods in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The present invention will be further described below with reference to the accompanying drawings of the specification and specific embodiments.

[0023] As Figure 1As shown in the figure, the power optimization method for suppressing the load of the drive train of a wind turbine provided by the embodiment of the present invention establishes a two-layer dynamic control framework. The two-layer dynamic control framework adopts a centralized control algorithm, and the corresponding control framework is divided into upper and lower layers. The upper-layer controller is the wind farm controller, and the lower-layer controller is the local controller of each wind turbine. During the operation of the wind farm, the upper-layer controller collects the feedback information from the lower-layer controller and issues control instructions to the lower-layer controller according to the calculation results of the model predictive control algorithm. The specific steps are as follows: S1. The upper-layer controller establishes a state-space equation of the wind turbine for model predictive control calculation according to the operating parameters of each wind turbine fed back by the lower-layer controller. The operating parameters include pitch angle, generator speed, active power reference value, aerodynamic torque, generator torque, etc. S2. The upper-layer controller receives the power demand instruction from the dispatching center as the boundary condition. The upper-layer controller takes the upper and lower limits of the active power output of the wind turbine, the angular velocity and torsional torque of the drive train as the constraint conditions. The upper-layer controller takes the minimization of the angular acceleration and torsional torque variation of the drive train as the objective function, and solves the active power reference value of each wind turbine based on the state-space equation of the wind turbine and the model predictive control algorithm. S3. The lower-layer controller measures the fatigue degree of the drive train locally according to the historical operation data of each wind turbine and feeds it back to the upper-layer controller. The upper-layer controller calculates the corresponding weights according to the fatigue degree of each drive train, and corrects the active power reference value according to the weights, and sends it to the lower-layer controller as the final active power instruction to control each wind turbine.

[0024] In step S1, the state-space equation of the wind turbine includes the dynamic equation of the wind turbine drive train and the power-torque state-space equation of the wind turbine. As Figure 2 shown, a three-mass model is used to describe the drive train of the wind turbine. This model describes the drive train as a torsion system with discrete masses, and the in-plane dynamics of the blade is also described as a torsion system. The inputs of the model are the aerodynamic torque and the generator torque, and the outputs are the angular accelerations of each mass and the torques between them. Since the blade bending occurs at a place far from the connection between the blade and the hub, the blade is modeled as a flexible part and a rigid part respectively; the gearbox is simplified to an ideal gearbox, and only its transmission ratio is considered.

[0025] To describe the influence of the mechanical disturbance of the generator on the drive train, the generator is modeled as a mass block related to the mechanical inertia of the generator rotor, namely the flexible blade mass block, the rigid blade-hub mass block, and the generator mass block. The flexible blade mass block concentrates the inertia of the flexible part of the blade; the rigid blade-hub mass block concentrates the inertia of the rigid part of the blade and the hub; the generator mass block concentrates the inertia of the generator. The stiffness and damping of the effective blade connect the blade mass block and the rigid blade-hub mass block, and the total stiffness and damping of the low-speed shaft and the high-speed shaft connect the rigid blade-hub mass block and the generator mass block. The dynamic equation of the wind turbine drive train established based on the three-mass block model is as follows:

[0026] Where, , , are the inertias of the flexible blade mass block, the rigid blade-hub mass block, and the generator mass block respectively; , , are the angular velocities of the flexible blade mass block, the rigid blade-hub mass block, and the generator mass block; , , are the torsional angles of the flexible blade mass block, the rigid blade-hub mass block, and the generator mass block; is the aerodynamic torque; is the generator torque; is the effective blade stiffness; is the effective blade damping; is the total stiffness of the low- and high-speed shafts; is the total damping of the low- and high-speed shafts; is the gearbox transmission ratio; is the torsional torque on the flexible part of the blade; is the torsional torque on the low-speed shaft.

[0027] In addition, based on the coupling relationship between the torque and power output of the wind turbine, a power-torque model of the wind turbine is established. This model is affected by the pitch angle, generator speed, active power reference value, aerodynamic torque, generator torque, etc. The model is expressed by the state space equation:

[0028] , , ; ; ; ; ; ; ; .

[0029] Among them, is the predicted quantity, is the state quantity, is the input quantity, is the output quantity, all are matrices; is the change in the pitch angle reference value, is the change in the pitch angle, is the change in the generator speed, is the change in the filtered generator speed, is the change in the active power reference value, are respectively the angular acceleration changes of the flexible blade mass block, the rigid blade - hub mass block, and the generator mass block, is the change in the torsional torque on the flexible part of the blade, is the change in the torsional torque on the low - speed shaft; , are all constants, is the equivalent mass of the blade and the generator, is the active power output at the current moment, is the generator efficiency, is the aerodynamic torque at the current moment, is the generator torque at the current moment, are all variables related to the torsional angle and the angular velocity increment.

[0030] In step S2, in order to reduce the load of the drive train and improve the health state of the wind turbine, the objective function of the model predictive control is set to minimize the angular acceleration and torsional torque fluctuations in the three - mass - block model. The angular accelerations respectively refer to the angular accelerations of the flexible blade mass block, the rigid blade - hub mass block, and the generator mass block. The torsional torque (referred to as torque) respectively refers to the torsional torque on the flexible part of the blade and the torsional torque on the low - speed shaft.

[0031] The specific expression of the objective function in the model predictive control is as follows: ; Among them, is the total number of sampling steps within the prediction time range, is the sampling time, is the total number of wind turbines, is the wind turbine number, is the weight, are respectively the rd The per-unit value of the change in the angular acceleration of the flexible blade mass, the rigid blade-hub mass, and the generator mass at the sampling moment is the th typhoon wind turbine at the per-unit value of the change in the torsional torque on the flexible part of the blade at the sampling moment is the th typhoon wind turbine at the per-unit value of the change in the torsional torque on the low-speed shaft at the sampling moment

[0032] To maintain the stability of the wind farm operation, the total active power output of all wind turbines should be equal to the power demand command of the dispatching center, and the active power output of each wind turbine should not exceed its maximum available power. To ensure the reliability of the transmission system operation, its internal angular velocity and torque should be kept within a safe range. The specific expressions of the constraint conditions in model predictive control are as follows:

[0033]

[0034]

[0035]

[0036] where the underscore represents the lower limit and the overline represents the upper limit is the active power output of the th typhoon wind turbine, is the power demand command of the dispatching center, is the active power reference value of the th typhoon wind turbine, is the corresponding angular velocity of the th typhoon wind turbine,

[0037] In step S3, the lower-layer wind turbine controller measures the cumulative fatigue degree of the transmission system in real time, and the upper-layer wind farm controller corrects the issued power reference command according to the health status of each wind turbine to achieve a more balanced fatigue load distribution. Specifically, an optimized weight algorithm considering the historical operation data of the transmission system is proposed, which calculates the corresponding weights based on the past torsional torque fluctuations. This algorithm improves the fatigue load distribution of the wind turbine transmission system by optimizing the power flow in the wind farm. In the local controllers of each wind turbine in the lower layer, the fatigue degree of the transmission system is locally measured according to the cumulative increment of the torsional torque in the three-mass model:

[0038] Among them, is the fatigue degree of the typhoon wind turbine; is the change amount of the torsional torque on the flexible part of the blade at the sampling moment, is the change amount of the torsional torque on the low-speed shaft at the sampling moment.

[0039] In the upper layer, the wind farm controller calculates the corresponding optimization weight in real time according to the fatigue degree of the drive train of each wind turbine :

[0040] If the optimization weight of the wind turbine is larger, it indicates that the fatigue degree of its drive train is more serious. During the optimization solution process of the wind farm controller, appropriate reduction of the load of the fatigued wind turbines will be considered to improve the health state of the wind turbines.

[0041] The double-layer dynamic control framework of the present invention comprehensively considers the power generation of the wind farm and the health state of the wind turbines. The simulation results compared with the traditional proportional allocation control method are as Figure 3 shown. It can be seen from Figure 3 that the method proposed by the present invention can effectively suppress the torque fluctuation of the wind turbines, reduce the fatigue degree of the drive train, and improve the power flow of the system.

[0042] The present invention realizes better dynamic performance by establishing a correlation model between the torque and power output of the drive train of the wind turbine and integrating the detailed wind turbine model into the active power optimal scheduling problem to describe the real dynamic response; proposes a double-layer active power optimal scheduling method based on model predictive control to reduce the load of the drive train of the wind turbine and improve the power flow of the wind farm; establishes a double-layer dynamic control framework for the wind farm. The lower-layer wind turbine controller measures the cumulative fatigue damage of the drive train in real time, and the upper-layer wind farm controller corrects the issued power reference command according to the health condition of each wind turbine to achieve a more balanced fatigue load distribution. In summary, the present invention can effectively suppress torsional vibration under the characteristics of machine-network interaction, improve the fatigue damage of the drive train, and thus improve the safety and stability of the grid-connected operation of the wind turbines.

[0043] The present invention also discloses a power optimization system for suppressing the load of the drive train of the wind turbine, including a memory and a processor connected to each other. A computer program is stored on the memory, and the computer program executes the steps of the above method when being run by the processor. The optimization system of the present invention corresponds to the above optimization method and has the same advantages as the above optimization method.

[0044] The implementation of all or part of the processes in the above-described embodiment methods of the present invention can also be completed by hardware related to computer program instructions. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable storage medium includes: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc. The memory is used to store the computer program and / or module. The processor realizes various functions by running or executing the computer program and / or module stored in the memory, and by calling the data stored in the memory. The memory can include high-speed random access memory, and can also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices, etc.

[0045] The above is only the preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the idea of the present invention belong to the protection scope of the present invention. It should be pointed out that for those of ordinary skill in the art in this technical field, several improvements and refinements made without departing from the principle of the present invention should be regarded as within the protection scope of the present invention.

Claims

1. A power optimization method for suppressing the load of a wind turbine drive system, characterized in that, Including the steps: S1. Obtain the operation parameters of each wind turbine generator set and establish the state space equation of the wind turbine generator set; S2. Taking the power demand instruction of the dispatching center as the boundary condition, taking the upper and lower limits of the active power output of the wind turbine generator set, the angular velocity and torsional torque of the drive train as the constraint conditions, and taking the minimization of the angular acceleration and torsional torque change of the drive train as the objective function, solve the reference value of the active power of each wind turbine generator set based on the state space equation of the wind turbine generator set; S3. Measure the fatigue degree of the drive train according to the historical operation data of each wind turbine generator set, calculate the corresponding weight according to the fatigue degree of the drive train, and then correct the reference value of the active power according to the weight, and send it to each wind turbine generator set as the final active power instruction.

2. The power optimization method for suppressing the load of a wind turbine drive system according to claim 1, characterized in that In step S1, the state space equation of the wind turbine generator set includes the dynamic equation of the wind turbine generator set drive train and the power-torque state space equation of the wind turbine generator set; the establishment process of the dynamic equation of the wind turbine generator set drive train is: Model the generator as a mass block related to the mechanical inertia of the generator rotor, namely the flexible blade mass block, the rigid blade-hub mass block and the generator mass block; Among them, the flexible blade mass block concentrates the inertia of the flexible part of the blade; The rigid blade-hub mass block concentrates the inertia of the rigid part of the blade and the hub; the generator mass block concentrates the inertia of the generator; The stiffness and damping of the effective blade connect the flexible blade mass block and the rigid blade-hub mass block, and the total stiffness and damping of the low-speed shaft and the high-speed shaft connect the rigid blade-hub mass block and the generator mass block; the dynamic equation of the wind turbine generator set drive train established based on the three mass blocks is: Among them, , , are the inertias of the flexible blade mass block, the rigid blade-hub mass block, and the generator mass block respectively; , , are the angular velocities of the flexible blade mass block, the rigid blade-hub mass block, and the generator mass block; , , are the torsional angles of the flexible blade mass block, the rigid blade-hub mass block, and the generator mass block; is the aerodynamic torque; is the generator torque; is the effective blade stiffness; is the effective blade damping; is the total stiffness of the low and high speed shafts; is the total damping of the low and high speed shafts; is the gearbox transmission ratio; is the torsional torque on the flexible part of the blade; is the torsional torque on the low speed shaft.

3. The power optimization method for suppressing the load of a wind turbine drive system according to claim 2, wherein In step S1, the power-torque state space equation of the wind turbine generator set is: ； , , ； ； ； ； ； ； ； ； Among them, is the predicted quantity, is the state quantity, is the input quantity, is the output quantity, and all are matrices; is the change in the pitch angle reference value, is the change in the pitch angle, is the change in the generator speed, is the change in the filtered generator speed, is the change in the active power reference value, are respectively the change in the angular acceleration of the flexible blade mass block, the rigid blade - hub mass block, and the generator mass block, is the change in the torsional torque on the flexible part of the blade, is the change in the torsional torque on the low - speed shaft; , are all constants, is the equivalent mass of the blade and the generator, is the active power output at the current moment, is the generator efficiency, is the aerodynamic torque at the current moment, is the generator torque at the current moment, are all variables related to the torsional angle and the angular velocity increment.

4. The power optimization method for suppressing the load of a wind turbine drive system according to claim 3, characterized in that, In step S2, the angular acceleration of the drive train is the angular acceleration of the flexible blade mass block, the rigid blade-hub mass block and the generator mass block; the torsional torque change amounts are respectively the torsional torque change amount on the flexible part of the blade and the torsional torque change amount on the low-speed shaft.

5. The power optimization method for suppressing the load of the drive train of a wind turbine according to any one of claims 1-4, characterized in that, In step S2, the expression of the objective function is: ； Among them, is the total number of sampling steps within the prediction time range, is the sampling moment, is the total number of wind turbines, is the wind turbine number, is the weight, are respectively the th wind turbine's per-unit values of the angular acceleration change of the flexible blade mass block, rigid blade-hub mass block, and generator mass block at the th sampling moment, is the th wind turbine's per-unit value of the change in torsional torque on the flexible part of the blade at the th sampling moment, is the th wind turbine's per-unit value of the change in torsional torque on the low-speed shaft at the th sampling moment.

6. The power optimization method for suppressing the load of the drive train of a wind turbine according to any one of claims 1-4, characterized in that In step S2, the expression of the constraint condition is: ； ； ； ； Among them, the underscore represents the lower limit and the overline represents the upper limit. is the total number of wind turbines; is the active power output of the th wind turbine; is the power demand instruction of the dispatching center; is the th active power reference value of the th wind turbine; is the th corresponding angular velocity of the wind turbine; is the th corresponding torque of the wind turbine.

7. The power optimization method for suppressing the load of a wind turbine drive system according to any one of claims 1-4, characterized in that In step S3, the historical operation data of the wind turbine generator set includes the change amount of the torsional torque on the flexible part of the blade and the change amount of the torsional torque on the low-speed shaft.

8. The power optimization method for suppressing the loads of a wind turbine drive train according to claim 7, characterized in that, In step S3, the degree of fatigue is expressed as: Among them, is the total number of sampling steps within the prediction time range; is the fatigue level of the typhoon wind turbine; is the change in the torsional torque on the flexible part of the blade at the sampling moment, and is the change in the torsional torque on the low-speed shaft at the 9. The power optimization method for suppressing the load of the wind turbine drive system according to claim 8, wherein Weight The expression is as follows: ； Among them is the total number of wind turbines.

10. A power optimization system for suppressing the loads of a wind turbine drive train, comprising a memory and a processor connected to each other, wherein a computer program is stored on the memory, characterized in that The computer program, when run by a processor, executes the steps of the method according to any one of claims 1-9.

Images