A wind turbine real-time regulation method, device and equipment based on thrust estimation

Abstract

This application discloses a method, apparatus, and equipment for real-time control of wind turbine generators based on thrust estimation in the field of wind power generation technology. The method includes: acquiring the operating state and dynamic parameters of the wind turbine generator; determining a target thrust estimator that matches the operating state from thrust estimators constructed and trained based on whole-machine dynamic simulation data of the wind turbine generator under different operating conditions; estimating the whole-machine thrust corresponding to the dynamic parameters using the target thrust estimator; and using the whole-machine thrust to perform real-time control of the wind turbine generator. This application can achieve real-time estimation of the whole-machine thrust under all operating conditions and perform real-time control of the wind turbine generator based on the estimated whole-machine thrust, effectively balancing wind energy capture efficiency and structural load safety.

Description

Technical Field

[0001] This application relates to the field of wind power generation technology, and in particular to a method, device and equipment for real-time control of wind turbine generators. Background Technology

[0002] Wind turbine thrust is the aerodynamic load generated along the main shaft axis by airflow acting on the blade surface, and it is the main dynamic load of the unit. The thrust of the unit is proportional to the square of the wind speed and positively correlated with the blade angle of attack, blade area, and air density, exhibiting alternating characteristics as it fluctuates with wind speed.

[0003] The thrust transmission path is blades, main shaft, drive train, nacelle tower, and foundation; its damage is transmitted and amplified step by step along this path. Excessive thrust leads to aerodynamic instability and fatigue damage to the blades, accelerated wear and subsequent failures in the drive train, increased nacelle vibration, and damage and collapse of the tower and foundation. Insufficient or highly fluctuating thrust can reduce the unit's power generation and increase operation and maintenance costs and the cost per kilowatt-hour.

[0004] However, the thrust of the generator unit cannot be directly measured, so effective thrust control is currently not possible, making it difficult to balance wind energy capture efficiency with structural load safety.

[0005] With the current trend towards larger generating units, how to accurately estimate and control thrust is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0006] The purpose of this application is to provide a method, device, and equipment for real-time control of wind turbines based on thrust estimation, which can realize real-time and accurate thrust estimation, and accurately control the wind turbine based on the estimated thrust, thereby balancing wind energy capture efficiency and structural load safety.

[0007] To solve the above-mentioned technical problems, this application provides the following technical solution:

[0008] A real-time control method for wind turbines based on thrust estimation includes:

[0009] Obtain the operating status and dynamic parameters of the wind turbine;

[0010] From the thrust estimators constructed and trained based on the whole-machine dynamics simulation data of wind turbines under different operating conditions, a target thrust estimator that matches the operating state is determined.

[0011] The target thrust estimator is used to estimate the overall thrust corresponding to the dynamic parameters;

[0012] The thrust of the entire unit is used to control the wind turbine in real time.

[0013] Preferably, obtaining the dynamic parameters includes:

[0014] Obtain the flapping torque, oscillation torque, and pitch angle of each blade;

[0015] Obtain the wind turbine azimuth angle, yaw error, nacelle forward and backward acceleration, and nacelle left and right acceleration;

[0016] The mean pitch angle is determined using the aforementioned pitch angle;

[0017] The out-of-plane torque signal of the wind turbine is determined using the oscillation torque, the flapping torque, and the blade pitch angle;

[0018] The in-plane torque signal of the wind turbine is determined using the swinging torque, the flapping torque, the wind turbine azimuth angle, and the blade pitch angle.

[0019] The out-of-plane torque signal of the wind turbine, the average pitch angle, the forward and backward acceleration of the nacelle, and the left and right acceleration of the nacelle are determined as the dynamic parameters.

[0020] Preferably, estimating the overall thrust corresponding to the dynamic parameters using the target thrust estimator includes:

[0021] If the working state corresponds to the normal power generation condition, then the target thrust estimator is a first thrust estimator based on the whole-machine dynamics simulation data of the wind turbine under normal power generation condition and combined with the least squares linear regression method.

[0022] The first thrust estimator according to Calculate the thrust of the entire machine;

[0023] in, Let A1, A2, A3, and A4 be the linear regression coefficients of the first thrust estimator, representing the total thrust of the engine. Here, θ represents the out-of-plane torque signal of the wind turbine, and θ is the mean pitch angle. This refers to the forward and backward acceleration of the cabin.

[0024] Preferably, estimating the overall thrust corresponding to the dynamic parameters using the target thrust estimator includes:

[0025] If the working state corresponds to the shutdown and start-up condition, then the target thrust estimator is a second thrust estimator based on the whole-machine dynamics simulation data of the wind turbine under the shutdown and start-up condition and combined with the least squares linear regression method.

[0026] The second thrust estimator according to Calculate the thrust of the entire machine;

[0027] in, B1, B2, B3, and B4 are the linear regression coefficients of the second thrust estimator, representing the total thrust of the engine. Here, θ represents the out-of-plane torque signal of the wind turbine, and θ is the mean pitch angle. This refers to the forward and backward acceleration of the cabin.

[0028] Preferably, estimating the overall thrust corresponding to the dynamic parameters using the target thrust estimator includes:

[0029] If the working state corresponds to a high wind condition, then the target thrust estimator is the third and fourth thrust estimators based on the whole-machine dynamics simulation data of the wind turbine under high wind conditions, combined with the least squares linear regression method.

[0030] Using the third thrust estimator Calculate the forward and backward thrust;

[0031] Using the fourth thrust estimator Calculate the left and right thrust;

[0032] in, Forward and backward thrust, For the left and right thrust, C1, C2, C3, and C4 are the linear regression coefficients of the third thrust estimator, and D1, D2, D3, and D4 are the linear regression coefficients of the fourth thrust estimator. This is the out-of-plane torque signal of the wind turbine. Here, θ represents the in-plane torque signal of the wind turbine, and θ is the mean pitch angle. Forward and backward acceleration of the cabin, This refers to the left-right acceleration of the cabin.

[0033] Preferably, determining a target thrust estimator that matches the operating state from thrust estimators constructed and trained based on wind turbine dynamics simulation data under different operating conditions includes:

[0034] Using the aforementioned operating state, the target parameters are determined from the thrust estimator parameter matrix;

[0035] The thrust estimator corresponding to the target parameter is determined as the target thrust estimator.

[0036] Preferably, the power generation control of the wind turbine using the thrust of the entire turbine includes:

[0037] By utilizing the overall thrust of the turbine, the thrust can be increased through pitch control to enhance the power generation of the wind turbine.

[0038] Alternatively, by utilizing the overall thrust of the unit, thrust can be reduced or thrust fluctuations can be decreased through pitch control to reduce damage to the unit.

[0039] A real-time control device for wind turbine generators, comprising:

[0040] The data acquisition module is used to acquire the operating status and dynamic parameters of the wind turbine.

[0041] The estimator selection module is used to determine the target thrust estimator that matches the operating state from the thrust estimators constructed and trained based on the wind turbine whole-machine dynamics simulation data under different operating conditions.

[0042] The thrust estimation module is used to estimate the overall thrust corresponding to the dynamic parameters using the target thrust estimator.

[0043] The real-time control module is used to control the wind turbine in real time using the thrust of the whole machine.

[0044] An electronic device, comprising:

[0045] Memory, used to store computer programs;

[0046] A processor is used to implement the steps of the above-described real-time control method for wind turbines based on thrust estimation when executing the computer program.

[0047] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described real-time control method for wind turbines based on thrust estimation.

[0048] The method provided in the embodiments of this application is used to obtain the working state and dynamic parameters of the wind turbine; from the thrust estimators constructed and trained based on the whole-machine dynamic simulation data of the wind turbine under different working conditions, a target thrust estimator matching the working state is determined; the whole-machine thrust corresponding to the dynamic parameters is estimated using the target thrust estimator; and the wind turbine is controlled in real time using the whole-machine thrust.

[0049] In this application, a thrust estimator can be constructed and trained based on the wind turbine's overall dynamic simulation data under different operating conditions. In scenarios requiring real-time control of the wind turbine, the wind turbine's operating state and dynamic parameters can be obtained first. Then, based on the operating state, the best-fitting target thrust estimator can be selected from these thrust estimators. By estimating the dynamic parameters based on the target thrust estimator, the corresponding overall turbine thrust can be obtained. Finally, the wind turbine can be controlled in real-time based on the estimated overall turbine thrust.

[0050] That is, this application can realize real-time estimation of the whole machine thrust under all operating conditions, and make real-time control of the wind turbine based on the estimated whole machine thrust, which can effectively balance wind energy capture efficiency and structural load safety.

[0051] Accordingly, embodiments of this application also provide a real-time control device, equipment, and readable storage medium for wind turbines based on thrust estimation, which corresponds to the above-mentioned real-time control method for wind turbines based on thrust estimation. These devices have the aforementioned technical effects and will not be elaborated upon here. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a flowchart illustrating the implementation of a real-time control method for wind turbines based on thrust estimation in an embodiment of this application.

[0054] Figure 2 This is a schematic diagram illustrating a specific implementation of a real-time control method for wind turbines based on thrust estimation in an embodiment of this application.

[0055] Figure 3 This is a comparison chart of thrust estimation effects under a normal power generation condition in an embodiment of this application;

[0056] Figure 4 This is a comparison chart of thrust estimation effects under a fault shutdown condition in an embodiment of this application;

[0057] Figure 5 This is a comparison chart of the forward and backward thrust estimation effects of a generator unit with yaw error under a high-wind condition in an embodiment of this application.

[0058] Figure 6 This is a comparison chart of the left and right thrust estimation effects of a generator unit with yaw error under high wind conditions in an embodiment of this application.

[0059] Figure 7 This is a schematic diagram of the structure of a real-time control device for wind turbines based on thrust estimation, as described in an embodiment of this application.

[0060] Figure 8 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application;

[0061] Figure 9 This is a schematic diagram of the specific structure of an electronic device in an embodiment of this application. Detailed Implementation

[0062] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are merely some embodiments of the present application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0063] Please refer to Figure 1 , Figure 1 This is a flowchart of a real-time control method for a wind turbine in an embodiment of this application. The method can be applied to the main control of a wind turbine and includes the following steps:

[0064] S101. Obtain the operating status and dynamic parameters of the wind turbine.

[0065] Wind turbine design standards specify various operating conditions, such as power generation, startup, normal shutdown, emergency shutdown, shutdown (stationary or idling), shutdown with malfunction, transportation, installation, and maintenance / repair. These can be further subdivided into different sub-conditions.

[0066] To facilitate overall thrust estimation, the operating conditions are summarized. In this embodiment, the operating states of the wind turbine can include normal power generation, shutdown and start-up, and high-wind conditions. Normal power generation includes the IEC 1.1~1.5 operating conditions specified in the wind turbine design standards; shutdown and start-up includes the IEC 2.1~2.5 fault shutdown condition, IEC 3.1~3.3 normal start-up condition, IEC 4.1~4.2 normal shutdown condition, and IEC 5.1 emergency shutdown condition, all specified in the wind turbine design standards. Faults mainly include overspeed, power failure, blade runaway, and short circuit; high-wind conditions include the IEC 6.1~6.4 and IEC 7.1 operating conditions specified in the wind turbine design standards, with wind speeds above 25 m / s, typically typhoons, hurricanes, and extreme gales, under which the wind turbine is in a wind-resistant state.

[0067] Here, the dynamic parameters are the specific number of parameters that can reflect or affect the magnitude of the thrust of the wind turbine. These dynamic parameters can be obtained by processing directly measurable dynamic parameters to obtain thrust change signals that can affect the overall thrust of the turbine.

[0068] In one specific embodiment of this application, obtaining dynamic parameters includes:

[0069] Obtain the flapping torque, oscillation torque, and pitch angle of each blade;

[0070] Obtain the wind turbine azimuth angle, yaw error, nacelle forward and backward acceleration, and nacelle left and right acceleration;

[0071] Determine the mean pitch angle using the pitch angle;

[0072] The out-of-plane torque signal of the wind turbine is determined by using the oscillation torque, flapping torque and blade pitch angle;

[0073] The in-plane torque signal of the wind turbine is determined by using the oscillation torque, flapping torque, wind turbine azimuth angle, and blade pitch angle.

[0074] The out-of-plane torque signal of the wind turbine, the average pitch angle, the fore-and-aft acceleration of the nacelle, and the lateral acceleration of the nacelle are determined as dynamic parameters.

[0075] Specifically, measurable dynamic parameters include the blade flapping torque M. y1 Blade 1 oscillation torque M x1 Blade 2 flapping torque M y2 Blade 2 swing moment M x2 Blade 3 flapping torque M y3 Blade 3 swing moment M x3 Blade 1 pitch angle θ1, Blade 2 pitch angle θ2, Blade 3 pitch angle θ3, rotor azimuth α, yaw error β, nacelle fore-and-aft acceleration lateral acceleration of the cabin .

[0076] The rotor azimuth is determined using an electric slip ring device, and the tower top acceleration is measured using an accelerometer. Blade flapping and tumbling moments need to be obtained through blade root load sensors, which are usually configured in independent pitch systems or blade monitoring systems. Therefore, a thrust estimation system can be added to these systems.

[0077] The thrust variation signal that needs to be newly constructed based on the above dynamic parameters includes the wind turbine out-of-plane torque signal. Wind turbine in-plane torque signal The average pitch angle is θ, where θ is the average of θ1, θ2, and θ3. Calculate using the following formula:

[0078] ;

[0079] Calculate using the following formula:

[0080] .

[0081] S102. From the thrust estimators constructed and trained based on the whole-machine dynamics simulation data of wind turbines under different operating conditions, determine the target thrust estimator that matches the operating state.

[0082] In the embodiments of this application, a first thrust estimator can be pre-trained and constructed based on the dynamic simulation data of the wind turbine under normal power generation conditions; a second thrust estimator can be pre-trained and constructed based on the dynamic simulation data of the wind turbine under shutdown and startup conditions; and a third and fourth thrust estimator can be pre-trained and constructed based on the dynamic simulation data of the wind turbine under high wind conditions. The first, second, and third thrust estimators calculate the forward and backward thrust of the wind turbine, while the fourth thrust estimator calculates the left and right thrust.

[0083] That is, the working state corresponds to the working condition of the wind turbine whole-machine dynamic simulation data used for training by which thrust estimator is selected, i.e., which thrust estimator is selected as the target thrust estimator.

[0084] For example, if the operating condition is the normal power generation condition, the first thrust estimator can be used as the target thrust estimator; if the operating condition is the shutdown and restart condition, the second thrust estimator can be used as the target thrust estimator; if the operating condition is the strong wind condition, the third thrust estimator can be used as the target thrust estimator.

[0085] S103. Use the target thrust estimator to estimate the overall thrust corresponding to the dynamic parameters.

[0086] Once the target thrust estimator is determined, it can be used to estimate the overall thrust of the engine based on dynamic parameters, thereby obtaining the real-time overall thrust.

[0087] In one specific embodiment of this application, estimating the overall thrust corresponding to dynamic parameters using a target thrust estimator includes:

[0088] If the working state corresponds to the normal power generation condition, then the target thrust estimator is the first thrust estimator based on the whole-machine dynamics simulation data of the wind turbine under the normal power generation condition and combined with the least squares linear regression method.

[0089] The first thrust estimator follows Calculate the thrust of the entire machine;

[0090] in, Let A1, A2, A3, and A4 be the linear regression coefficients of the first thrust estimator, representing the total thrust of the engine. Here, θ represents the out-of-plane torque signal of the wind turbine, and θ is the mean pitch angle. This refers to the forward and backward acceleration of the cabin.

[0091] In other words, normal power generation conditions can include the IEC 1.1~1.5 operating conditions specified in the wind turbine design standards. The wind turbine dynamics simulation data required for training must include the normal power generation operating range of the wind turbine from the cut-in wind speed to the cut-out wind speed. Operating condition data a1, b1, ... h1 of IEC 1.2 can be selected. In practical applications, other operating condition data can be added as needed. Based on this, the first thrust estimator of the wind turbine under normal operating conditions is obtained by combining the least squares linear regression method: Where A1, A2, A3, and A4 are the linear regression coefficients of the first thrust estimator. Substituting the dynamic parameters into the calculation formula corresponding to the first thrust estimator yields the overall thrust of the engine.

[0092] In one specific embodiment of this application, estimating the overall thrust corresponding to dynamic parameters using a target thrust estimator includes:

[0093] If the working state corresponds to the shutdown and start-up condition, then the target thrust estimator is a second thrust estimator based on the whole-machine dynamics simulation data of the wind turbine under the shutdown and start-up condition and combined with the least squares linear regression method.

[0094] The second thrust estimator follows Calculate the thrust of the entire machine;

[0095] in, B1, B2, B3, and B4 are the linear regression coefficients of the second thrust estimator, representing the total thrust of the engine. Here, θ represents the out-of-plane torque signal of the wind turbine, and θ is the mean pitch angle. This refers to the forward and backward acceleration of the cabin.

[0096] In this embodiment, the shutdown and start-up conditions include the IEC 2.1~2.5 fault shutdown conditions, IEC 3.1~3.3 normal start-up conditions, IEC 4.1~4.2 normal shutdown conditions, and IEC 5.1 emergency shutdown conditions specified in the wind turbine design standards. The faults mainly include overspeed, power failure, blade runaway, short circuit, etc. The wind turbine whole-machine dynamics simulation data required for training must include the wind turbine shutdown and start-up operating range from the cut-in wind speed to the cut-out wind speed. The a1, b1, ... h1 condition data of typical fault conditions in IEC 2.2 can be selected. In practical applications, other condition data can be added based on the training and testing results. Based on this, the second thrust estimator of the wind turbine under the shutdown and start-up conditions is obtained by combining the least squares linear regression method: Where B1, B2, B3, and B4 are the linear regression coefficients of the second thrust estimator. Substituting the dynamic parameters into the calculation formula corresponding to the first thrust estimator yields the overall thrust of the engine.

[0097] In one specific embodiment of this application, estimating the overall thrust corresponding to dynamic parameters using a target thrust estimator includes:

[0098] If the working state corresponds to the high wind condition, then the target thrust estimator is the third and fourth thrust estimators based on the whole-machine dynamics simulation data of the wind turbine under the high wind condition and the least squares linear regression method.

[0099] Using a third thrust estimator Calculate the forward and backward thrust;

[0100] Using the fourth thrust estimator Calculate the left and right thrust;

[0101] in, Forward and backward thrust, For the left and right thrust, C1, C2, C3, and C4 are the linear regression coefficients of the third thrust estimator, and D1, D2, D3, and D4 are the linear regression coefficients of the fourth thrust estimator. Here, θ represents the out-of-plane torque signal of the wind turbine, and θ is the mean pitch angle. Forward and backward acceleration of the cabin, This refers to the left-right acceleration of the cabin.

[0102] In this embodiment, a third and fourth thrust estimator are trained and constructed based on the whole-machine dynamics simulation data of the wind turbine under high wind conditions. High wind conditions include IEC 6.1~6.4 and IEC 7.1 conditions specified in wind turbine design standards, with wind speeds above 25 m / s, typically typhoons, hurricanes, and extreme gales. Under these conditions, the wind turbine is in a wind-resistant state, and its backup power-supported yaw system may fail, preventing yaw operations and resulting in excessive yaw error β. Therefore, the forward and backward thrust and lateral thrust of the wind turbine are prone to exceeding limits, requiring real-time estimation to assess the risk. The whole-machine dynamics simulation data of the wind turbine required for training must include a yaw error range of 0°~360°. Data from IEC 6.2 conditions 0_1, 10_1, 20_1, ... 350_1 can be selected, or other condition data can be added depending on the training and testing results. Based on this, the third thrust estimator for the wind turbine under high wind conditions is obtained by combining the least squares linear regression method. Where: C1, C2, C3, and C4 are the linear regression coefficients of the third thrust estimator, which is used to estimate the forward and backward thrust of the unit under high wind conditions.

[0103] The fourth thrust estimator for wind turbines under high wind conditions is obtained by combining the least squares linear regression method: Where: D1, D2, D3, and D4 are the linear regression coefficients of the fourth thrust estimator, which is used to estimate the left and right thrust of the unit under high wind conditions.

[0104] That is, under high wind conditions, the dynamic parameters can be substituted into the formulas corresponding to the third and fourth thrust estimators for calculation, thereby obtaining the forward and backward thrust and the left and right thrust of the unit under wind conditions.

[0105] That is, under non-high wind conditions, only the forward and backward thrust of the computer unit is required, while under high wind conditions, both the forward and backward thrust of the computer unit and the left and right thrust of the unit under high wind conditions are required.

[0106] S104. Real-time control of the wind turbine unit using the thrust of the whole machine.

[0107] After calculating the real-time thrust of the entire turbine, the wind turbine can be controlled in real time based on that thrust.

[0108] Specifically, by setting the overall thrust and wind direction, a mapping relationship can be established with the corresponding operation of the wind turbine, thereby enabling real-time control of the wind turbine based on the overall thrust.

[0109] In one specific real-time method described in this application, the power generation control of the wind turbine unit is achieved using the thrust of the entire turbine, including:

[0110] By utilizing the overall thrust of the wind turbine and increasing thrust through pitch control, the power generation of the wind turbine can be improved.

[0111] Alternatively, by utilizing the overall thrust of the unit, thrust can be reduced or thrust fluctuations can be minimized through pitch control to reduce damage to the unit.

[0112] In this embodiment, based on the estimated thrust, thrust can be increased through operations such as pitch control to improve the generator's power generation, while thrust can be reduced or thrust fluctuations can be decreased to reduce generator damage.

[0113] The method provided in the embodiments of this application is used to obtain the working state and dynamic parameters of the wind turbine; from the thrust estimators constructed and trained based on the whole-machine dynamic simulation data of the wind turbine under different working conditions, a target thrust estimator matching the working state is determined; the whole-machine thrust corresponding to the dynamic parameters is estimated using the target thrust estimator; and the wind turbine is controlled in real time using the whole-machine thrust.

[0114] In this application, a thrust estimator can be constructed and trained based on the wind turbine's overall dynamic simulation data under different operating conditions. In scenarios requiring real-time control of the wind turbine, the wind turbine's operating state and dynamic parameters can be obtained first. Then, based on the operating state, the best-fitting target thrust estimator can be selected from these thrust estimators. By estimating the dynamic parameters based on the target thrust estimator, the corresponding overall turbine thrust can be obtained. Finally, the wind turbine can be controlled in real-time based on the estimated overall turbine thrust.

[0115] That is, this application can realize real-time estimation of the whole machine thrust under all operating conditions, and make real-time control of the wind turbine based on the estimated whole machine thrust, which can effectively balance wind energy capture efficiency and structural load safety.

[0116] It should be noted that, based on the above embodiments, the embodiments of this application also provide corresponding improvement schemes. In the preferred / improved embodiments, the same or corresponding steps as in the above embodiments can be referred to each other, and the corresponding beneficial effects can also be referred to each other; however, these will not be elaborated upon in the preferred / improved embodiments herein.

[0117] In one specific embodiment of this application, determining a target thrust estimator that matches the operating state from thrust estimators constructed and trained based on wind turbine whole-machine dynamics simulation data under different operating conditions includes:

[0118] Target parameters are determined from the thrust estimator parameter matrix using the operating status;

[0119] The thrust estimator corresponding to the target parameters is determined as the target thrust estimator.

[0120] In this embodiment, all thrust estimators can be written into the wind turbine main control program, and combined with the unit status codes, real-time estimation of the whole machine thrust under all operating conditions can be achieved. The written thrust estimator can be divided into two parts: parameters and algorithms. For a certain type of unit, its thrust estimator parameters can be represented as a matrix of the following form: .

[0121] The thrust estimation algorithm is as follows: based on the master control acquiring and constructing the thrust estimation signal; based on the wind turbine state parameters (VsprState) in the master control, select the corresponding thrust estimator to estimate the thrust; when VsprState is the normal power generation code (i.e., the corresponding normal power generation operating state), select the first thrust estimator to estimate the thrust; when VsprState is the start-up / shutdown code (i.e., the corresponding start-up / shutdown operating state), select the second thrust estimator to estimate the thrust; when VsprState is the high wind code (i.e., the corresponding high wind operating state), select the third and fourth thrust estimators to estimate the thrust.

[0122] To facilitate a better understanding and implementation of the real-time wind turbine control method based on thrust estimation provided in the embodiments of this application, the following verification is conducted using an operation example from Bladed, a leading software for simulating the overall load of wind turbines.

[0123] Please refer to Figure 2 The verification process is as follows:

[0124] Step 1: Construct a thrust variation signal for the entire wind turbine based on measurable wind turbine dynamic parameters. Here, variables from the Bladed simulation results are used to replace the actually measured dynamic parameters. Dynamic parameters directly used as the thrust variation signal include the rotor azimuth angle α, yaw error β, and nacelle fore-and-aft acceleration. Forward and backward acceleration of the cabin The thrust change signal that needs to be converted includes the external torque signal of the wind turbine surface. Wind turbine in-plane torque signal , the mean pitch angle θ.

[0125] Step 2: Train and construct the first thrust estimator based on the wind turbine's overall dynamics simulation data under normal power generation conditions. Here, the a1, b1, ... h1 operating condition data of IEC 1.2 are selected as training data. Based on this, the first thrust estimator of the wind turbine under normal operating conditions is obtained by combining the least squares linear regression method: .

[0126] Step 3: Train and construct a second thrust estimator based on the wind turbine's overall dynamics simulation data under shutdown and startup conditions. Here, the a1, b1, ... h1 conditions of the IEC 2.2 overspeed fault condition are selected as training data. Based on this, the second thrust estimator of the wind turbine under shutdown and startup conditions is obtained by combining the least squares linear regression method: .

[0127] Step 4: Train and construct the third and fourth thrust estimators based on the wind turbine's overall dynamics simulation data under high wind conditions. Here, the IEC 6.2 operating condition data 0_1, 10_1, 20_1, ... 350_1 are selected as training data. Based on this, the third thrust estimator for the wind turbine under high wind conditions is obtained by combining the least squares linear regression method: .

[0128] Furthermore, by combining the least squares linear regression method, a fourth thrust estimator for wind turbines is obtained to estimate the left and right thrust of the unit under high wind conditions: .

[0129] Step 4: Write all thrust estimators into the wind turbine main control program, and combine them with the turbine status codes to achieve real-time thrust estimation under all operating conditions. Here, the first, second, third, and fourth thrust estimators are all written into the wind turbine main control program, and Bladed simulation tests are performed under different operating conditions. Based on the wind turbine state parameter VsprState, the main control program will select the corresponding thrust estimator for thrust estimation.

[0130] in, Figure 3 The thrust estimation effect corresponds to the normal power generation conditions. Figure 4 Thrust estimation effect under fault shutdown conditions Figure 5 The estimation effect of forward and backward thrust of the unit under high wind conditions with yaw error. Figure 6 The thrust estimation effect of the wind turbine under high wind conditions with yaw error is shown. It can be seen that the thrust estimation effect of the real-time control of the wind turbine provided in the embodiments of this application is almost consistent with the simulation effect. Therefore, the thrust estimation is accurate. Further adjustment of the wind turbine based on the accurate thrust can effectively balance wind energy capture efficiency and structural load safety.

[0131] Corresponding to the above method embodiments, this application also provides a real-time control device for wind turbines based on thrust estimation. The real-time control device for wind turbines based on thrust estimation described below and the real-time control method for wind turbines based on thrust estimation described above can be referred to each other.

[0132] See Figure 7 As shown, the device includes the following modules:

[0133] The data acquisition module 101 is used to acquire the operating status and dynamic parameters of the wind turbine.

[0134] The estimator selection module 102 is used to determine the target thrust estimator that matches the working state from the thrust estimators built and trained based on the whole-machine dynamics simulation data of the wind turbine under different working conditions.

[0135] The thrust estimation module 103 is used to estimate the overall thrust corresponding to the dynamic parameters using the target thrust estimator.

[0136] The real-time control module 104 is used to control the wind turbine in real time using the thrust of the whole machine.

[0137] Using the apparatus provided in the embodiments of this application, the operating state and dynamic parameters of the wind turbine are obtained; a target thrust estimator matching the operating state is determined from the thrust estimators constructed and trained based on the whole-machine dynamic simulation data of the wind turbine under different operating conditions; the whole-machine thrust corresponding to the dynamic parameters is estimated using the target thrust estimator; and the wind turbine is controlled in real time using the whole-machine thrust.

[0138] In this application, a thrust estimator can be constructed and trained based on the wind turbine's overall dynamic simulation data under different operating conditions. In scenarios requiring real-time control of the wind turbine, the wind turbine's operating state and dynamic parameters can be obtained first. Then, based on the operating state, the best-fitting target thrust estimator can be selected from these thrust estimators. By estimating the dynamic parameters based on the target thrust estimator, the corresponding overall turbine thrust can be obtained. Finally, the wind turbine can be controlled in real-time based on the estimated overall turbine thrust.

[0139] That is, this application can realize real-time estimation of the whole machine thrust under all operating conditions, and make real-time control of the wind turbine based on the estimated whole machine thrust, which can effectively balance wind energy capture efficiency and structural load safety.

[0140] In one specific embodiment of this application, the data acquisition module is specifically used to acquire the flapping torque, yaw torque, and pitch angle of each blade; acquire the rotor azimuth angle, yaw error, nacelle forward / backward acceleration, and nacelle left / right acceleration; determine the mean pitch angle using the pitch angle; determine the rotor out-of-plane torque signal using the yaw torque, flapping torque, and pitch angle; determine the rotor in-plane torque signal using the yaw torque, flapping torque, rotor azimuth angle, and pitch angle; and determine the rotor out-of-plane torque signal, the mean pitch angle, the nacelle forward / backward acceleration, and the nacelle left / right acceleration as dynamic parameters.

[0141] In one specific embodiment of this application, the thrust estimation module is specifically used to, if the working state corresponds to the normal power generation condition, then the target thrust estimator is a first thrust estimator based on the whole-machine dynamics simulation data of the wind turbine under the normal power generation condition and combined with the least squares linear regression method.

[0142] The first thrust estimator follows Calculate the thrust of the entire machine;

[0143] in, Let A1, A2, A3, and A4 be the linear regression coefficients of the first thrust estimator, representing the total thrust of the engine. Here, θ represents the out-of-plane torque signal of the wind turbine, and θ is the mean pitch angle. This refers to the forward and backward acceleration of the cabin.

[0144] In one specific embodiment of this application, the thrust estimation module is specifically used to, if the working state corresponds to the shutdown and start-up condition, then the target thrust estimator is a second thrust estimator based on the whole-machine dynamics simulation data of the wind turbine under the shutdown and start-up condition and combined with the least squares linear regression method.

[0145] The second thrust estimator follows Calculate the thrust of the entire machine;

[0146] in, B1, B2, B3, and B4 are the linear regression coefficients of the second thrust estimator, representing the total thrust of the engine. Here, θ represents the out-of-plane torque signal of the wind turbine, and θ is the mean pitch angle. This refers to the forward and backward acceleration of the cabin.

[0147] In one specific embodiment of this application, the thrust estimation module is specifically used to, if the working state corresponds to a high wind condition, then the target thrust estimator is a third thrust estimator and a fourth thrust estimator based on the dynamic simulation data of the wind turbine under the high wind condition combined with the least squares linear regression method.

[0148] Using a third thrust estimator Calculate the forward and backward thrust;

[0149] Using the fourth thrust estimator Calculate the left and right thrust;

[0150] in, Forward and backward thrust, For the left and right thrust, C1, C2, C3, and C4 are the linear regression coefficients of the third thrust estimator, and D1, D2, D3, and D4 are the linear regression coefficients of the fourth thrust estimator. Here, θ represents the out-of-plane torque signal of the wind turbine, and θ is the mean pitch angle. Forward and backward acceleration of the cabin, This refers to the left-right acceleration of the cabin.

[0151] In one specific embodiment of this application, the estimator selection module is specifically used to determine the target parameter from the thrust estimator parameter matrix using the operating state;

[0152] The thrust estimator corresponding to the target parameters is determined as the target thrust estimator.

[0153] In one specific embodiment of this application, the real-time control module is specifically used to increase the thrust of the wind turbine by using the thrust of the whole machine through pitch operation to increase the power generation of the wind turbine.

[0154] Alternatively, by utilizing the overall thrust of the unit, thrust can be reduced or thrust fluctuations can be minimized through pitch control to reduce damage to the unit.

[0155] Corresponding to the above method embodiments, this application also provides an electronic device. The electronic device described below can be referred to in conjunction with the wind turbine real-time control method based on thrust estimation described above.

[0156] See Figure 8 As shown, the electronic device includes:

[0157] Memory 332 is used to store computer programs;

[0158] The processor 322 is used to execute a computer program to implement the steps of the real-time control method for wind turbines based on thrust estimation in the above method embodiments.

[0159] For details, please refer to Figure 9 , Figure 9 This is a schematic diagram of the specific structure of an electronic device provided in this embodiment. The electronic device can vary significantly due to differences in configuration or performance. It may include one or more central processing units (CPUs) (e.g., one or more processors) and a memory 332. The memory 332 stores one or more computer programs 342 or data 344. The memory 332 can be temporary or permanent storage. The program stored in the memory 332 may include one or more modules (not shown in the diagram), each module may include a series of instruction operations on the data processing device. Furthermore, the processor 322 may be configured to communicate with the memory 332 and execute the series of instruction operations stored in the memory 332 on the electronic device 301.

[0160] Electronic device 301 may also include one or more power supplies 326, one or more wired or wireless network interfaces 350, one or more input / output interfaces 358, and / or one or more operating systems 341.

[0161] The steps in the real-time control method for wind turbines based on thrust estimation described above can be implemented by the structure of electronic equipment.

[0162] Corresponding to the above method embodiments, this application also provides a readable storage medium. The readable storage medium described below can be referred to in conjunction with the real-time control method for wind turbines based on thrust estimation described above.

[0163] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the real-time control method for wind turbines based on thrust estimation as described in the above method embodiments.

[0164] Specifically, the readable storage medium can be a USB flash drive, external hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or any other readable storage medium capable of storing program code.

[0165] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0166] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0167] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0168] Finally, it should be noted that in this document, relationships such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "include," "contain," or any other variations are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0169] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A real-time control method for wind turbine generators based on thrust estimation, characterized in that, include: Obtain the operating status and dynamic parameters of the wind turbine; From the thrust estimators constructed and trained based on the whole-machine dynamics simulation data of wind turbines under different operating conditions, a target thrust estimator that matches the operating state is determined. A first thrust estimator is pre-trained and constructed based on the dynamic simulation data of the wind turbine under normal power generation conditions; a second thrust estimator is pre-trained and constructed based on the dynamic simulation data of the wind turbine under shutdown and start-up conditions; and a third and fourth thrust estimator are pre-trained and constructed based on the dynamic simulation data of the wind turbine under high wind conditions. The target thrust estimator is used to estimate the overall thrust corresponding to the dynamic parameters; The thrust of the entire unit is used to control the wind turbine in real time; Among them, obtaining dynamic parameters includes: Obtain the flapping torque, oscillation torque, and pitch angle of each blade; Obtain the wind turbine azimuth angle, yaw error, nacelle forward and backward acceleration, and nacelle left and right acceleration; The mean pitch angle is determined using the aforementioned pitch angle; The out-of-plane torque signal of the wind turbine is determined using the oscillation torque, the flapping torque, and the blade pitch angle; The in-plane torque signal of the wind turbine is determined using the swinging torque, the flapping torque, the wind turbine azimuth angle, and the blade pitch angle. The out-of-plane torque signal of the wind turbine, the average pitch angle, the fore-and-aft acceleration of the nacelle, and the lateral acceleration of the nacelle are determined as the dynamic parameters. The process of estimating the overall thrust corresponding to the dynamic parameters using the target thrust estimator includes: If the working state corresponds to the normal power generation condition, then the target thrust estimator is a first thrust estimator based on the whole-machine dynamics simulation data of the wind turbine under normal power generation condition and combined with the least squares linear regression method. The first thrust estimator according to Calculate the thrust of the entire machine; in, Let A1, A2, A3, and A4 be the linear regression coefficients of the first thrust estimator, representing the total thrust of the engine. Here, θ represents the out-of-plane torque signal of the wind turbine, and θ is the mean pitch angle. Forward and backward acceleration of the cabin; If the working state corresponds to the shutdown and start-up condition, then the target thrust estimator is a second thrust estimator based on the whole-machine dynamics simulation data of the wind turbine under the shutdown and start-up condition and combined with the least squares linear regression method. The second thrust estimator according to Calculate the thrust of the entire machine; in, B1, B2, B3, and B4 are the linear regression coefficients of the second thrust estimator, representing the total thrust of the engine. If the operating state corresponds to a high wind condition, then the target thrust estimator is the third and fourth thrust estimators based on the wind turbine's whole-machine dynamics simulation data under high wind conditions, combined with the least squares linear regression method. Using the third thrust estimator Calculate the forward and backward thrust; Using the fourth thrust estimator Calculate the left and right thrust; in, Forward and backward thrust, For the left and right thrust, C1, C2, C3, and C4 are the linear regression coefficients of the third thrust estimator, and D1, D2, D3, and D4 are the linear regression coefficients of the fourth thrust estimator. β represents the in-plane torque signal of the wind turbine, and β represents the yaw error. This refers to the lateral acceleration of the cabin.

2. The method according to claim 1, characterized in that, From the thrust estimators constructed and trained based on wind turbine dynamics simulation data under different operating conditions, a target thrust estimator matching the operating state is determined, including: Using the aforementioned operating state, the target parameters are determined from the thrust estimator parameter matrix; The thrust estimator corresponding to the target parameter is determined as the target thrust estimator.

3. The method according to claim 1 or 2, characterized in that, Using the thrust of the entire turbine to control the power generation of the wind turbine includes: By utilizing the overall thrust of the turbine, the thrust can be increased through pitch control to enhance the power generation of the wind turbine. Alternatively, by utilizing the overall thrust of the unit, thrust can be reduced or thrust fluctuations can be decreased through pitch control to reduce damage to the unit.

4. A real-time control device for wind turbine generators, characterized in that, include: The data acquisition module is used to acquire the operating status and dynamic parameters of the wind turbine. The estimator selection module is used to determine the target thrust estimator that matches the operating state from the thrust estimators constructed and trained based on the wind turbine whole-machine dynamics simulation data under different operating conditions. A first thrust estimator is pre-trained and constructed based on the dynamic simulation data of the wind turbine under normal power generation conditions; a second thrust estimator is pre-trained and constructed based on the dynamic simulation data of the wind turbine under shutdown and start-up conditions; and a third and fourth thrust estimator are pre-trained and constructed based on the dynamic simulation data of the wind turbine under high wind conditions. The thrust estimation module is used to estimate the overall thrust corresponding to the dynamic parameters using the target thrust estimator. The real-time control module is used to control the wind turbine in real time using the thrust of the whole machine; Among them, obtaining dynamic parameters includes: Obtain the flapping torque, oscillation torque, and pitch angle of each blade; Obtain the wind turbine azimuth angle, yaw error, nacelle forward and backward acceleration, and nacelle left and right acceleration; The mean pitch angle is determined using the aforementioned pitch angle; The out-of-plane torque signal of the wind turbine is determined using the oscillation torque, the flapping torque, and the blade pitch angle; The in-plane torque signal of the wind turbine is determined using the swinging torque, the flapping torque, the wind turbine azimuth angle, and the blade pitch angle. The out-of-plane torque signal of the wind turbine, the average pitch angle, the fore-and-aft acceleration of the nacelle, and the lateral acceleration of the nacelle are determined as the dynamic parameters. The process of estimating the overall thrust corresponding to the dynamic parameters using the target thrust estimator includes: If the working state corresponds to the normal power generation condition, then the target thrust estimator is a first thrust estimator based on the whole-machine dynamics simulation data of the wind turbine under normal power generation condition and combined with the least squares linear regression method. The first thrust estimator according to Calculate the thrust of the entire machine; in, Let A1, A2, A3, and A4 be the linear regression coefficients of the first thrust estimator, representing the total thrust of the engine. Here, θ represents the out-of-plane torque signal of the wind turbine, and θ is the mean pitch angle. Forward and backward acceleration of the cabin; If the working state corresponds to the shutdown and start-up condition, then the target thrust estimator is a second thrust estimator based on the whole-machine dynamics simulation data of the wind turbine under the shutdown and start-up condition and combined with the least squares linear regression method. The second thrust estimator according to Calculate the thrust of the entire machine; in, B1, B2, B3, and B4 are the linear regression coefficients of the second thrust estimator, representing the total thrust of the engine. If the operating state corresponds to a high wind condition, then the target thrust estimator is the third and fourth thrust estimators based on the wind turbine's whole-machine dynamics simulation data under high wind conditions, combined with the least squares linear regression method. Using the third thrust estimator Calculate the forward and backward thrust; Using the fourth thrust estimator Calculate the left and right thrust; in, Forward and backward thrust, For the left and right thrust, C1, C2, C3, and C4 are the linear regression coefficients of the third thrust estimator, and D1, D2, D3, and D4 are the linear regression coefficients of the fourth thrust estimator. β represents the in-plane torque signal of the wind turbine, and β represents the yaw error. This refers to the lateral acceleration of the cabin.

5. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the real-time control method for wind turbines based on thrust estimation as described in any one of claims 1 to 3 when executing the computer program.

6. A readable storage medium, characterized in that, The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the real-time control method for wind turbines based on thrust estimation as described in any one of claims 1 to 3.

Images