Method for controlling maximum generated power of wind turbine generator based on artificial intelligence management

Abstract

The invention discloses a wind turbine generator maximum generation power control method based on artificial intelligence management. The method comprises the following steps that 1, the initial wind speed V0 passing through a first wind turbine generator is measured; 2, measuring the generation power and the axial induction factor of the first wind driven generator in real time to obtain the maximum power delta P1 of the first wind driven generator; 3, the wake flow velocity V11 of the first wind driven generator is obtained through calculation; 4, the initial wind speed V20 passing through the second wind driven generator is measured, the wake flow expansion coefficient beta is calculated according to a Jensen wake flow model, and in the technical field of wind power generation, the wake flow expansion coefficient is deduced through the first wind driven generator and the second wind driven generator, and the initial wind speeds of all the wind driven generators are sequentially derived; therefore, the power generation efficiency of the wind turbine generator is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and in particular to a method for controlling the maximum power generation of a wind turbine generator set based on artificial intelligence management. Background Art

[0002] Wind power generation is an electric device that converts wind energy into mechanical energy and mechanical energy into electrical energy. In a broad sense, it is a heat energy utilization engine that uses the sun as a heat source and the atmosphere as a working medium. Wind power generation uses natural energy. It is much better than diesel power generation. However, if used in an emergency, it is still not as good as a diesel generator. Wind power generation cannot be regarded as a backup power source, but it can be used for a long time.

[0003] In the existing wind power generation technology, according to the patent number: CN116006400A, the patent name: Maximum power point tracking control method and system of wind turbines based on wake prediction, hereinafter collectively referred to as the reference patent, the reference patent records "considering the wake of the unit and its conduction model, and at the same time, the calculation complexity can be greatly simplified. The wake model consists of three prediction models: wake wind speed change, wake radius expansion and wake centerline motion trajectory. For the convenience of principle analysis, there is no influence of expansion, and only the wake wind speed change model is considered here." The technical personnel in this field can know that the reference patent uses the expansion coefficient to predict the wake wind speed change model, but due to the complex environment on site, the expansion coefficient will change according to factors such as on-site pressure.

[0004] Therefore, a maximum power generation control method for wind turbines based on artificial intelligence management was designed. Summary of the invention

[0005] In order to overcome the above-mentioned shortcomings, the present invention provides a maximum power generation control method of a wind turbine generator set based on artificial intelligence management.

[0006] The present invention achieves the above-mentioned purpose through the following technical solutions:

[0007] A method for controlling the maximum power generation of a wind turbine generator system based on artificial intelligence management comprises the following steps:

[0008] Step 1: Measure the initial wind speed V0 passing through the first wind turbine to obtain the current initial wind power P0;

[0009] Step 2: measuring the power generation and axial induction factor of the first wind turbine in real time, and adjusting the rotor angle of the first wind turbine until the axial induction factor converges, thereby obtaining the maximum power ΔP1 of the first wind turbine;

[0010] Step 3: Calculate and obtain the wake velocity V11 of the first wind turbine;

[0011] Step 4: Measure the initial wind speed V20 passing the second wind turbine and calculate the wake expansion coefficient β according to the Jensen wake model;

[0012] Step 5: measuring the power generation and axial induction factor of the second wind turbine in real time, and adjusting the rotor angle of the wind turbine until the axial induction factor converges, and obtaining the maximum power ΔP2 of the second wind turbine;

[0013] Step 6: Calculate and obtain the wake velocity V21 of the second wind turbine;

[0014] Step 7: Calculate the initial wind speed V30 of the third wind turbine by using the wake expansion coefficient β obtained in step 4. At this time, the third wind turbine can start to adjust its power generation and axial induction factor, and adjust the rotor angle of the wind turbine until the axial induction factor converges to obtain the maximum power ΔP3 of the second wind turbine.

[0015] Step 8: Follow steps 6 and 7 to loop and calculate the output flow rate ν of the mth wind turbine in the wind turbine group. m0 .

[0016] Preferably, in step 1, according to the initial wind speed and the coverage area of ​​the wind turbine, P0=0.5*ρ*A*ν0 3 , ρ is the air density, A is the coverage area, V0 is the initial wind speed, and the initial wind power P0 is obtained.

[0017] Preferably, in step 3, P1 = P0 - ΔP1, since P1 = 0.5*ρ*A*ν 11 3 , then calculate the wake velocity V11 of the first wind turbine.

[0018] Preferably, in step 4, the derivation formula of the Jensen wake model is as follows:

[0019]

[0020] Among them, V n+1 is the wake velocity, V n is the flow velocity, C T is the thrust coefficient, x is the distance between two adjacent wind turbines, and d is the diameter of the wind turbine rotor.

[0021] Preferably, the thrust coefficient = thrust / 0.5*ρ*ν m0 2 *A, thrust is measured by the pressure sensor on the wind turbine, ν m0is the initial wind speed at the wind turbine.

[0022] Preferably, the maximum power generation control method of a wind turbine generator set based on artificial intelligence management includes: a measurement module for measuring the initial speed, wake speed, pressure of the fluid on the wind turbine generator, power generation and axial induction factor of the current wind turbine generator;

[0023] A prediction module is used to calculate the initial wind speed of the wind turbine based on real-time measurement data or derived parameters;

[0024] The control module is used to control the impeller of the wind turbine to adjust the power generation and axial induction factor of the wind turbine.

[0025] Preferably, in the prediction module, the difference between the actual maximum output power of the wind turbine and the calculated actual maximum output power is ΔP, which is automatically recorded in the maximum output power calculation of the next wind turbine.

[0026] Preferably, the wind speeds in steps one to eight are measured by a wind speed sensor, which is an ultrasonic wind speed sensor. The air flows through a sensor probe measurement area, where two pairs of ultrasonic probes are provided. The wind speed can be calculated by calculating the time difference in the transmission of the ultrasonic wave between two points. This method can avoid the influence of temperature on the speed of sound.

[0027] Preferably, the wind turbines transmit data to each other via a wireless data module.

[0028] Preferably, the air density in steps 1 to 8 is measured by a gas density sensor.

[0029] The beneficial effects of the present invention are as follows: in the maximum power generation control method of a wind turbine generator set based on artificial intelligence management:

[0030] 1. The expansion coefficient of the wake is derived through the first wind turbine and the second wind turbine, and the initial wind speed of each wind turbine is derived in turn to adjust the impeller in advance, thereby improving the power generation efficiency of the wind turbine;

[0031] 2. In step 4, the Jensen wake model calculates the wake expansion coefficient β by adding the thrust coefficient to improve the accuracy of the wake expansion coefficient calculation;

[0032] 3. An error ΔP is added to the prediction module, which can be taken into account when calculating the output power of the wind turbine, thereby improving the accuracy of the calculation of the output power of the wind turbine. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The present invention will now be described by way of example with reference to the accompanying drawings, in which:

[0034] Figure 1 This is a distribution diagram of the wind turbines in the wind turbine generator set of the present invention. DETAILED DESCRIPTION

[0035] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0036] like Figure 1 , a method for controlling the maximum power generation of a wind turbine based on artificial intelligence management, comprising the following steps:

[0037] Step 1: Measure the initial wind speed V0 passing through the first wind turbine to obtain the current initial wind power P0;

[0038] Step 2: measuring the power generation and axial induction factor of the first wind turbine in real time, and adjusting the rotor angle of the first wind turbine until the axial induction factor converges, thereby obtaining the maximum power ΔP1 of the first wind turbine;

[0039] Step 3: Calculate and obtain the wake velocity V11 of the first wind turbine;

[0040] Step 4: Measure the initial wind speed V20 passing the second wind turbine and calculate the wake expansion coefficient β according to the Jensen wake model;

[0041] Step 5: measuring the power generation and axial induction factor of the second wind turbine in real time, and adjusting the rotor angle of the wind turbine until the axial induction factor converges, and obtaining the maximum power ΔP2 of the second wind turbine;

[0042] Step 6: Calculate and obtain the wake velocity V21 of the second wind turbine;

[0043] Step 7: Calculate the initial wind speed V30 of the third wind turbine by using the wake expansion coefficient β obtained in step 4. At this time, the third wind turbine can start to adjust its power generation and axial induction factor, and adjust the rotor angle of the wind turbine until the axial induction factor converges to obtain the maximum power ΔP3 of the second wind turbine.

[0044] Step 8: Follow steps 6 and 7 to loop and calculate the output flow rate ν of the mth wind turbine in the wind turbine group. m0 .

[0045] In the specific embodiment, in step 1, according to the initial wind speed and the coverage area of ​​the wind turbine, P0 = 0.5*ρ*A*ν0 3 , ρ is the air density, A is the coverage area, V0 is the initial wind speed, and the initial wind power P0 is obtained.

[0046] In the specific embodiment, in step 3, P1 = P0-ΔP1, since P1 = 0.5*ρ*A*ν 11 3 , then calculate the wake velocity V11 of the first wind turbine.

[0047] In the specific embodiment, in step 4, the derivation formula of the Jensen wake model is as follows:

[0048]

[0049] Among them, V n+1 is the wake velocity, V n is the flow velocity, C T is the thrust coefficient, x is the distance between two adjacent wind turbines, and d is the diameter of the wind turbine rotor.

[0050] In a specific embodiment, the thrust coefficient = thrust / 0.5*ρ*ν m0 2 *A, thrust is measured by the pressure sensor on the wind turbine, ν m0 is the initial wind speed at the wind turbine.

[0051] In a specific embodiment, the maximum power generation control method of a wind turbine generator system based on artificial intelligence management includes:

[0052] The measurement module is used to measure the initial speed, wake speed, fluid pressure on the wind turbine, power generation and axial induction factor of the current wind turbine;

[0053] A prediction module is used to calculate the initial wind speed of the wind turbine based on real-time measurement data or derived parameters;

[0054] The control module is used to control the impeller of the wind turbine to adjust the power generation and axial induction factor of the wind turbine.

[0055] In a specific embodiment, in the prediction module, the difference between the actual maximum output power of the wind turbine and the calculated actual maximum output power is ΔP, which is automatically recorded in the maximum output power calculation of the next wind turbine. For example, the difference between the actual maximum output power of the second wind turbine and the calculated actual maximum output power is ΔP. ​​When calculating the third wind turbine, the power brought by the initial speed of the wind reaching the third wind turbine is subtracted from the maximum output power calculated by the third wind turbine, and then ΔP is subtracted. The wake speed of the third wind turbine can be calculated more accurately, which can help adjust the maximum output power of the fourth wind turbine.

[0056] In a specific embodiment, the wind speeds in steps 1 to 8 are all measured by a wind speed sensor, and the wind speed sensor is an ultrasonic wind speed sensor.

[0057] In a specific embodiment, the wind turbines transmit data to each other via wireless data modules.

[0058] In a specific embodiment, the air density in steps 1 to 8 is measured by a gas density sensor.

[0059] The above is based on the present invention as an inspiration. Through the above description, relevant staff can make various changes and modifications without departing from the technical idea of ​​this invention. The technical scope of this invention is not limited to the content in the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. A method for controlling the maximum power generation of a wind turbine based on artificial intelligence management, characterized in that: The following steps are involved: Step 1: Measure the initial wind speed V0 passing through the first wind turbine to obtain the current initial wind power P0; Step 2: measuring the power generation and axial induction factor of the first wind turbine in real time, and adjusting the rotor angle of the first wind turbine until the axial induction factor converges, thereby obtaining the maximum power ΔP1 of the first wind turbine; Step 3: Calculate and obtain the wake velocity V11 of the first wind turbine; Step 4: Measure the initial wind speed V20 passing the second wind turbine and calculate the wake expansion coefficient β according to the Jensen wake model; Step 5: measuring the power generation and axial induction factor of the second wind turbine in real time, and adjusting the rotor angle of the wind turbine until the axial induction factor converges, and obtaining the maximum power ΔP2 of the second wind turbine; Step 6: Calculate and obtain the wake velocity V21 of the second wind turbine; Step 7: Calculate the initial wind speed V30 of the third wind turbine by using the wake expansion coefficient β obtained in step 4. At this time, the third wind turbine can start to adjust its power generation and axial induction factor, and adjust the rotor angle of the wind turbine until the axial induction factor converges to obtain the maximum power ΔP3 of the second wind turbine. Step 8: Follow steps 6 and 7 to loop and calculate the output flow rate ν of the mth wind turbine in the wind turbine group. m0 .

2. The method for controlling the maximum power generation of a wind turbine generator system based on artificial intelligence management according to claim 1 is characterized in that: In step 1, according to the initial wind speed and the coverage area of ​​the wind turbine, P0 = 0.5*ρ*A*ν0 3 , ρ is the air density, A is the coverage area, V0 is the initial wind speed, and the initial wind power P0 is obtained.

3. The method for controlling the maximum power generation of a wind turbine generator system based on artificial intelligence management according to claim 1 is characterized in that: In step 3, P1 = P0-ΔP1, since P1 = 0.5*ρ*A*ν 11 3 , then calculate the wake velocity V11 of the first wind turbine.

4. The method for controlling the maximum power generation of a wind turbine generator system based on artificial intelligence management according to claim 1 is characterized in that: In step 4, the derivation formula of the Jensen wake model is as follows: Among them, V n+1 is the wake velocity, V n is the flow velocity, C T is the thrust coefficient, x is the distance between two adjacent wind turbines, and d is the diameter of the wind turbine rotor.

5. The method for controlling the maximum power generation of a wind turbine generator system based on artificial intelligence management according to claim 4 is characterized in that: The thrust coefficient = thrust / 0.5*ρ*ν m0 2 *A, thrust is measured by the pressure sensor on the wind turbine, ν m0 is the initial wind speed at the wind turbine.

6. The method for controlling the maximum power generation of a wind turbine generator system based on artificial intelligence management according to claim 1, characterized in that: include: The measurement module is used to measure the initial speed, wake speed, fluid pressure on the wind turbine, power generation and axial induction factor of the current wind turbine; A prediction module is used to calculate the initial wind speed of the wind turbine based on real-time measurement data or derived parameters; The control module is used to control the impeller of the wind turbine to adjust the power generation and axial induction factor of the wind turbine.

7. The method for controlling the maximum power generation of a wind turbine generator system based on artificial intelligence management according to claim 6 is characterized in that: In the prediction module, the difference between the actual maximum output power of the wind turbine generator and the calculated actual maximum output power is ΔP, which is automatically recorded in the maximum output power calculation of the next wind turbine generator.

8. The method for controlling the maximum power generation of a wind turbine generator system based on artificial intelligence management according to claim 1, characterized in that: The wind speeds in steps 1 to 8 are all measured by a wind speed sensor, which is an ultrasonic wind speed sensor.

9. The method for controlling the maximum power generation of a wind turbine generator system based on artificial intelligence management according to claim 1, characterized in that: The wind turbines transmit data to each other via wireless data modules.

10. The method for controlling the maximum power generation of a wind turbine generator system based on artificial intelligence management according to claim 1, characterized in that: The air density in steps 1 to 8 is measured by a gas density sensor.

Images