Wind turbine generator self-adaptive control method, medium and system based on environmental turbulence

Abstract

The invention discloses a wind turbine generator self-adaptive control method, medium and system based on environmental turbulence, and the method comprises the steps: S1, collecting the power of a generator and the current pitch angle in the normal operation process of a wind turbine generator; s2, estimating the real-time wind speed based on the power of the generator and the inherent parameters of the unit; s3, calculating real-time environmental turbulence intensity according to the real-time estimated wind speed; s4, inputting the real-time environmental turbulence intensity and the current pitch angle into a fuzzy controller, and calculating a variable pitch control parameter coefficient according to a preset fuzzy rule; and S5, based on the variable-pitch control parameter coefficient, the variable-pitch control parameter is adjusted to carry out variable-pitch control, and self-adaptive stable operation of the unit is achieved. According to the method, no hardware needs to be additionally installed, unit load impact and rotating speed fluctuation caused by large turbulence can be effectively restrained, and on the premise that it is ensured that the limit load of key components does not exceed the limit, the operation stability of the unit is improved, the power generation loss is reduced, and cost reduction, efficiency improvement and safe and stable operation are achieved.

Description

Technical Field

[0001] This invention mainly relates to the field of wind power generation technology, specifically to an adaptive control method, medium, and system for wind turbine generators based on environmental turbulence. Background Technology

[0002] With the development of complex terrain sites, the turbulence intensity at certain sites is high, and the ultimate loads of wind turbine hubs, blades, towers, etc. are very easy to exceed the limits. Moreover, vibration over-limit faults are frequently triggered during operation, leading to shutdowns. Therefore, it is necessary to reduce power generation loss and improve the operational stability of the unit while ensuring ultimate load.

[0003] The following methods are commonly used in the industry: 1. Install vibration sensors on the engine room to monitor the overall operation of the aircraft; 2. Installing lidar to monitor wind speed and turbulence can improve the operational stability of wind turbines in complex terrain with high turbulence. However, the installation of additional hardware equipment will increase the overall cost of the unit, which is not conducive to the concept of cost reduction and efficiency improvement.

[0004] Therefore, how to develop adaptive control technology for wind turbines based on environmental turbulence from the perspective of control strategy, and improve the operational stability of the unit under complex terrain, will become an urgent problem to be solved in the overall development of the turbine. Summary of the Invention

[0005] To address the technical problems existing in the prior art, this invention provides an adaptive control method, medium, and system for wind turbines based on environmental turbulence, which achieves cost reduction, efficiency improvement, and safe and stable operation.

[0006] To solve the above-mentioned technical problems, the technical solution proposed by this invention is as follows: An adaptive control method for wind turbines based on environmental turbulence includes the following steps: S1. During normal operation of the wind turbine, the generator power and the current pitch angle are collected; S2. Based on the generator power and the inherent parameters of the unit, estimate the real-time wind speed to obtain the real-time estimated wind speed; S3. Calculate the real-time environmental turbulence intensity based on the real-time estimated wind speed; S4. Input the real-time environmental turbulence intensity and the current pitch angle into the fuzzy controller, and calculate the pitch control parameter coefficient k according to the preset fuzzy rules; S5. Based on the pitch control parameter coefficient k, adjust the pitch control parameters to perform pitch control and achieve adaptive and stable operation of the unit.

[0007] Preferably, in step S2, the inherent parameters of the unit include the rotor diameter, air density, and power coefficient.

[0008] Preferably, in step S2, the wind speed is estimated in real time. v The calculation formula is:

[0009] in, P For generator power, A For the area of ​​the wind turbine, ρ air density, Cp This is the power coefficient.

[0010] Preferably, the specific process of step S3 is as follows: Based on real-time estimated wind speed v Calculate real-time estimated wind speed v The standard deviation and mean value within a preset sliding window time are used to calculate the real-time environmental turbulence intensity. Tur .

[0011] Preferably, the real-time environmental turbulence intensity Tur The calculation formula is:

[0012] in, v This is for the real-time estimated wind speed within the preset sliding window time. std(v) This represents the standard deviation within the preset sliding window time. ave(v) This represents the average value over the preset sliding window time.

[0013] Preferably, in step S4, the fuzzy controller measures the real-time environmental turbulence intensity. Tur The real-time environmental turbulence intensity is mapped to multiple quantization levels, namely ZEt, PSt, PMt, and PBt, with ZEt, PSt, PMt, and PBt increasing in intensity sequentially. The fuzzy controller performs fuzzification processing on the pitch angle, mapping the pitch angle to multiple quantization levels, namely ZEp, PSP, PMp, and PBp, with ZEp, PSP, PMp, and PBp increasing sequentially from smallest to largest.

[0014] Preferably, in step S4, the specific process for calculating the pitch control parameter coefficient k is as follows: Based on turbulence intensity Tur and propeller pitch angle Pitch The quantization level is determined by using a fuzzy rule table to identify the output variables, which are then defuzzified to obtain the pitch control parameter coefficients. k .

[0015] Preferably, the pitch control parameters in step S5 include the proportional gain K. p Integration time T i Integral gain K i Differential gain Kd Differential time T d Gain margin G M and phase margin P M .

[0016] The present invention also discloses a computer-readable storage medium having a computer program stored thereon, the computer program performing the steps of the method described above when run by a processor.

[0017] The present invention further discloses an adaptive control system for wind turbines based on environmental turbulence, including a memory and a processor connected to each other. The memory stores a computer program, which executes the steps of the method described above when run by the processor.

[0018] Compared with the prior art, the advantages of the present invention are as follows: This invention achieves adaptive control of wind turbines in complex terrain through innovative pure software algorithms. Specifically, it utilizes existing sensor data (such as generator speed and power) to estimate wind speed in real time and accurately assess the intensity of environmental turbulence. This real-time turbulence and pitch angle are then input into a fuzzy controller. This controller, mimicking expert experience, uses fuzzification rules based on normal distribution and fuzzy inference to obtain pitch control parameter coefficients, dynamically and smoothly adjusting these parameters. This method effectively suppresses load impacts and speed fluctuations caused by high turbulence without requiring expensive hardware. Ultimately, while ensuring that the ultimate loads of key components do not exceed limits, it significantly improves the operational stability of the turbine, reduces power generation losses, and achieves the dual goals of cost reduction and efficiency improvement, as well as safe and stable operation. Attached Figure Description

[0019] Figure 1 This is a flowchart of an embodiment of the wind turbine adaptive control method based on environmental turbulence of the present invention.

[0020] Figure 2 This is a flowchart of obtaining the pitch control parameter coefficients in this invention.

[0021] Figure 3 This is a schematic diagram of the fuzzy controller in this invention.

[0022] Figure 4 The diagrams show a comparison between the control method of this invention and conventional methods; where (a) is a comparison diagram of the maximum value fluctuation of the generator speed; and (b) is a comparison diagram of the average value of the generator speed. Detailed Implementation

[0023] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0024] like Figure 1As shown in the embodiment of the present invention, the adaptive control method for wind turbines based on environmental turbulence includes the following steps: S1. During the normal operation of the wind turbine generator set, the generator power and current pitch angle are collected and preprocessed to ensure data reliability and eliminate signal interference; the preprocessing includes data cleaning, sliding window filtering and delay processing, etc. S2. Based on the preprocessed generator power and unit inherent parameters, real-time wind speed is estimated to obtain the real-time estimated wind speed. v The inherent parameters of the unit include the rotor diameter, air density, and unit power coefficient. Real-time wind speed estimation v The calculation formula is:

[0025] in, P For generator power, A This is the area of ​​the wind turbine (calculated from the wind turbine diameter). ρ air density, Cp This is the power coefficient.

[0026] S3. Estimate wind speed in real time. v Calculate the standard deviation and mean value of the turbulence over a preset sliding window time, and then calculate the real-time environmental turbulence intensity based on the standard deviation and mean value. Tur ; Real-time environmental turbulence intensity Tur The calculation formula is as follows:

[0027] in, v This is for the real-time estimated wind speed within the preset sliding window time. std(v) This represents the standard deviation within the preset sliding window time. ave(v) This represents the average value over the preset sliding window time.

[0028] S4, Real-time environmental turbulence intensity Tur The current pitch angle is input to the fuzzy control controller, which calculates the pitch control parameter coefficient k according to preset fuzzy rules, such as... Figure 2 As shown; S401. At the beginning of operation, the initial pitch control parameters T1 are set, as shown in Table 1: Table 1 Preset pitch control parameters

[0029] Among them, K p For proportional gain; T i K is the integration time; i K is the integral gain; dT is the differential gain; d For differential time; G M P represents the gain margin. M Phase margin; S402, Real-time environmental turbulence intensity Tur The current pitch angle is input to the fuzzy controller, which in turn controls the real-time environmental turbulence intensity. Tur The current pitch angle and the current propeller angle are both fuzzed; the real-time environmental turbulence intensity is also fuzzed. Tur A normal distribution model is used for fuzzification to map the real-time environmental turbulence intensity to multiple quantization levels, as shown in Table 2: Table 2 Quantification of Turbulence Intensity

[0030] Among them, ZEt, PSt, PMt, and PBt are different quantization levels, which increase in strength in turn. The horizontal axis 0.10-0.25 represents the input turbulence intensity. Combining the normal distribution, the turbulence intensity is finally mapped one-to-one with the quantization level.

[0031] Similarly, the blurring of the pitch angle maps the pitch angle to multiple quantization levels, as shown in Table 3: Table 3 Pitch Angle Quantification Grades

[0032] Among them, ZEp, PSP, PMp, and PBp are different quantization levels, in ascending order. The horizontal axis 5-20 represents the input pitch angle. Combining the normal distribution, the turbulence intensity is finally mapped one-to-one with the quantization level.

[0033] S403, Based on turbulence intensity Tur and propeller pitch angle Pitch The quantization level is determined by using a fuzzy rule table to identify the output variables, which are then defuzzified to obtain the pitch control parameter coefficients. k， like Figure 3 As shown; The fuzzy rule table is shown in Table 4: Table 4 Fuzzy Rule Table

[0034] S5. Multiply the pitch control parameter coefficient k with the initial pitch control parameter to obtain the final pitch control parameter, and perform pitch control to achieve adaptive and stable operation of the unit.

[0035] like Figure 4 As shown, the fuzzy control of the present invention is compared with conventional control, from... Figure 4As can be seen from (a), after adopting fuzzy control, the maximum fluctuation of the generator speed under the high turbulence condition of DLC1.3 is significantly reduced, demonstrating a good effect on stabilizing the speed; similarly, from Figure 4 As can be seen from (b), after adopting fuzzy control, the average fluctuation of the generator speed under the turbulent condition of dlc1.3 is also significantly reduced, which has a good effect on stabilizing the speed.

[0036] This invention achieves adaptive control of wind turbines in complex terrain through an innovative pure software algorithm. It utilizes existing sensor data (such as generator speed and power) to estimate wind speed in real time and accurately assess environmental turbulence intensity. This real-time turbulence and pitch angle are then input into a fuzzy controller. This controller, mimicking expert experience, uses fuzzy rules based on normal distribution and fuzzy inference to obtain pitch control parameter coefficients, dynamically and smoothly adjusting these parameters. This method effectively suppresses load impacts and speed fluctuations caused by high turbulence without requiring expensive hardware (such as lidar). Ultimately, while ensuring that the ultimate loads of key components do not exceed limits, it significantly improves the operational stability of the wind turbine, reduces power generation losses, and achieves the dual goals of cost reduction and efficiency improvement, as well as safe and stable operation.

[0037] The present invention also discloses a computer-readable storage medium having a computer program stored thereon, the computer program performing the steps of the method described above when run by a processor.

[0038] The present invention further discloses an adaptive control system for wind turbines based on environmental turbulence, including a memory and a processor connected to each other. The memory stores a computer program, which executes the steps of the method described above when run by the processor.

[0039] The medium and system of the present invention, corresponding to the methods described above, also have the advantages described above.

[0040] The present invention can implement all or part of the processes in the methods of the above embodiments, or it can be implemented 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, it can implement the steps of the above method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable storage medium includes: any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. The memory is used to store computer programs and / or modules. The processor implements various functions by running or executing the computer programs and / or modules stored in the memory, and by calling data stored in the memory. The memory may include high-speed random access memory, as well as non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart media cards (SMC), secure digital (SD) cards, flash cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0041] The above are merely preferred embodiments of the present invention. The scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for those skilled in the art, any improvements and modifications made without departing from the principles of the present invention should be considered within the scope of protection of the present invention.

Claims

1. An adaptive control method for wind turbine generators based on environmental turbulence, characterized in that, Including the following steps: S1. During normal operation of the wind turbine, the generator power and the current pitch angle are collected; S2. Based on the generator power and the inherent parameters of the unit, estimate the real-time wind speed to obtain the real-time estimated wind speed; S3. Calculate the real-time environmental turbulence intensity based on the real-time estimated wind speed; S4. Input the real-time environmental turbulence intensity and the current pitch angle into the fuzzy controller, and calculate the pitch control parameter coefficient k according to the preset fuzzy rules; S5. Based on the pitch control parameter coefficient k, adjust the pitch control parameters to perform pitch control and achieve adaptive and stable operation of the unit.

2. The adaptive control method for wind turbines based on environmental turbulence according to claim 1, characterized in that, In step S2, the inherent parameters of the unit include the rotor diameter, air density, and power coefficient.

3. The adaptive control method for wind turbines based on environmental turbulence according to claim 2, characterized in that, In step S2, wind speed is estimated in real time. v The calculation formula is: in, P For generator power, A For the area of ​​the wind turbine, ρ air density, Cp This is the power coefficient.

4. The adaptive control method for wind turbines based on environmental turbulence according to claim 1, 2, or 3, characterized in that, The specific process of step S3 is as follows: Based on real-time estimated wind speed v Calculate real-time estimated wind speed v The standard deviation and mean value within a preset sliding window time are used to calculate the real-time environmental turbulence intensity. Tur .

5. The adaptive control method for wind turbines based on environmental turbulence according to claim 4, characterized in that, Real-time environmental turbulence intensity Tur The calculation formula is: in, v This is for the real-time estimated wind speed within the preset sliding window time. std(v) This represents the standard deviation within the preset sliding window time. ave (v) This represents the average value over the preset sliding window time.

6. The adaptive control method for wind turbines based on environmental turbulence according to claim 1, 2, or 3, characterized in that, In step S4, the fuzzy controller measures the real-time environmental turbulence intensity. Tur The real-time environmental turbulence intensity is mapped to multiple quantization levels, namely ZEt, PSt, PMt, and PBt, with ZEt, PSt, PMt, and PBt increasing in intensity sequentially. The fuzzy controller performs fuzzification processing on the pitch angle, mapping the pitch angle to multiple quantization levels, namely ZEp, PSP, PMp, and PBp, with ZEp, PSP, PMp, and PBp increasing sequentially from smallest to largest.

7. The adaptive control method for wind turbines based on environmental turbulence according to claim 6, characterized in that, In step S4, the specific process for calculating the pitch control parameter coefficient k is as follows: Based on turbulence intensity Tur and propeller pitch angle Pitch The quantization level is determined by using a fuzzy rule table to identify the output variables, which are then defuzzified to obtain the pitch control parameter coefficients. k .

8. The adaptive control method for wind turbines based on environmental turbulence according to claim 1, 2, or 3, characterized in that, The pitch control parameters in step S5 include the proportional gain K. p Integration time T i Integral gain K i Differential gain K d Differential time T d Gain margin G M and phase margin P M .

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when run by a processor, performs the steps of the method as described in any one of claims 1-8.

10. An adaptive control system for a wind turbine based on environmental turbulence, comprising an interconnected memory and a processor, wherein the memory stores a computer program, characterized in that, The computer program, when run by a processor, performs the steps of the method as described in any one of claims 1-8.

Images