A flexible tower resonant crossing control method and device based on laser radar

By using a BP neural network model based on lidar to predict wind speed and adjust the wind turbine rotation speed, the problem of flexible tower resonance was solved, enabling safe and reliable wind turbine operation and improving power generation efficiency.

CN112814850BActive Publication Date: 2026-01-13CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202011605034.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-12-30
Publication Date
2026-01-13
Estimated Expiration
2040-12-30

AI Technical Summary

Technical Problem

The natural frequency of the flexible tower is lower than the rated rotation frequency of the rotor, which causes resonance during normal operation of the unit, seriously affecting the safety of the tower.

Method used

A flexible tower resonance crossing control method based on lidar is adopted. By predicting wind speed and adjusting the rotational speed of the wind turbine through a BP neural network model, the resonance zone is avoided. By combining the coupling relationship between rotational speed, torque and wind speed, accurate and rapid crossing is achieved.

Benefits of technology

This effectively avoids resonance in the flexible tower, reduces the load, and improves the power generation and safety of the wind turbine.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112814850B_ABST
    Figure CN112814850B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of new energy wind turbine, and particularly provides a flexible tower drum resonance crossing control method and device based on laser radar, aiming to solve the technical problem that resonance is generated during normal operation of the unit due to the fact that the natural frequency of the flexible tower drum is lower than the rated rotating frequency of the rotor, comprising: taking the wind speed collected at a preset distance from the hub height in front of the impeller of the flexible tower drum as the input of the trained BP neural network model, and obtaining the predicted wind speed at the hub height in front of the impeller of the flexible tower drum output by the trained BP neural network model; and adjusting the rotating speed of the wind turbine according to the predicted wind speed at the hub height in front of the impeller of the flexible tower drum and a preset generator torque limit value; the scheme provides a braking time for the controller, so that the unit accurately and quickly crosses the resonance zone, and the back-and-forth crossing caused by large wind speed turbulence is avoided, and the fatigue damage of the unit is increased.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new energy wind turbine, in particular to a flexible tower resonance crossing control method and device based on laser radar. BACKGROUND

[0002] In recent years, with the vigorous development of new energy, the first three types of wind energy resources in the domestic land have been basically developed, and the low wind speed of the fourth type of wind energy resources in the mountainous area will become the key area of land wind power development in China. Due to the characteristics of low wind speed, large turbulence, high wind shear and large wind direction change in this type of wind resource area, high tower wind turbine is used to improve the utilization rate of wind energy in this area and effectively increase the power generation.

[0003] In order to ensure the stiffness of the tower, the weight of the traditional tower will increase exponentially when it is higher than 100 meters, the cost of the tower will increase, and the economy will decrease. The flexible tower is favored by high tower wind turbine because of its "light" body. The first order natural frequency of the traditional tower is between the rotor rotation frequency 1P and 3P, while the first order natural frequency of the flexible tower is less than 1P (the first order frequency under the rated rotation speed of the rotor is called 1P, and the third order frequency is called 3P). The rotation frequency of the rotor of the traditional tower and the natural frequency of the tower have a certain interval, and will not cause structural resonance, but the natural frequency of the flexible tower will be lower than the rated rotation frequency of the rotor, which will cause resonance when the unit is running normally.

[0004] The resonance of the flexible tower will make the tower bear a lot of energy, the tower will shake violently, the displacement will be obvious, and the load will increase sharply, which will seriously affect the safety of the tower. SUMMARY

[0005] In order to overcome the above defects, the present application is provided to solve or at least partially solve the technical problem that the natural frequency of the flexible tower is lower than the rated rotation frequency of the rotor, which will cause resonance when the unit is running normally. The flexible tower resonance crossing control method and device based on laser radar are provided.

[0006] In a first aspect, a flexible tower resonance crossing control method based on laser radar is provided, which comprises:

[0007] The wind speed collected at the hub height of the flexible tower in front of the rotor within a preset distance is taken as the input of the trained BP neural network model, and the predicted wind speed at the hub height of the flexible tower in front of the rotor output by the trained BP neural network model is obtained.

[0008] The speed of the wind turbine is adjusted according to the predicted wind speed at the hub height of the flexible tower in front of the rotor and the preset generator torque limit value.

[0009] Preferably, the obtaining process of the trained BP neural network model comprises:

[0010] The wind speed data of the flexible tower at a preset distance in front of the impeller hub height is used as the initial BP neural network model input layer training sample, and the actual wind speed data of the flexible tower at the hub height in front of the impeller corresponding to the wind speed data is used as the initial BP neural network model output layer training sample to train the initial BP neural network model, and obtain the trained BP neural network model.

[0011] Preferably, the flexible tower hub height in front of the impeller is adjusted according to the predicted wind speed and the preset generator torque limit value, which comprises:

[0012] When the predicted wind speed at the flexible tower hub height in front of the impeller rises to WS1, the generator speed of the flexible tower is adjusted to maintain ω1;

[0013] When the predicted wind speed at the flexible tower hub height in front of the impeller rises from WS1 to WS2 and the generator torque of the flexible tower is higher than T2, the generator speed of the flexible tower is stopped adjusting, when the generator speed of the flexible tower rises to ω2, the generator speed of the flexible tower is adjusted to maintain ω2, when the generator torque of the flexible tower is again higher than T2, the generator speed of the flexible tower is controlled in the maximum power tracking mode;

[0014] When the predicted wind speed at the flexible tower hub height in front of the impeller drops to WS2, the generator speed of the flexible tower is adjusted to maintain ω2;

[0015] When the predicted wind speed at the flexible tower hub height in front of the impeller drops from WS2 to WS1 and the generator torque of the flexible tower is lower than T1, the generator speed of the flexible tower is stopped adjusting, when the generator speed of the flexible tower drops to ω1, the generator speed of the flexible tower is adjusted to maintain ω1, when the generator torque of the flexible tower is again lower than T1, the generator speed of the flexible tower is controlled in the maximum power tracking mode;

[0016] Wherein, ω1 is the generator speed corresponding to the lower limit of the preset flexible tower resonance crossing zone, ω2 is the generator speed corresponding to the upper limit of the preset flexible tower resonance crossing zone, WS1 is the lower limit of the preset wind speed, WS2 is the upper limit of the preset wind speed, T1 is the lower limit of the preset generator torque, and T2 is the upper limit of the preset generator torque.

[0017] Further, the generator speed ω1 corresponding to the lower limit of the preset flexible tower resonance crossing zone is determined by the following formula:

[0018] ω1=0.9xΩxN

[0019] The upper limit of the resonance crossing region of the preset flexible tower is determined according to the following formula:

[0020] ω2=1.1xΩxN

[0021] The lower limit of the preset wind speed WS1 is determined according to the following formula:

[0022]

[0023] The upper limit of the preset wind speed WS2 is determined according to the following formula:

[0024]

[0025] The lower limit of the preset generator torque T1 is determined according to the following formula:

[0026]

[0027] The upper limit of the preset generator torque T2 is determined according to the following formula:

[0028]

[0029] Where Ω=2xπxf, f is the natural frequency of the flexible tower, ρ is the air density, R is the radius of the wind wheel, C P is the wind energy utilization coefficient, λ is the tip speed ratio, N is the gear box speed ratio;

[0030] Preferably, the preset distance is 50m, 100m or 150m.

[0031] Preferably, the collected wind speed at the hub height of the flexible tower is collected by a laser radar installed at the hub height of the flexible tower.

[0032] In a second aspect, a laser radar-based flexible tower resonance crossing control device is provided, which comprises:

[0033] A prediction module for taking the collected wind speed at the hub height of the flexible tower as the input of the trained BP neural network model, and obtaining the predicted wind speed at the hub height of the flexible tower output by the trained BP neural network model.

[0034] An adjustment module for adjusting the speed of the wind turbine according to the predicted wind speed at the hub height of the flexible tower and the preset generator torque limit value.

[0035] Preferably, the adjustment module is specifically used for:

[0036] When the predicted wind speed at the hub height in front of the impeller of the flexible tower increases to WS1, the generator speed of the flexible tower is adjusted to maintain at ω1;

[0037] When the predicted wind speed at the hub height in front of the impeller of the flexible tower increases from WS1 to WS2 and the generator torque of the flexible tower is higher than T2, the adjustment of the generator speed of the flexible tower is stopped, when the generator speed of the flexible tower increases to ω2, the generator speed of the flexible tower is adjusted to maintain at ω2, and when the generator torque of the flexible tower is again higher than T2, the generator speed of the flexible tower is controlled in a maximum power tracking mode;

[0038] When the predicted wind speed at the hub height in front of the impeller of the flexible tower decreases to WS2, the generator speed of the flexible tower is adjusted to maintain at ω2;

[0039] When the predicted wind speed at the hub height in front of the impeller of the flexible tower decreases from WS2 to WS1 and the generator torque of the flexible tower is lower than T1, the adjustment of the generator speed of the flexible tower is stopped, when the generator speed of the flexible tower decreases to ω1, the generator speed of the flexible tower is adjusted to maintain at ω1, and when the generator torque of the flexible tower is again lower than T1, the generator speed of the flexible tower is controlled in a maximum power tracking mode;

[0040] Wherein, ω1 is the generator speed corresponding to the lower limit of the preset flexible tower resonance crossing zone, ω2 is the generator speed corresponding to the upper limit of the preset flexible tower resonance crossing zone, WS1 is the lower limit of the preset wind speed, WS2 is the upper limit of the preset wind speed, T1 is the lower limit of the preset generator torque, and T2 is the upper limit of the preset generator torque.

[0041] In a third aspect, a storage device is provided, wherein a plurality of program codes are stored in the storage device, the program codes being adapted to be loaded and run by a processor to execute the laser radar-based flexible tower resonance crossing control method according to any one of the technical solutions described above.

[0042] In a fourth aspect, a control device is provided, comprising a processor and a storage device, wherein the storage device is adapted to store a plurality of program codes, the program codes being adapted to be loaded and run by the processor to execute the laser radar-based flexible tower resonance crossing control method according to any one of the technical solutions described above.

[0043] The one or more technical solutions described above have at least one or more of the following beneficial effects:

[0044] The application provides a laser radar-based flexible tower resonant crossing control method and device, which comprises the following steps: taking the wind speed collected at a hub height in front of an impeller of a flexible tower within a preset distance as an input of a trained BP neural network model, and obtaining a predicted wind speed at the hub height in front of the impeller of the flexible tower output by the trained BP neural network model; and adjusting the rotating speed of a wind turbine generator according to the predicted wind speed at the hub height in front of the impeller of the flexible tower and a preset generator torque limit value. The scheme can give a main control time through the wind speed predicted in advance, can make the unit accurately and quickly cross the resonance zone, can avoid frequent back-and-forth crossing caused by large wind speed turbulence, can increase the fatigue damage of the unit, can increase the accuracy of crossing by combining the rotating speed, torque and wind speed coupling relationship, can avoid back-and-forth crossing caused by large turbulence wind speed, can quickly and accurately cross the crossing zone, can avoid the number of back-and-forth crossing, and can achieve the dual purposes of reducing load and improving power. BRIEF DESCRIPTION OF DRAWINGS

[0045] Figure 1 FIG. 1 is a main step flow schematic diagram of a laser radar-based flexible tower resonant crossing control method according to an embodiment of the application;

[0046] Figure 2 FIG. 4 is an application scenario schematic diagram of the application;

[0047] Figure 3 FIG. 5 is a main structure block diagram of a laser radar-based flexible tower resonant crossing control device according to an embodiment of the application. DETAILED DESCRIPTION

[0048] The specific embodiments of the application will be further described in detail below with reference to the accompanying drawings.

[0049] To make the objectives, technical solutions and advantages of the embodiments of the application clearer, the technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings of the embodiments of the application. Obviously, the described embodiments are some but not all of the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the application.

[0050] Reference is made to the accompanying Figure 1 , Figure 1 FIG. 1 is a main step flow schematic diagram of a laser radar-based flexible tower resonant crossing control method according to an embodiment of the application. As shown in FIG. 1, the laser radar-based flexible tower resonant crossing control method in the embodiment of the application mainly comprises the following steps: Figure 1

[0051] ​Step S101: taking the wind speed collected at the hub height of the flexible tower at a preset distance in front of the impeller as an input of the trained BP neural network model, and obtaining the predicted wind speed at the hub height of the flexible tower in front of the impeller output by the trained BP neural network model;

[0052] Step S102: adjusting the rotating speed of the wind turbine generator according to the predicted wind speed at the hub height of the flexible tower in front of the impeller and a preset generator torque limit value.

[0053] In the embodiment, the wind speed collected at the hub height of the flexible tower at a preset distance in front of the impeller is collected by a laser radar installed at the hub height of the flexible tower at a preset distance in front of the impeller. The laser radar anemometer has high space-time resolution and sensitivity, and strong anti-interference ability. Further, the wind speed at a certain distance in front of the impeller at the hub height is measured based on the laser radar anemometer, the incoming flow wind speed at the wind wheel is predicted in advance, and the main control operation instruction is given in advance. The preset distance is 50 m, 100 m or 150 m.

[0054] In one embodiment, the obtaining process of the trained BP neural network model comprises:

[0055] The wind speed data collected at the hub height of the flexible tower at a preset distance in front of the impeller is taken as an input layer training sample of an initial BP neural network model, and the actual wind speed data at the hub height of the flexible tower in front of the impeller corresponding to the wind speed data is taken as an output layer training sample of the initial BP neural network model, the initial BP neural network model is trained, and the trained BP neural network model is obtained.

[0056] Further, in another embodiment of the present application, the trained BP neural network model can be obtained by the following steps:

[0057] 1) A radar anemometer is installed on the top of the wind turbine generator cabin, and the wind speed at 50 m, 100 m, 150 m in front of the impeller at the hub height is collected, which is respectively set as V(t+x0), V(t+x1) and V(t+x2).

[0058] 2) V(t+x1) is taken as an input, V(t+x0) is taken as an output, a period of data is collected as a training sample, a BP neural network model about V(t+x1) and V(t+x0) is constructed, and a prediction model of V(t+x0) = f(V(t+x1)) is obtained.

[0059] 3) Determine the correctness and extendibility of the model. Select another period of collected data, and use the prediction model relationship in 2) to verify that V(t+x0) is consistent with its predicted value; assuming that the evolution of the wind from one point to another within the measurement range of the laser radar is a time-dependent relationship that does not change, the prediction model in 2) is used to the relationship of V(t+x1) and V(t+x2) (V(t+x1) is the output value, and V(t+x2) is the input value), and it is also found that V(t+x1) is consistent with its predicted value, i.e., the correctness and extendibility of the prediction model are determined.

[0060] 4) As can be seen from 3), for V(t) (the wind speed at the wind wheel, 0 m in front of the wind wheel), the BP prediction model of V(t)=f(V(t+x0)) can be accurately obtained in advance, and further, the main control operation command can be given in advance according to the predicted V(t) value (the wind speed involved in the generator control strategy is the predicted V(t)).

[0061] In the embodiment, considering the coupling relationship between the rotation speed, torque and wind speed, step S102 is adopted to quickly and accurately pass through the passing zone. Specifically, the rotation speed of the wind turbine is adjusted according to the predicted wind speed at the hub height in front of the impeller of the flexible tower and the preset generator torque limit value, and the method comprises the following steps.

[0062] When the predicted wind speed at the hub height in front of the impeller of the flexible tower rises to WS1, the rotation speed of the generator of the flexible tower is adjusted and maintained at ω1;

[0063] When the predicted wind speed at the hub height in front of the impeller of the flexible tower rises from WS1 to WS2 and the generator torque of the flexible tower is higher than T2, the rotation speed of the generator of the flexible tower is stopped adjusting, when the rotation speed of the generator of the flexible tower rises to ω2, the rotation speed of the generator of the flexible tower is adjusted and maintained at ω2, and when the generator torque of the flexible tower is higher than T2 again, the rotation speed of the generator of the flexible tower is controlled in a maximum power tracking mode;

[0064] In one application scenario, for example, Figure 2As shown, when the predicted wind speed rises, the generator speed of the flexible tower is maintained at ω1, the generator speed of the flexible tower is in the region A-B, the wind turbine adopts the conventional optimal power (optimal tip speed ratio) tracking control, the speed is controlled so that the wind wheel can maximize the wind energy to improve the power generation of the unit. When the generator speed reaches the lower limit B, the speed is maintained at the lower limit value by the PID controller, and as the wind speed increases, the torque starts to increase along B-C. When the torque exceeds the predetermined upper limit T2 and the predicted wind speed exceeds the upper limit WS2, the PID controller stops controlling the speed, and the generator speed starts to increase under the dual action of the wind speed and the torque, quickly traverses the resonance region along CD, at this time the wind turbine again adopts the conventional optimal power (optimal tip speed ratio) tracking control, and completes the upward traversal process.

[0065] When the predicted wind speed at the hub height in front of the impeller of the flexible tower drops to WS2, the generator speed of the flexible tower is maintained at ω2;

[0066] When the predicted wind speed at the hub height in front of the impeller of the flexible tower drops from WS2 to WS1 and the generator torque of the flexible tower is lower than T1, the generator speed of the flexible tower is stopped, and when the generator speed of the flexible tower drops to ω1, the generator speed of the flexible tower is maintained at ω1, and when the generator torque of the flexible tower is lower than T1 again, the generator speed of the flexible tower is controlled in the maximum power tracking mode;

[0067] Wherein, ω1 is the generator speed corresponding to the lower limit of the preset flexible tower resonance traversal region, ω2 is the generator speed corresponding to the upper limit of the preset flexible tower resonance traversal region, WS1 is the lower limit of the preset wind speed, WS2 is the upper limit of the preset wind speed, T1 is the lower limit of the preset generator torque, and T2 is the upper limit of the preset generator torque.

[0068] In one application scenario, as shown in Figure 2 As shown, when the wind speed drops, the torque drops, and the generator speed drops. When the torque of the generator is lower than the upper limit T2 of the resonance traversal region (i.e., point E), the PID controller starts again to fix the generator speed, because the generator torque will continue to drop due to the drop of the wind speed, and when the torque drops to D point and the wind speed is less than WS1, the PID controller is stopped, at this time because the wind speed is low and the speed is too high, the wind energy absorbed cannot guarantee the high speed load of the unit, so the speed drops rapidly, the torque rises along the D-C segment, and quickly traverses the resonance region, at this time the wind turbine again adopts the conventional optimal power (optimal tip speed ratio) tracking control, and completes the downward traversal process.

[0069] In one embodiment, the generator speed ω1 corresponding to the lower limit of the preset flexible tower resonance traversal region is determined as follows:

[0070] ω1= 0.9 x Ω x N

[0071] The upper limit of the resonance crossing region of the preset flexible tower is determined by the following formula:

[0072] ω2= 1.1 x Ω x N

[0073] The lower limit of the preset wind speed WS1 is determined by the following formula:

[0074]

[0075] The upper limit of the preset wind speed WS2 is determined by the following formula:

[0076]

[0077] The lower limit of the preset generator torque T1 is determined by the following formula:

[0078]

[0079] The upper limit of the preset generator torque T2 is determined by the following formula:

[0080]

[0081] where Ω = 2 x π x f, f is the natural frequency of the flexible tower, p is the air density, R is the wind wheel radius, C P is the wind energy utilization coefficient, λ is the tip speed ratio, and N is the gear box speed ratio.

[0082] It should be noted that although the above embodiments describe the steps in a specific order, those skilled in the art can understand that in order to achieve the effect of the present application, the steps do not have to be executed in this order, they can be executed simultaneously (in parallel) or in other order, and these changes are within the scope of protection of the present application.

[0083] Referring to the accompanying Figure 3 , Figure 3 is the main structure diagram of the laser radar-based flexible tower resonance crossing control device according to an embodiment of the present application. As shown in Figure 3 , the laser radar-based flexible tower resonance crossing control device in the embodiment of the present application mainly includes a prediction module and an adjustment module. In some embodiments, the prediction module and the adjustment module can be combined together into one module. In some embodiments, the prediction module can be configured to perform the step S101. The adjustment module can be configured to perform the step S102.

[0084] Specifically, the process of obtaining the trained BP neural network model includes:

[0085] The wind speed data of a preset distance from the front of the impeller of the flexible tower at the hub height is taken as the input layer training sample of the initial BP neural network model, and the actual wind speed data of the flexible tower at the hub height corresponding to the wind speed data is taken as the output layer training sample of the initial BP neural network model, so as to train the initial BP neural network model and obtain the trained BP neural network model.

[0086] Preferably, the adjustment module is specifically used for:

[0087] When the predicted wind speed at the hub height in front of the impeller of the flexible tower rises to WS1, the generator speed of the flexible tower is adjusted and maintained at ω1.

[0088] When the predicted wind speed at the hub height in front of the impeller of the flexible tower rises from WS1 to WS2 and the generator torque of the flexible tower is higher than T2, the adjustment of the generator speed of the flexible tower is stopped, when the generator speed of the flexible tower rises to ω2, the generator speed of the flexible tower is adjusted and maintained at ω2, and when the generator torque of the flexible tower is again higher than T2, the generator speed of the flexible tower is controlled in the maximum power tracking mode.

[0089] When the predicted wind speed at the hub height in front of the impeller of the flexible tower drops to WS2, the generator speed of the flexible tower is adjusted and maintained at ω2.

[0090] When the predicted wind speed at the hub height in front of the impeller of the flexible tower drops from WS2 to WS1 and the generator torque of the flexible tower is lower than T1, the adjustment of the generator speed of the flexible tower is stopped, when the generator speed of the flexible tower drops to ω1, the generator speed of the flexible tower is adjusted and maintained at ω1, and when the generator torque of the flexible tower is again lower than T1, the generator speed of the flexible tower is controlled in the maximum power tracking mode.

[0091] Wherein, ω1 is the generator speed corresponding to the lower limit of the preset flexible tower resonance crossing zone, ω2 is the generator speed corresponding to the upper limit of the preset flexible tower resonance crossing zone, WS1 is the lower limit of the preset wind speed, WS2 is the upper limit of the preset wind speed, T1 is the lower limit of the preset generator torque, and T2 is the upper limit of the preset generator torque.

[0092] Further, the generator speed ω1 corresponding to the lower limit of the preset flexible tower resonance crossing zone is determined according to the following formula:

[0093] ω1 = 0.9 × Ω × N

[0094] The generator speed ω2 corresponding to the upper limit of the preset flexible tower resonance crossing zone is determined according to the following formula:

[0095] ω2 = 1.1 x Ω x N

[0096] The preset lower limit of wind speed WS1 is determined by the following formula:

[0097]

[0098] The preset upper limit of wind speed WS2 is determined by the following formula:

[0099]

[0100] The preset lower limit of generator torque T1 is determined by the following formula:

[0101]

[0102] The preset upper limit of generator torque T2 is determined by the following formula:

[0103]

[0104] Wherein, Ω = 2 x π x f, f is the natural frequency of the flexible tower, p is the air density, R is the wind wheel radius, C P is the wind energy utilization coefficient, λ is the tip speed ratio, N is the gear box speed ratio;

[0105] Preferably, the preset distance is 50 m, 100 m or 150 m.

[0106] Preferably, the collected wind speed at the preset distance from the hub height in front of the impeller of the flexible tower is collected by a laser radar installed at the preset distance from the hub height in front of the impeller of the flexible tower.

[0107] Those skilled in the art can understand that all or part of the processes in the method of the above-mentioned embodiment can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms, etc. The computer readable medium can include any entity or device, medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal and software distribution medium, etc. that can carry the computer program code. It should be noted that the contents included in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

[0108] Further, the present application also provides a storage device. In an embodiment of the storage device according to the present application, the storage device can be configured to store a program of the laser radar based flexible tower resonant crossing control method as described above, which can be loaded and run by the processor to implement the laser radar based flexible tower resonant crossing control method as described above. For the convenience of description, only the parts related to the embodiments of the present application are shown, and the specific technical details not disclosed are referred to the method part of the embodiments of the present application. The storage device can be a storage device device formed by various electronic devices, and optionally, the storage in the embodiments of the present application is a non-transitory computer readable storage medium.

[0109] Further, the present application also provides a control device. In an embodiment of the control device according to the present application, the control device comprises a processor and a storage device, and the storage device can be configured to store a program of the laser radar based flexible tower resonant crossing control method as described above, and the processor can be configured to execute the program in the storage device, which includes but is not limited to the program of the laser radar based flexible tower resonant crossing control method as described above. For the convenience of description, only the parts related to the embodiments of the present application are shown, and the specific technical details not disclosed are referred to the method part of the embodiments of the present application. The control device can be a control device device formed by various electronic devices.

[0110] Further, it should be understood that, since the setting of each module is only for illustrating the functional units of the system of the present application, the physical device corresponding to the module can be the processor itself, or a part of software in the processor, a part of hardware, or a part of combination of software and hardware.

[0111] Those skilled in the art can understand that each module in the system can be adaptively split or combined. Such splitting or combining of the specific module does not cause the technical solution to deviate from the principles of the present application, and therefore, the technical solution after splitting or combining will fall within the protection scope of the present application.

[0112] So far, the technical solution of the present application has been described in combination with one embodiment shown in the drawings, but those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without deviating from the principles of the present application, and the technical solution after the changes or replacements will fall within the protection scope of the present application.

Claims

1. A flexible tower resonance crossing control method based on lidar, characterized in that, The method includes: The wind speed at a preset distance from the hub height in front of the impeller of the flexible tower is collected as the input of the trained BP neural network model, and the predicted wind speed at the hub height in front of the impeller of the flexible tower is obtained from the output of the trained BP neural network model. The wind turbine speed is adjusted according to the predicted wind speed at the height of the impeller hub in front of the flexible tower and the preset generator torque limit. The adjustment of the wind turbine speed based on the predicted wind speed at the height of the impeller hub in front of the flexible tower and the preset generator torque limit includes: When the predicted wind speed at the hub height in front of the impeller of the flexible tower rises to At that time, the generator speed of the flexible tower is maintained at... ; When the predicted wind speed at the hub height in front of the impeller of the flexible tower is... Rise to Furthermore, the generator torque of the flexible tower is higher than... Stop adjusting the generator speed of the flexible tower. When the generator speed of the flexible tower rises to... At that time, the generator speed of the flexible tower is maintained at... When the generator torque of the flexible tower is again higher than At that time, the generator speed of the flexible tower is controlled by maximum power point tracking. When the predicted wind speed at the hub height in front of the impeller of the flexible tower drops to At that time, the generator speed of the flexible tower is maintained at... ; When the predicted wind speed at the hub height in front of the impeller of the flexible tower is... Descending to Furthermore, the generator torque of the flexible tower is lower than... Stop adjusting the generator speed of the flexible tower. When the generator speed of the flexible tower drops to... At that time, the generator speed of the flexible tower is maintained at... When the generator torque of the flexible tower is again lower than At that time, the generator speed of the flexible tower is controlled by maximum power point tracking. in, The generator speed corresponding to the lower limit of the resonance crossing zone of the preset flexible tower is set. The generator speed corresponding to the upper limit of the resonance crossing zone of the preset flexible tower is set. This is the lower limit of the preset wind speed. To preset the upper limit of wind speed, To preset the lower limit of generator torque, The preset generator torque upper limit; The generator speed corresponding to the lower limit of the resonance crossing zone of the preset flexible tower is determined by the following formula. : The generator speed corresponding to the upper limit of the resonance crossing zone of the preset flexible tower is determined by the following formula. : The preset lower limit of wind speed is determined by the following formula. : The preset wind speed upper limit WS2 is determined by the following formula: The preset generator torque lower limit T1 is determined by the following formula: The preset upper limit of generator torque T2 is determined by the following formula: in, , f The natural frequency of the flexible tower. air density, Where is the radius of the wind turbine. The wind energy utilization coefficient, For the tip speed ratio, This is the gearbox speed ratio.

2. The method as described in claim 1, characterized in that, The process of obtaining the trained BP neural network model includes: The initial BP neural network model is trained by using wind speed data at a predetermined distance from the hub in front of the impeller of the flexible tower, which is collected in advance, as the input layer training sample. The actual wind speed data at the hub height in front of the impeller of the flexible tower corresponding to the wind speed data is used as the output layer training sample. The trained BP neural network model is obtained.

3. The method as described in claim 1, characterized in that, The preset distance is 50m, 100m or 150m.

4. The method as described in claim 1, characterized in that, The wind speed at a predetermined distance from the hub height in front of the impeller of the flexible tower is collected using a lidar sensor installed at the predetermined distance from the hub height in front of the impeller of the flexible tower.

5. A flexible tower resonance crossing control device based on lidar, characterized in that, The device includes: The prediction module is used to take the wind speed at a preset distance from the hub height in front of the impeller of the flexible tower as the input of the trained BP neural network model, and obtain the predicted wind speed at the hub height in front of the impeller of the flexible tower as the output of the trained BP neural network model. The adjustment module is used to adjust the speed of the wind turbine based on the predicted wind speed at the height of the impeller hub in front of the flexible tower and the preset generator torque limit. The adjustment module is specifically used for: When the predicted wind speed at the hub height in front of the impeller of the flexible tower rises to At that time, the generator speed of the flexible tower is maintained at... ; When the predicted wind speed at the hub height in front of the impeller of the flexible tower is... Rise to Furthermore, the generator torque of the flexible tower is higher than... Stop adjusting the generator speed of the flexible tower. When the generator speed of the flexible tower rises to... At that time, the generator speed of the flexible tower is maintained at... When the generator torque of the flexible tower is again higher than At that time, the generator speed of the flexible tower is controlled by maximum power point tracking. When the predicted wind speed at the hub height in front of the impeller of the flexible tower drops to At that time, the generator speed of the flexible tower is maintained at... ; When the predicted wind speed at the hub height in front of the impeller of the flexible tower is... Descending to Furthermore, the generator torque of the flexible tower is lower than... Stop adjusting the generator speed of the flexible tower. When the generator speed of the flexible tower drops to... At that time, the generator speed of the flexible tower is maintained at... When the generator torque of the flexible tower is again lower than At that time, the generator speed of the flexible tower is controlled by maximum power point tracking. in, The generator speed corresponding to the lower limit of the resonance crossing zone of the preset flexible tower is set. The generator speed corresponding to the upper limit of the resonance crossing zone of the preset flexible tower is set. This is the lower limit of the preset wind speed. To preset the upper limit of wind speed, To preset the lower limit of generator torque, The preset generator torque upper limit; The generator speed corresponding to the lower limit of the resonance crossing zone of the preset flexible tower is determined by the following formula. : The generator speed corresponding to the upper limit of the resonance crossing zone of the preset flexible tower is determined by the following formula. : The preset lower limit of wind speed is determined by the following formula. : The preset wind speed upper limit WS2 is determined by the following formula: The preset generator torque lower limit T1 is determined by the following formula: The preset upper limit of generator torque T2 is determined by the following formula: in, , f The natural frequency of the flexible tower. air density, Where is the radius of the wind turbine. The wind energy utilization coefficient, For the tip speed ratio, This is the gearbox speed ratio.

6. A storage device storing a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by a processor to perform the lidar-based flexible tower resonance crossing control method as described in any one of claims 1 to 4.

7. A control device, comprising a processor and a storage device, said storage device being adapted to store a plurality of program codes, characterized in that, The program code is adapted to be loaded and run by the processor to perform the lidar-based flexible tower resonance crossing control method as described in any one of claims 1 to 4.

Citation Information

Patent Citations

  • Wind turbine generator control method, controller and control system of wind turbine generator

    CN102797629A

  • Wind speed prediction method and apparatus based on NARX neural network

    CN105590144A