Method and System for Detecting Imbalance of Wind Turbine Impeller

Abstract

The embodiment of the present invention relates to the technical field of wind turbine impeller imbalance detection, and provides a method and system for detecting the impeller imbalance of a wind turbine. The method includes: obtaining the blade sweeping audio and blade operation video when the target wind turbine is operating; calculating the energy difference degree of blade sweeping based on the blade sweeping audio, and calculating the blade zero position deviation angle value based on the blade operation video; and performing imbalance detection on the impeller of the target wind turbine based on the energy difference degree and the blade zero position deviation angle value. Thus, the impeller imbalance problem caused by zero position deviation is detected and confirmed jointly through the blade sweeping audio and blade operation video data, and the detection accuracy is high; at the same time, the blade zero position deviation angle value can be initially estimated, which helps to investigate and solve the impeller imbalance problem.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine impeller imbalance detection, and particularly to a method and system for detecting impeller imbalance of a wind turbine generator set. Background Art

[0002] With the rapid development of wind power in China, problems of wind turbine generator sets have also emerged, especially vibration faults of wind turbine generator sets, which directly affect the mechanical performance and service life of the sets. The impeller of a wind turbine generator set includes blades, a hub, and a fairing. Among them, the blades are devices for absorbing energy of the wind turbine generator set. As the power source of the wind turbine generator set, impeller imbalance will cause additional loads or load imbalance of the set. Especially with the continuous increase in the capacity of wind turbine generator sets, the blades are getting longer and longer, and the swept area, weight, and moment of inertia of the blades also increase accordingly. The impact of impeller imbalance on the performance and service life of the set is more prominent. Impeller imbalance will reduce the power generation efficiency and power curve of the wind turbine generator set, and will also cause damage to key components such as the pitch system, drive train, and yaw system. At the same time, if the impeller imbalance fault is not solved for a long time, the fault may become more serious, which will pose a great threat to the reliability and safety of the wind turbine generator set, and thus affect the service life of the wind turbine generator set. Currently, 75% of the in-service sets have impeller imbalance phenomena to varying degrees. Among them, the aerodynamic imbalance of the blades caused by non-standard zero-position calibration or installation identification errors during the blade installation process accounts for a relatively large proportion in practice; and the aerodynamic imbalance caused by zero-position deviation is also the easiest to correct. Therefore, it is of great significance to detect impeller imbalance caused by zero-position deviation.

[0003] At present, the detection methods for impeller imbalance include vibration methods, load methods, vision and clearance detection methods, etc. However, the vibration method has low measurement accuracy and cannot effectively extract characteristic signals in a timely manner. The load detection method requires accurate load measurement. At present, the maturity of load measurement technology is not high. Due to problems such as pasting technology, the measurement consistency is poor, which is prone to false measurement. The vision and clearance detection method is the main means in current measurement and detection. It mainly detects impeller imbalance problems through offline equipment or configured clearance equipment, but this online monitoring method relies on clearance equipment. Summary of the Invention

[0004] The present invention provides a method and system for detecting impeller imbalance of a wind turbine generator set to solve the defects in the prior art such as low measurement accuracy, poor measurement consistency causing false measurement, and dependence on clearance equipment, and to achieve high detection accuracy and be able to initially estimate the zero-position deviation angle value, which is helpful for troubleshooting of the fan and solving the impeller imbalance problem.

[0005] The present invention provides a method for detecting impeller imbalance of a wind turbine generator set, including:

[0006] Obtain the blade sweeping audio and blade operation video when the target wind turbine is operating;

[0007] Calculate the energy difference degree of blade sweeping based on the blade sweeping audio, and calculate the blade zero position deviation angle value based on the blade operation video;

[0008] Perform unbalance detection on the impeller of the target wind turbine based on the energy difference degree and the blade zero position deviation angle value.

[0009] In a possible implementation manner, the method further includes:

[0010] Perform audio data processing on the blade sweeping audio to obtain a spectrogram with time as the abscissa and frequency as the ordinate;

[0011] Perform graphic segmentation on the spectrogram to obtain sub-spectrograms corresponding to each blade;

[0012] Calculate the spectral energy amplitude of each blade based on the sub-spectrogram;

[0013] Calculate the energy difference degree of blade sweeping based on the spectral energy amplitude of each blade.

[0014] In a possible implementation manner, the method further includes:

[0015] Perform image segmentation on the blade operation video to obtain a first image when each blade passes through a certain fixed position of the pan-tilt camera, and the pan-tilt camera is installed on the top of the nacelle of the target wind turbine and faces the blade direction;

[0016] Perform image recognition on the first image, extract the blade contour of each blade in the corresponding first image, and calculate the area of the first pixel points of the blade within the blade contour;

[0017] Calculate the maximum difference in the area of all blade pixel points based on the area of the first pixel points of each blade;

[0018] Obtain the standard pixel point area when a standard blade without zero position deviation passes through the same fixed position of the pan-tilt camera;

[0019] Calculate the blade zero position deviation angle value based on the maximum difference in the area of all blade pixel points and the standard pixel point area.

[0020] In a possible implementation manner, the method further includes:

[0021] Preset an energy difference threshold and a deviation angle threshold; when the energy difference degree is greater than the energy difference threshold and the blade zero position deviation angle value is greater than the deviation angle threshold, it is determined that the target wind turbine has an impeller imbalance caused by a zero position deviation.

[0022] In a possible implementation, the method further includes:

[0023] Set multiple energy difference threshold levels based on the energy difference threshold, and set multiple deviation angle threshold levels based on the deviation angle threshold;

[0024] Judge the target energy difference threshold level that the energy difference degree conforms to based on the multiple energy difference threshold levels, and judge the target deviation angle threshold level that the blade zero position deviation angle value conforms to based on the multiple deviation angle threshold levels;

[0025] Determine the severity of the impeller imbalance caused by the zero position deviation of the target wind turbine based on the target energy difference threshold level and the target deviation angle threshold level.

[0026] In a possible implementation, the method further includes:

[0027] When it is detected that the target wind turbine has an impeller imbalance caused by a zero position deviation, give an early warning based on the severity.

[0028] The present invention also provides an impeller imbalance detection system for a wind turbine, including:

[0029] A pan-tilt camera, an audio sensor, and a host computer;

[0030] Wherein, the pan-tilt camera is installed on the top of the nacelle of the target wind turbine and faces the direction of the blade, and is used to collect the blade operation video when the target wind turbine is operating;

[0031] The audio sensor is installed on the tower barrel wall in the main wind direction at the bottom of the target wind turbine, and is used to collect the blade sweeping wind audio when the target wind turbine is operating;

[0032] Both the pan-tilt camera and the audio sensor are communicatively connected to the host computer. The host computer is used to obtain the blade operation video collected by the pan-tilt camera and the blade sweeping wind audio collected by the audio sensor; calculate the energy difference degree of the blade sweeping wind based on the blade sweeping wind audio, and calculate the blade zero position deviation angle value based on the blade operation video; then perform an imbalance detection on the impeller of the target wind turbine based on the energy difference degree and the blade zero position deviation angle value.

[0033] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the method for detecting the imbalance of the impeller of a wind turbine as described in any one of the above is implemented.

[0034] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for detecting the imbalance of the impeller of a wind turbine as described in any one of the above is implemented.

[0035] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the method for detecting the imbalance of the impeller of a wind turbine as described in any one of the above is implemented.

[0036] The method and system for detecting the imbalance of the impeller of a wind turbine provided by the present invention obtain the blade sweeping audio and the blade running video when the target wind turbine is operating; calculate the energy difference degree of the blade sweeping based on the blade sweeping audio, and calculate the blade zero position deviation angle value based on the blade running video; and perform the imbalance detection on the impeller of the target wind turbine based on the energy difference degree and the blade zero position deviation angle value. Compared with the existing vibration method for detecting the imbalance of the impeller with low measurement accuracy and inability to extract characteristic signals in a timely and effective manner, the load detection method with poor measurement consistency causing mismeasurement, and the visual and clearance detection method relying on clearance equipment, in this solution, the problem of impeller imbalance caused by zero position deviation is detected and confirmed jointly through the blade sweeping audio and the blade running video data, and the detection accuracy is high; at the same time, the blade zero position deviation angle value can be initially estimated, which helps to investigate and solve the problem of impeller imbalance. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0038] Figure 1 is one of the flow diagrams of the method for detecting the imbalance of the impeller of a wind turbine provided by the present invention.

[0039] Figure 2 is the second flow diagram of the method for detecting the imbalance of the impeller of a wind turbine provided by the present invention.

[0040] Figure 3 is the schematic diagram of the blade sweeping audio data provided by the present invention.

[0041] Figure 4It is the spectrogram obtained by processing the blade sweeping audio data provided by the present invention.

[0042] Figure 5 It is the image of a single blade passing through the field of view of the pan-tilt camera provided by the present invention.

[0043] Figure 6 It is the simplified diagram of the blade contour when the blade is facing the pan-tilt camera provided by the present invention.

[0044] Figure 7 It is the topology diagram of the impeller imbalance detection system of the wind turbine provided by the present invention.

[0045] Figure 8 It is the structural schematic diagram of the electronic device provided by the present invention. Specific embodiments

[0046] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts fall within the scope of protection of the present invention.

[0047] For the convenience of understanding the embodiments of the present invention, the following will further explain and illustrate with specific embodiments in conjunction with the accompanying drawings. The embodiments do not constitute a limitation to the embodiments of the present invention.

[0048] Figure 1 It is one of the flow schematic diagrams of the impeller imbalance detection method of the wind turbine provided by the present invention. As Figure 1 shown, the method includes the following:

[0049] S11. Obtain the blade sweeping audio and blade running video when the target wind turbine is operating.

[0050] Collect the blade sweeping audio during the operation of the fan through the audio sensor installed on the tower wall in the main wind direction at the bottom of the target wind turbine. Collect the blade running video during the operation of the fan through the pan-tilt camera installed on the top of the nacelle of the target wind turbine and facing the blade direction.

[0051] S12. Calculate the energy difference degree of the blade sweeping based on the blade sweeping audio, and calculate the blade zero position deviation angle value based on the blade running video.

[0052] Perform audio data processing on the blade sweeping audio to obtain a spectrogram with time as the abscissa and frequency as the ordinate; perform graphic segmentation on the spectrogram to obtain a sub-spectrogram corresponding to each blade; calculate the spectral energy amplitude of each blade based on the sub-spectrogram; calculate the energy difference degree of the blade sweeping based on the spectral energy amplitude of each blade.

[0053] In addition, perform image segmentation on the blade operation video to obtain a first image when each blade passes through a certain fixed position of the pan-tilt camera. The pan-tilt camera is installed on the top of the nacelle of the target wind turbine and faces the blade direction; perform image recognition on the first image, extract the blade contour of each blade in the corresponding first image and calculate the area of the first pixel points of the blade within the blade contour; calculate the maximum difference in the area of all blade pixel points based on the area of the first pixel points of the blade; obtain the standard pixel point area when the standard blade without zero position deviation passes through the same fixed position of the pan-tilt camera; calculate the blade zero position deviation angle value based on the maximum difference in the area of all blade pixel points and the standard pixel point area.

[0054] S13. Based on the energy difference degree and the blade zero position deviation angle value, perform unbalance detection on the impeller of the target wind turbine.

[0055] Preset an energy difference threshold and a deviation angle threshold. When the obtained energy difference degree of the blade sweeping is greater than the energy difference threshold and the blade zero position deviation angle value is greater than the deviation angle threshold, it is determined that there is an impeller imbalance situation caused by zero position deviation in the target wind turbine.

[0056] Optionally, multiple gears can also be set for both the energy difference threshold and the angle threshold, for example, two gears, namely the first gear of the energy difference threshold, the second gear of the energy difference threshold, the first gear of the angle threshold, and the second gear of the angle threshold; when the energy difference degree of the blade sweeping is greater than the first gear of the energy difference threshold and the blade zero position deviation angle value is greater than the first gear of the angle threshold, it is determined that there is a mild impeller imbalance problem caused by zero position deviation in the unit; when the energy difference degree of the blade sweeping is greater than the second gear of the energy difference threshold and the blade zero position deviation angle value is greater than the second gear of the angle threshold, it is determined that there is a severe impeller imbalance problem caused by zero position deviation in the unit.

[0057] The impeller imbalance detection method for a wind turbine provided by the present invention includes obtaining the blade sweeping audio and blade operation video during the operation of the target wind turbine; calculating the energy difference degree of blade sweeping based on the blade sweeping audio, and calculating the blade zero position deviation angle value based on the blade operation video; and performing impeller imbalance detection on the target wind turbine based on the energy difference degree and the blade zero position deviation angle value. Compared with the existing vibration method for impeller imbalance detection with low measurement accuracy and inability to effectively extract characteristic signals in a timely manner, the load detection method with poor measurement consistency causing false measurements, and the vision and clearance detection method relying on clearance equipment, this method jointly detects and confirms the impeller imbalance problem caused by zero position deviation through blade sweeping audio and blade operation video data, with high detection accuracy; at the same time, it can preliminarily estimate the zero position deviation angle value, which helps to investigate and solve the impeller imbalance problem.

[0058] Figure 2 It is the second schematic flow diagram of the impeller imbalance detection method for a wind turbine provided by the present invention. As Figure 2 shown, this method includes the following:

[0059] First, collect the blade sweeping audio during the operation of the wind turbine through an audio sensor installed on the tower barrel wall in the main wind direction at the bottom of the target wind turbine, as Figure 3 shown. Collect the blade operation video during the operation of the wind turbine through a pan-tilt camera installed on the top of the nacelle of the target wind turbine and facing the blade direction.

[0060] Furthermore, process the blade sweeping audio data to obtain a spectrogram with time as the abscissa and frequency as the ordinate, as Figure 4 shown. In the figure, 1 - the spectral characteristic peak of blade 1, 2 - the spectral characteristic peak of blade 2, 3 - the spectral characteristic peak of blade 3. Segment the spectrogram to obtain the independent sub-spectrograms of each blade, and then calculate the magnitude of the spectral energy amplitude of each blade. The spectral energy amplitudes of the three blades are respectively 、 、 .

[0061] Among them, calculate the energy difference degree of blade sweeping, and the calculation formula is as follows:

[0062]

[0063] Among them, the audio data extracts spectral characteristics after windowing and short-time Fourier transform, and the spectrogram is obtained after splicing.

[0064] Furthermore, read the blade operation video data, and through image segmentation, respectively obtain the images of the three blades when passing through a certain fixed position, as Figure 5As shown, the contours of single blades are extracted from the image respectively, as Figure 6 shown. Since the image is composed of pixel points, by calculating the number of pixel points inside the contour, a value proportional to the actual area of the blade can be obtained. The pixel areas of the three blades are respectively , , .

[0065] Furthermore, calculate the maximum difference of the pixel areas of the three blades. The calculation formula is as follows:

[0066]

[0067] Furthermore, obtain the pixel area when the blade without zero-position deviation is at the same fixed position, and calculate the blade zero-position deviation angle value θ. The calculation formula is as follows:

[0068]

[0069] The calculation principle of the blade zero-position deviation angle value θ is as follows: If the installation angle of a certain blade has a zero-position deviation, it is equivalent to that the surface of the blade facing the pan-tilt camera rotates around its pitch rotation center by an angle. If the surface contour of the blade facing the pan-tilt camera direction is simplified as a rectangle, as Figure 6 shown. The two sides of the rectangle are x and y respectively. Then the true area of the blade without zero-position deviation in the field of view of the pan-tilt camera; when the blade has a zero-position deviation of a certain angle θ, the true area of the blade with zero-position deviation in the field of view of the pan-tilt camera is , where . Assuming that when the maximum difference in the pixel areas of the three blades appears, one is the blade without zero-position deviation and the other is the blade with zero-position deviation, then it can be obtained that:

[0070] ;

[0071] That is ;

[0072] Among them: is the proportionality coefficient between the pixel area and the true area of the object, which can be obtained through the initial calibration of the blade design parameters.

[0073] Since the pixel area when the blade without zero-position deviation is at the same fixed position, then:

[0074] ;

[0075] Thus, the blade zero-position deviation angle value θ is calculated.

[0076] Further, a preset energy difference threshold and a deviation angle threshold are set. When the energy difference degree of the blade sweeping obtained above is greater than the energy difference threshold, and the blade zero position deviation angle value is greater than the deviation angle threshold, it is determined that there is an impeller imbalance caused by the zero position deviation in the target wind turbine unit.

[0077] Optionally, multiple gears can also be set for both the energy difference threshold and the angle threshold. For example, two gears, namely the first gear of the energy difference threshold, the second gear of the energy difference threshold, the first gear of the angle threshold, and the second gear of the angle threshold. When the energy difference degree of the blade sweeping is greater than the first gear of the energy difference threshold, and the blade zero position deviation angle value is greater than the first gear of the angle threshold, it is determined that there is a mild impeller imbalance problem caused by the zero position deviation in the unit. When the energy difference degree of the blade sweeping is greater than the second gear of the energy difference threshold, and the blade zero position deviation angle value is greater than the second gear of the angle threshold, it is determined that there is a severe impeller imbalance problem caused by the zero position deviation in the unit. For example, the first gear of the energy difference threshold is 0.3, the second gear of the energy difference threshold is 0.5; the first gear of the angle threshold is 1°, and the second gear of the angle threshold is 3°.

[0078] Further, when it is detected that there is an impeller imbalance situation caused by the zero position deviation in the target wind turbine unit, a warning is given based on the severity.

[0079] Compared with the prior art, the beneficial effects of the embodiments of the present invention are: (1) By jointly detecting and confirming the impeller imbalance problem caused by the zero position deviation through blade audio and blade video data, the detection accuracy is high, and the blade zero position deviation angle value can be initially estimated, which is helpful for troubleshooting the problems of the fan and solving the impeller imbalance problem.

[0080] (2) The energy difference degree of the blade sweeping is represented by the ratio of the maximum difference value of the spectral energy amplitudes of the three blades to the average value of the spectral energy amplitudes of the three blades. When the energy difference degree is greater than 0.3, it is initially determined that the impeller is mildly unbalanced; when the energy difference degree is greater than 0.5, it is initially determined that the impeller is severely unbalanced.

[0081] (3) The pixel point area when the three blades are at the same fixed position is identified through video data, and the blade zero position deviation angle value is calculated through the difference in the pixel point areas of the three blades. When the zero position deviation angle value is greater than 1°, and the energy difference degree is greater than 0.3, it is determined that the impeller is mildly unbalanced and a mild imbalance warning is issued; when the zero position deviation angle value is greater than 3°, and the energy difference degree is greater than 0.5, it is determined that the impeller is severely unbalanced and a severe imbalance warning is issued, so as to timely adjust and repair the impeller imbalance problem caused by the zero position deviation.

[0082] The impeller imbalance detection system of the wind turbine unit provided by the present invention is described below. The impeller imbalance detection system of the wind turbine unit described below can be mutually referred to with the impeller imbalance detection method of the wind turbine unit described above.

[0083] Figure 7 is the topology diagram of the impeller imbalance detection system of the wind turbine provided by the present invention. As Figure 7 shown, the system includes a pan-tilt camera 1, an audio sensor 2, an audio acquisition unit 3, and a host computer 4. As Figure 5 shown. Among them, the pan-tilt camera 1 is installed on the top of the nacelle and faces the direction of the blade, shooting the video of the blade passing through the top of the nacelle; the audio sensor 2 is installed on the tower barrel wall in the main wind direction at the bottom of the tower, and the installation height is at a position 5-10 m from the bottom of the tower, collecting the sound of the blade sweeping when passing through the audio sensor 2 during the operation of the fan; the audio acquisition unit 3 is connected to the audio sensor 2, collecting the audio data of the blade sweeping. In this embodiment, the audio acquisition unit 3 is installed at the bottom of the tower. The pan-tilt camera 1 and the audio acquisition unit 3 are both connected to the host computer 4 through the fan cloud network. The host computer 4 collects the video data and audio data and processes and analyzes them, calculates and warns the impeller balance result.

[0084] Figure 8 illustrates a schematic physical structure diagram of an electronic device. As Figure 8 shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840. Among them, the processor 810, the communication interface 820, and the memory 830 complete mutual communication through the communication bus 840. The processor 810 can call the logical instructions in the memory 830 to execute the impeller imbalance detection method of the wind turbine, and the method includes: acquiring the blade sweeping audio and the blade running video when the target wind turbine is running; calculating the energy difference degree of the blade sweeping based on the blade sweeping audio, and calculating the blade zero position deviation angle value based on the blade running video; based on the energy difference degree and the blade zero position deviation angle value, performing imbalance detection on the impeller of the target wind turbine.

[0085] In addition, when the logical instructions in the above-mentioned memory 830 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0086] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the impeller imbalance detection method for a wind turbine provided by the above-mentioned various methods. The method includes: acquiring the blade sweeping audio and blade operation video when a target wind turbine is operating; calculating the energy difference degree of blade sweeping based on the blade sweeping audio, and calculating the blade zero position deviation angle value based on the blade operation video; and performing impeller imbalance detection on the target wind turbine based on the energy difference degree and the blade zero position deviation angle value.

[0087] On another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the impeller imbalance detection method for a wind turbine provided by the above-mentioned various methods. The method includes: acquiring the blade sweeping audio and blade operation video when a target wind turbine is operating; calculating the energy difference degree of blade sweeping based on the blade sweeping audio, and calculating the blade zero position deviation angle value based on the blade operation video; and performing impeller imbalance detection on the target wind turbine based on the energy difference degree and the blade zero position deviation angle value.

[0088] The device implementation cases described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this implementation case. A person of ordinary skill in the art can understand and implement it without creative labor.

[0089] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims

1. A method for detecting the imbalance of the impeller of a wind turbine, characterized in that, include: Obtain blade sweeping audio and blade operation video of the target wind turbine when it is running; Calculate the energy difference degree of the blade sweeping wind based on the blade sweeping wind audio through the first formula, and calculate the blade zero position deviation angle value based on the blade operation video through the second formula. The first formula is: , and the second formula is: ; Among them, the spectral energy amplitudes of the three blades are respectively , , , and the maximum difference in the pixel point areas of the three blades is the pixel point area when the blade without zero position deviation is at the same fixed position;​ The calculating the energy difference of the blade sweep wind based on the blade sweep wind audio includes: Processing the blade sweeping wind audio data to obtain a frequency spectrum with time as the horizontal axis and frequency as the vertical axis; Performing graphic segmentation on the spectrum graph to obtain a sub-spectrum graph corresponding to each leaf; Calculating the spectrum energy amplitude of each leaf based on the sub-spectrum graph; Calculating the energy difference of the blade swept air based on the spectrum energy amplitude of each blade; The calculating the blade zero position deviation angle value based on the blade operation video includes: Performing image segmentation on the blade operation video to obtain a first image of each blade when it passes a fixed position of a pan-tilt camera, wherein the pan-tilt camera is installed on the top of the nacelle of the target wind turbine and faces the direction of the blade; Performing image recognition on the first image, extracting the leaf outline of each leaf in the corresponding first image, and calculating the area of a first pixel point of the leaf within the leaf outline; Calculating the maximum difference in the areas of all leaf pixels based on the area of the first pixel of each leaf; Obtaining the standard pixel area when a standard blade without zero deviation passes through the same fixed position of the pan-tilt camera; Calculating the leaf zero position deviation angle value based on the maximum difference between the areas of all leaf pixels and the standard pixel area; Performing imbalance detection on the impeller of the target wind turbine generator set based on the energy difference and the blade zero position deviation angle value; The performing imbalance detection on the impeller of the target wind turbine generator set based on the energy difference and the blade zero position deviation angle value includes: An energy difference threshold and a deviation angle threshold are preset; when the energy difference is greater than the energy difference threshold and the blade zero position deviation angle value is greater than the deviation angle threshold, it is determined that the target wind turbine has an impeller imbalance caused by zero position deviation.

2. The method according to claim 1, characterized in that, The method further comprises: Setting a plurality of energy difference threshold levels based on the energy difference threshold, and setting a plurality of deviation angle threshold levels based on the deviation angle threshold; Determining a target energy difference threshold level that the energy difference meets based on the multiple energy difference threshold levels, and determining a target deviation angle threshold level that the blade zero position deviation angle value meets based on the multiple deviation angle threshold levels; The severity of the impeller imbalance caused by the zero position deviation of the target wind turbine generator set is determined based on the target energy difference threshold level and the target deviation angle threshold level.

3. The method according to claim 2, wherein The method further comprises: When it is detected that the target wind turbine generator set has an impeller imbalance caused by a zero position deviation, an early warning is issued based on the severity.

4. An impeller imbalance detection system for a wind turbine, characterized in that, include: PTZ camera, audio sensor, host computer; The pan-tilt camera is installed on the top of the nacelle of the target wind turbine and faces the blade direction, and is used to collect blade operation video when the target wind turbine is in operation; The audio sensor is installed on the tower wall of the target wind turbine in the main wind direction at the bottom of the tower, and is used to collect the blade sweeping audio when the target wind turbine is running; The pan-tilt camera and the audio sensor are both communicatively connected to the host computer. The host computer is configured to obtain the blade operation video collected by the pan-tilt camera and the blade sweeping audio collected by the audio sensor; and calculate the energy difference degree of blade sweeping based on the blade sweeping audio through a first formula, and calculate the blade zero-position deviation angle value based on the blade operation video through a second formula. The first formula is: , and the second formula is: ; Among them, the spectral energy amplitudes of the three blades are respectively , , , and the maximum difference in the pixel point areas of the three blades is the pixel point area when the blade without zero position deviation is at the same fixed position; calculating the energy difference degree of the blade sweeping wind based on the blade sweeping wind audio includes: performing audio data processing on the blade sweeping wind audio to obtain a spectrogram with time as the abscissa and frequency as the ordinate; performing graphic segmentation on the spectrogram to obtain a sub-spectrogram corresponding to each blade; calculating the spectral energy amplitude of each blade based on the sub-spectrogram; calculating the energy difference degree of the blade sweeping wind based on the spectral energy amplitude of each blade; calculating the blade zero position deviation angle value based on the blade running video includes: performing image segmentation on the blade running video to obtain a first image when each blade passes through a certain fixed position of the pan-tilt camera, where the pan-tilt camera is installed on the top of the nacelle of the target wind turbine and faces the blade direction; performing image recognition on the first image to extract the blade contour of each blade in the corresponding first image and calculate the first pixel point area of the blade within the blade contour; calculating the maximum difference in the pixel point areas of all blades based on the first pixel point areas of each blade; obtaining the standard pixel point area when the standard blade without zero position deviation passes through the same fixed position of the pan-tilt camera; calculating the blade zero position deviation angle value based on the maximum difference in the pixel point areas of all blades and the standard pixel point area; then, based on the energy difference degree and the blade zero position deviation angle value, performing unbalance detection on the impeller of the target wind turbine; performing unbalance detection on the impeller of the target wind turbine based on the energy difference degree and the blade zero position deviation angle value includes: presetting an energy difference threshold and a deviation angle threshold; in the case where the energy difference degree is greater than the energy difference threshold and the blade zero position deviation angle value is greater than the deviation angle threshold, determining that there is an impeller imbalance situation caused by zero position deviation in the target wind turbine.

5. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, When the processor executes the computer program, the impeller imbalance detection method of the wind turbine unit according to any one of claims 1 to 3 is implemented.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the impeller imbalance detection method of the wind turbine unit according to any one of claims 1 to 3 is implemented.

7. A computer program product comprising a computer program, characterized in that When the computer program is executed by the processor, the impeller imbalance detection method of the wind turbine unit according to any one of claims 1 to 3 is implemented.

Images