Impeller unbalance detection method and system of wind turbine generator

Abstract

The embodiment of the invention relates to the technical field of impeller unbalance detection of wind turbine generators, and provides an impeller unbalance detection method and system for a wind turbine generator, and the method comprises the steps: obtaining a blade wind sweeping audio and a blade operation video during the operation of a target wind turbine generator; calculating an energy difference degree of blade wind sweeping based on the blade wind sweeping audio, and calculating a blade zero deviation angle value based on the blade operation video; and on the basis of the energy difference degree and the blade zero deviation angle value, performing unbalance detection on an impeller of the target wind turbine generator. Therefore, the impeller imbalance problem caused by the zero deviation is detected and confirmed through the blade wind sweeping audio and the blade operation video data, and the detection accuracy is high; and meanwhile, the zero deviation angle value can be preliminarily estimated, and the impeller imbalance problem can be checked and solved easily.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine impeller imbalance detection, and in particular to a wind turbine impeller imbalance detection method and system. Background Art

[0002] With the rapid development of wind power in China, the problem of wind turbine failure has also come along, especially the vibration failure of wind turbines, which directly affects the mechanical performance and life of the unit. The impeller of a wind turbine includes blades, hubs and fairings. The blades are the device for absorbing energy of the wind turbine. As the power source of the wind turbine, the unbalanced impeller will cause the unit to generate additional load or load imbalance. In particular, with the continuous increase in the capacity of wind turbines, the blades are getting longer and longer, and the swept area, weight and moment of inertia of the blades are also increasing. The impact of impeller imbalance on the performance and life of the unit is more prominent. Impeller imbalance will reduce the power generation efficiency and power curve of the wind turbine, and will also cause damage to key components such as the pitch system, transmission chain, and yaw system. At the same time, if the impeller imbalance fault is not resolved 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, and thus affect the service life of the wind turbine. Currently, 75% of the units in service have varying degrees of impeller imbalance. Among them, aerodynamic imbalance of blades caused by pitch angle deviation due to improper zero-position calibration or installation identification errors during blade installation accounts for a large proportion in practice; and, since the aerodynamic imbalance caused by zero-position deviation is also the easiest to correct, it is of great significance to detect impeller imbalance caused by zero-position deviation.

[0003] At present, there are several detection methods for impeller imbalance, including vibration method, load method, visual and clearance detection method. 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 load measurement technology is not mature enough. Due to problems such as the pasting process, the measurement consistency is poor, which can easily lead to mismeasurement. The visual and clearance detection method is the main means of measurement and detection at present. It mainly detects impeller imbalance problems through offline equipment or configuration of clearance equipment, but this online monitoring method needs to rely on clearance equipment. Summary of the invention

[0004] The present invention provides a method and system for detecting impeller imbalance of a wind turbine, which are used to solve the defects of low measurement accuracy, poor measurement consistency causing erroneous measurement, and dependence on clearance equipment in the prior art, achieve high detection accuracy, and can preliminarily estimate the zero-position deviation angle value, which is helpful for troubleshooting wind turbine problems and solving impeller imbalance problems.

[0005] The present invention provides a method for detecting an unbalanced impeller of a wind turbine generator set, comprising: Acquire the blade sweeping audio and blade operation video of the target wind turbine when it is running; Calculate the energy difference of the blade sweep wind based on the blade sweep wind audio, and calculate the blade zero position deviation angle value based on the blade operation video; Based on the energy difference and the blade zero position deviation angle value, an imbalance detection is performed on the impeller of the target wind turbine generator set.

[0006] In a possible implementation, the method further includes: Performing audio data processing on the blade sweeping wind audio to obtain a frequency spectrum diagram with time as the horizontal axis and frequency as the vertical axis; Performing graphic segmentation on the frequency spectrum to obtain a sub-frequency spectrum corresponding to each leaf; Calculating the spectrum energy amplitude of each leaf based on the sub-spectrum graph; The energy difference of the blade swept wind is calculated based on the spectrum energy amplitude of each blade.

[0007] In a possible implementation, the method further 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 contour of each leaf in the corresponding first image, and calculating the first pixel point area of ​​the leaf within the leaf contour; Calculating the maximum difference of the pixel point areas of all leaves based on the first pixel point area of ​​each leaf; Obtaining the standard pixel area when a standard blade without zero position deviation passes through the same fixed position of the pan-tilt camera; The blade zero position deviation angle value is calculated based on the maximum difference of all blade pixel point areas and the standard pixel point area.

[0008] In a possible implementation, the method further 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 a zero-position deviation.

[0009] In a possible implementation, the method further includes: 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; Determine the target energy difference threshold level that the energy difference degree meets based on the multiple energy difference threshold levels, and determine the 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 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.

[0010] In a possible implementation, the method further includes: When it is detected that the target wind turbine has an impeller imbalance caused by a zero position deviation, an early warning is issued based on the severity.

[0011] The present invention also provides a wind turbine impeller imbalance detection system, comprising: 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 at the bottom of the target wind turbine in the main wind direction, and is used to collect the blade sweeping audio when the target wind turbine is running; The gimbal camera and the audio sensor are both communicatively connected to the host computer, and the host computer is used to obtain the blade operation video collected by the gimbal camera and the blade wind sweeping audio collected by the audio sensor; and calculate the energy difference of the blade wind sweeping based on the blade wind sweeping audio, and calculate the blade zero position deviation angle value based on the blade operation video; and then based on the energy difference and the blade zero position deviation angle value, perform imbalance detection on the impeller of the target wind turbine.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the impeller imbalance detection method for a wind turbine set as described in any one of the above is implemented.

[0013] 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 impeller imbalance detection method for a wind turbine set as described in any one of the above methods is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the impeller imbalance detection method for a wind turbine set as described in any one of the above is implemented.

[0015] The impeller imbalance detection method and system of the wind turbine provided by the present invention obtains the blade sweeping audio and blade running video when the target wind turbine is running; calculates the energy difference of the blade sweeping based on the blade sweeping audio, and calculates the blade zero position deviation angle value based on the blade running video; and performs imbalance detection on the impeller of the target wind turbine based on the energy difference and the blade zero position deviation angle value. Compared with the existing impeller imbalance detection vibration method, which has low measurement accuracy and cannot effectively extract characteristic signals in time, the load detection method has poor measurement consistency and causes mismeasurement, and the visual and clearance detection method relies on the defects of clearance equipment, this scheme jointly detects and confirms the impeller imbalance problem caused by zero position deviation through the blade sweeping audio and blade running video data, and has high detection accuracy; at the same time, it can preliminarily estimate the zero position deviation angle value, which is helpful for the investigation and resolution of impeller imbalance problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 This is one of the flow charts of the impeller imbalance detection method for a wind turbine provided by the present invention.

[0018] Figure 2 This is the second flow chart of the impeller imbalance detection method for a wind turbine provided by the present invention.

[0019] Figure 3 It is a schematic diagram of blade sweeping audio data provided by the present invention.

[0020] Figure 4 It is a frequency spectrum diagram obtained by processing the blade sweeping audio data provided by the present invention.

[0021] Figure 5 This is the image of a single blade provided by the present invention when it passes through the field of view of the pan-tilt camera.

[0022] Figure 6 It is a simplified diagram of the blade profile when the blade provided by the present invention is facing the pan-tilt camera.

[0023] Figure 7 It is a topological diagram of the impeller imbalance detection system of the wind turbine set provided by the present invention.

[0024] Figure 8 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] To facilitate the understanding of the implementation cases of the present invention, the following will further explain and illustrate specific implementation cases in conjunction with the accompanying drawings. The implementation cases do not constitute a limitation on the implementation cases of the present invention.

[0027] Figure 1 FIG. 1 is a flow chart of a method for detecting an unbalanced impeller of a wind turbine provided by the present invention. Figure 1 As shown, the method includes the following: S11, obtaining blade sweeping audio and blade operation video when the target wind turbine is in operation.

[0028] The audio sensor installed on the tower wall in the main wind direction at the bottom of the target wind turbine collects the blade sweeping audio when the wind turbine is running. The pan-tilt camera installed on the top of the nacelle of the target wind turbine and facing the blade direction collects the blade running video when the wind turbine is running.

[0029] S12, calculating the energy difference of the blade sweeping wind based on the blade sweeping wind audio, and calculating the blade zero position deviation angle value based on the blade operation video.

[0030] The audio data of the blade wind sweeping is processed to obtain a spectrum diagram with time as the horizontal axis and frequency as the vertical axis; the spectrum diagram is graphically segmented to obtain a sub-spectrum diagram corresponding to each blade; the spectrum energy amplitude of each blade is calculated based on the sub-spectrum diagram; the energy difference of the blade wind sweeping is calculated based on the spectrum energy amplitude of each blade.

[0031] And, perform 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 cabin of the target wind turbine and faces the direction of the blade; perform image recognition on the first image, 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; calculate the maximum difference in the pixel point areas of all blades based on the first pixel point area of ​​the blade; obtain the standard pixel point area of ​​a standard blade without zero deviation when it passes the same fixed position of the pan-tilt camera; calculate the blade zero deviation angle value based on the maximum difference in the pixel point areas of all blades and the standard pixel point area.

[0032] S13. Based on the energy difference and the blade zero position deviation angle value, perform imbalance detection on the impeller of the target wind turbine generator set.

[0033] An energy difference threshold and a deviation angle threshold are preset. When the energy difference of the blade swept wind 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 the target wind turbine has an impeller imbalance caused by zero-position deviation.

[0034] Optionally, the energy difference threshold and the angle threshold can be set to multiple levels, for example, two levels, namely energy difference threshold level 1, energy difference threshold level 2, angle threshold level 1 and angle threshold level 2; when the energy difference of the blade swept air is greater than the energy difference threshold level 1, and the blade zero position deviation angle value is greater than the angle threshold level 1, it is judged that the unit has a slight impeller imbalance problem caused by the zero position deviation; when the energy difference of the blade swept air is greater than the energy difference threshold level 2, and the blade zero position deviation angle value is greater than the angle threshold level 2, it is judged that the unit has a severe impeller imbalance problem caused by the zero position deviation.

[0035] The impeller imbalance detection method of the wind turbine provided by the present invention obtains the blade sweeping audio and blade running video when the target wind turbine is running; calculates the energy difference of the blade sweeping based on the blade sweeping audio, and calculates the blade zero position deviation angle value based on the blade running video; and performs imbalance detection on the impeller of the target wind turbine based on the energy difference and the blade zero position deviation angle value. Compared with the existing impeller imbalance detection vibration method, which has low measurement accuracy and cannot effectively extract characteristic signals in time, the load detection method has poor measurement consistency and causes mismeasurement, and the visual and clearance detection method relies on the defects of clearance equipment, this method jointly detects and confirms the impeller imbalance problem caused by zero position deviation through the blade sweeping audio and blade running video data, and has high detection accuracy; at the same time, it can preliminarily estimate the zero position deviation angle value, which is helpful for the investigation and resolution of the impeller imbalance problem.

[0036] Figure 2 FIG. 2 is a flow chart of the impeller imbalance detection method for a wind turbine provided by the present invention. Figure 2 As shown, the method includes the following: First, the audio sensor installed on the tower wall in the main wind direction at the bottom of the target wind turbine collects the blade sweeping audio when the wind turbine is running, such as Figure 3 The blade operation video of the wind turbine is collected by a pan / tilt camera installed on the top of the nacelle of the target wind turbine and facing the blade direction.

[0037] Furthermore, the blade sweeping audio data is processed to obtain a spectrum diagram with time as the horizontal axis and frequency as the vertical axis, such as Figure 4As shown in the figure, 1-the characteristic peak of the spectrum of blade 1, 2-the characteristic peak of the spectrum of blade 2, and 3-the characteristic peak of the spectrum of blade 3. The spectrum graph is segmented to obtain an independent sub-spectrum graph for each blade, and then the amplitude of the spectrum energy of each blade is calculated. The amplitudes of the spectrum energy of the three blades are , , .

[0038] Among them, the energy difference of blade sweeping wind is calculated , the calculation formula is as follows: The audio data is windowed and short-time Fourier transformed to extract spectral features, and the spectrum graph is obtained after splicing.

[0039] Furthermore, the blade operation video data is read, and through image segmentation, the images of the three blades passing through a fixed position are obtained respectively, such as Figure 5 As shown in , the contours of a single leaf in the image are extracted respectively, such as Figure 6 As shown in the figure. Since the image is composed of pixels, by calculating the number of pixels inside the contour, we can get a value proportional to the actual area of ​​the leaf. The pixel areas of the three leaves are , , .

[0040] Furthermore, the maximum difference in the pixel areas of the three leaves is calculated. , the calculation formula is as follows: Furthermore, the pixel area of ​​the leaf without zero deviation at the same fixed position is obtained. , calculate the blade zero position deviation angle value θ, the calculation formula is as follows: The calculation principle of the blade zero deviation angle value θ is: if the installation angle of a blade has a zero deviation, it is equivalent to the blade surface facing the gimbal camera rotating around its pitch rotation center. If the surface contour of the blade facing the gimbal camera is simplified as a rectangle, such as Figure 6 The two sides of the rectangle are x and y respectively, then the actual area of ​​the blade without zero deviation in the field of view of the gimbal camera ; When the zero position of the blade has a certain angle θ deviation, the actual area of ​​the blade with zero position deviation in the field of view of the gimbal camera is ,in Assuming that there are three leaves with the largest pixel area difference, one of them is a leaf without zero deviation and the other is a leaf with zero deviation, then we can get: ; Right now ; in: It is the ratio coefficient of the pixel area to the actual area of ​​the object, which can be obtained through the initial calibration of the blade design parameters.

[0041] Since the pixel area of ​​the leaves without zero deviation is at the same fixed position ,but: ; Thus, the blade zero position deviation angle value θ is calculated.

[0042] Furthermore, an energy difference threshold and a deviation angle threshold are preset. When the energy difference of the blade swept wind 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 the target wind turbine has an impeller imbalance caused by zero-position deviation.

[0043] Optionally, the energy difference threshold and the angle threshold can be set to multiple gears, for example, two gears, namely, energy difference threshold gear one, energy difference threshold gear two, angle threshold gear one and angle threshold gear two; when the energy difference of the blade swept wind is greater than the energy difference threshold gear one, and the blade zero position deviation angle value is greater than the angle threshold gear one, it is judged that the unit has a slight impeller imbalance problem caused by the zero position deviation; when the energy difference of the blade swept wind is greater than the energy difference threshold gear two, and the blade zero position deviation angle value is greater than the angle threshold gear two, it is judged that the unit has a severe impeller imbalance problem caused by the zero position deviation. For example, the energy difference threshold gear one is 0.3, the energy difference threshold gear two is 0.5; the angle threshold gear one is 1°, and the angle threshold gear two is 3°.

[0044] Furthermore, when it is detected that the target wind turbine has an impeller imbalance caused by a zero position deviation, an early warning is issued based on the severity.

[0045] Compared with the prior art, the beneficial effects of the embodiments of the present invention are: (1) the impeller imbalance problem caused by the zero-position deviation is confirmed by jointly detecting the blade audio and blade video data, with high detection accuracy, and the zero-position deviation angle value can be preliminarily estimated, which is helpful for fan problem detection and solution of impeller imbalance problem.

[0046] (2) The energy difference of the blade swept air is expressed by the ratio of the maximum difference of the spectrum energy amplitudes of the three blades to the average of the spectrum energy amplitudes of the three blades. When the energy difference is greater than 0.3, it is preliminarily judged that the impeller is slightly unbalanced; when the energy difference is greater than 0.5, it is preliminarily judged that the impeller is severely unbalanced.

[0047] (3) The pixel area of ​​the three blades at the same fixed position is identified through video data, and the blade zero-position deviation angle value is calculated by the pixel area difference of the three blades. When the zero-position deviation angle value is greater than 1° and the energy difference is greater than 0.3, the impeller is judged to be slightly unbalanced and a slight imbalance warning is issued; when the zero-position deviation angle value is greater than 3° and the energy difference is greater than 0.5, the impeller is judged to be 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.

[0048] The impeller imbalance detection system of the wind turbine set provided by the present invention is described below. The impeller imbalance detection system of the wind turbine set described below and the impeller imbalance detection method of the wind turbine set described above can be referred to each other.

[0049] Figure 7 is a topological diagram of the impeller imbalance detection system of the wind turbine provided by the present invention, such as Figure 7 As shown, the system includes a pan-tilt camera 1, an audio sensor 2, an audio acquisition unit 3, and a host computer 4. Figure 5 As shown. The pan-tilt camera 1 is installed on the top of the cabin and faces the direction of the blades to shoot the video of the blades passing through the top of the cabin; the audio sensor 2 is installed on the tower wall in the main wind direction of the tower bottom, and the installation height is 5-10m from the bottom of the tower to collect the sound of the wind when the blades pass through the audio sensor 2 when the wind turbine is running; the audio acquisition unit 3 is connected to the audio sensor 2 to collect the audio data of the blades sweeping the wind. 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 wind turbine cloud network. The host computer 4 collects video data and audio data and processes and analyzes them, and calculates and warns the impeller balance results.

[0050] Figure 8 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 8 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the impeller imbalance detection method of the wind turbine, the method comprising: obtaining the blade sweeping wind audio and the blade running video when the target wind turbine is running; calculating the energy difference of the blade sweeping wind based on the blade sweeping wind audio, and calculating the blade zero position deviation angle value based on the blade running video; and performing imbalance detection on the impeller of the target wind turbine based on the energy difference and the blade zero position deviation angle value.

[0051] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0052] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program 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 set provided by the above-mentioned methods, the method including: obtaining blade sweeping audio and blade operation video when the target wind turbine set is running; calculating the energy difference of the blade sweeping audio 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 set based on the energy difference and the blade zero-position deviation angle value.

[0053] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the impeller imbalance detection method for a wind turbine set provided by the above-mentioned methods, the method comprising: obtaining blade sweeping audio and blade operation video when the target wind turbine set is running; calculating the energy difference of the blade sweeping audio 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 set based on the energy difference and the blade zero-position deviation angle value.

[0054] The device implementation cases described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the implementation case scheme. Ordinary technicians in this field can understand and implement it without creative work.

[0055] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on this understanding, the above technical solution, in essence or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation case or some parts of the implementation case.

[0056] 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 it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned implementation cases, or replace some of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the implementation cases of the present invention.

Claims

1. A method for detecting impeller imbalance of a wind turbine, characterized in that: include: Acquire the blade sweeping audio and blade operation video of the target wind turbine when it is running; Calculate the energy difference of the blade sweep wind based on the blade sweep wind audio, and calculate the blade zero position deviation angle value based on the blade operation video; Based on the energy difference and the blade zero position deviation angle value, an imbalance detection is performed on the impeller of the target wind turbine generator set.

2. The method according to claim 1, characterized in that: The calculating the energy difference of the blade sweep wind based on the blade sweep wind audio comprises: Performing audio data processing on the blade sweeping wind audio to obtain a frequency spectrum diagram with time as the horizontal axis and frequency as the vertical axis; Performing graphic segmentation on the frequency spectrum to obtain a sub-frequency spectrum corresponding to each leaf; Calculating the spectrum energy amplitude of each leaf based on the sub-spectrum graph; The energy difference of the blade swept wind is calculated based on the spectrum energy amplitude of each blade.

3. The method according to claim 1, characterized in that 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 contour of each leaf in the corresponding first image, and calculating the first pixel point area of ​​the leaf within the leaf contour; Calculating the maximum difference of the pixel point areas of all leaves based on the first pixel point area of ​​each leaf; Obtaining the standard pixel area when a standard blade without zero position deviation passes through the same fixed position of the pan-tilt camera; The blade zero position deviation angle value is calculated based on the maximum difference of all blade pixel point areas and the standard pixel point area.

4. The method according to any one of claims 1 to 3, characterized in that: The unbalance detection of 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 a zero-position deviation.

5. The method according to claim 4, 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; Determine the target energy difference threshold level that the energy difference degree meets based on the multiple energy difference threshold levels, and determine the 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 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.

6. The method according to claim 5, characterized in that The method further comprises: When it is detected that the target wind turbine has an impeller imbalance caused by a zero position deviation, an early warning is issued based on the severity.

7. A wind turbine impeller imbalance detection system, 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 at the bottom of the target wind turbine in the main wind direction, and is used to collect the blade sweeping audio when the target wind turbine is running; The gimbal camera and the audio sensor are both communicatively connected to the host computer, and the host computer is used to obtain the blade operation video collected by the gimbal camera and the blade wind sweeping audio collected by the audio sensor; and calculate the energy difference of the blade wind sweeping based on the blade wind sweeping audio, and calculate the blade zero position deviation angle value based on the blade operation video; and then based on the energy difference and the blade zero position deviation angle value, perform imbalance detection on the impeller of the target wind turbine.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the impeller imbalance detection method for a wind turbine set according to any one of claims 1 to 6 is implemented.

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

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the impeller imbalance detection method for a wind turbine set according to any one of claims 1 to 6 is implemented.

Images