CN117072380A - Wind turbine generator blade running state monitoring method - Google Patents
Wind turbine generator blade running state monitoring method Download PDFInfo
- Publication number
- CN117072380A CN117072380A CN202310796980.XA CN202310796980A CN117072380A CN 117072380 A CN117072380 A CN 117072380A CN 202310796980 A CN202310796980 A CN 202310796980A CN 117072380 A CN117072380 A CN 117072380A
- Authority
- CN
- China
- Prior art keywords
- blade
- wind turbine
- blades
- data
- running state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012544 monitoring process Methods 0.000 title claims abstract description 35
- 238000010977 unit operation Methods 0.000 claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims abstract description 7
- 238000010219 correlation analysis Methods 0.000 claims abstract description 4
- 238000003745 diagnosis Methods 0.000 claims abstract description 4
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 208000025274 Lightning injury Diseases 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 10
- 230000001133 acceleration Effects 0.000 claims description 9
- 238000005259 measurement Methods 0.000 claims description 9
- 230000003287 optical effect Effects 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 9
- 238000012935 Averaging Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 239000013307 optical fiber Substances 0.000 claims description 6
- 230000000737 periodic effect Effects 0.000 claims description 6
- 230000005236 sound signal Effects 0.000 claims description 6
- 238000001228 spectrum Methods 0.000 claims description 6
- 238000010183 spectrum analysis Methods 0.000 claims description 6
- 230000001360 synchronised effect Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 4
- 230000002238 attenuated effect Effects 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 210000005036 nerve Anatomy 0.000 claims description 2
- 238000010248 power generation Methods 0.000 abstract description 4
- 238000007689 inspection Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000036561 sun exposure Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Wind Motors (AREA)
Abstract
The invention relates to the technical field of wind power generation, in particular to a method for monitoring the running state of a wind turbine generator blade, which comprises the following steps: acquiring unit operation condition data, pneumatic audio data during unit operation, and blade image data shot by a pan-tilt camera in real time, and storing and transmitting the data to a data preprocessing unit; analyzing the stable working condition of the collected unit operation information; performing cross-correlation analysis on the audio data of three blades separated in the previous step, setting a threshold value, and judging that the blades have faults when the cross-correlation coefficient is lower than the threshold value; extracting a feature matrix from the fault audio data; comparing the model identification result with the picture diagnosis result and the degree, and sending fault alarm information if the results are consistent, wherein the results are different from the picture discrimination result; the method is used for monitoring the running state of the wind turbine generator blade.
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to a method for monitoring the running state of a wind turbine generator blade.
Background
The blades are key components of the wind turbine, and the performance of the blades can directly influence the power generation efficiency of the wind turbine. However, the wind power generation device is in a wind field with severe environment for a long time, and can be corroded by lightning stroke, rain, sun exposure and the like, so that faults are frequent. At present, common blade fault monitoring means have manual inspection, unmanned aerial vehicle inspection and vibration sensor monitoring, and manual inspection and unmanned aerial vehicle inspection can directly show the blade damage situation, but have the problem that the detection is untimely, downtime is long, and vibration sensor can realize online real-time monitoring, but its installation difficulty, technique change time are long, and can't monitor blade surface damage.
The current pan-tilt camera control method for monitoring the running state of the blade mainly comprises the following steps: 1) Based on single-angle fixed monitoring shooting; 2) Fixedly monitoring shooting based on multiple angles; 3) Photographing based on manual observation. The prior scheme for analyzing the video monitoring control of the running state of the blade is not specially adopted, so that the following problems are caused: 1) In the stage of ice and snow melting, weather conditions are changed well, sunlight can be strong, and when a camera faces the sunlight, the grains of the blade cannot be clearly shown; 2) The movement mode and the route of the cradle head are fixed and cannot be combined with the state of the unit; 3) The cradle head cameras on the market do not develop a closed loop feedback port of the cradle head quantized pose, the quantized pitch angle and yaw angle of the cradle head cannot be transmitted to an upper computer, and only instruction values can be fed back and displayed. The pan-tilt camera cannot return to the quantized pose value, and when the pan-tilt camera is frozen by ice and snow, the real angle cannot be obtained or the icing state of the pan-tilt camera cannot be reported.
Disclosure of Invention
In order to solve the defects in the prior art, the invention aims to provide a method for monitoring the running state of a wind turbine blade so as to overcome the defects in the prior art.
The embodiment of the invention is realized by the following technical scheme: a wind turbine generator blade running state monitoring method comprises the following steps:
step one: acquiring unit operation condition data, pneumatic audio data and path planning for a cradle head camera in real time, and storing and transmitting blade image data shot by the cradle head camera to a data preprocessing unit;
step two: analyzing the stable working condition of the collected unit operation information, and if the unit operation information is judged to be stable, further filtering, envelope spectrum analysis, time domain synchronous averaging and data segmentation are carried out on the unit operation audio data;
step three: performing cross-correlation analysis on the audio data of three blades separated in the previous step, setting a threshold value, and judging that the blades have faults when the cross-correlation coefficient is lower than the threshold value;
step four: extracting a feature matrix from fault audio data, importing a single or three blade feature matrix into a trained neural network model to perform fault identification, and simultaneously acquiring a fault picture by a tripod head camera, wherein the fault picture is assisted with manual discrimination to determine the fault type and degree;
step five: and comparing the model identification result with the picture diagnosis result and the degree, and sending fault alarm information if the results are consistent, wherein the results are different from the picture judgment result.
As a further explanation of the method for monitoring the running state of the wind turbine blade, preferably, the data of the running condition of the wind turbine comprises data collected by an acceleration sensor, a lightning stroke sensor and a load sensor, wherein the acceleration sensor and the load sensor are arranged on the inner surface of the blade, and the lightning stroke sensor is arranged on a drainage cable of the blade; the acceleration sensor, the optical fiber MEMS lightning stroke sensor and the optical fiber MEMS load sensor are respectively connected with a demodulator, the demodulator is in wireless communication with a wireless module, and the wireless module is connected with a server through a plurality of switches.
As a further explanation of the method for monitoring the running state of the wind turbine blade according to the present invention, preferably, the pan-tilt camera is installed at the top of the nacelle of the large wind turbine, and is used for recording the running state video of the large wind turbine blade, and the central controller includes a GPU and a neural computing unit, and is connected with the pan-tilt camera in a communication manner, and is used for controlling the pan-tilt camera to track the movement of the blade, intercept the video stream, and perform detailed video analysis.
As a further explanation of the wind turbine generator system blade running state monitoring method, preferably, the data sampling rate of the operating condition of the wind turbine generator system is 1Hz, and data are continuously collected in real time; the sampling rate of the pneumatic audio data is t seconds when the unit operates, and the unit is ensured to at least comprise three rotation periods within the operating rotating speed range; the pneumatic audio data sampling rate is 44100Hz; the frequency of the images shot by the cradle head camera is 10Hz, so that the camera can be guaranteed to shoot pictures of downward rotation of the blades when the machine set operates.
As a further explanation of the method for monitoring the running state of the wind turbine blade according to the present invention, preferably, the motion path of the pan-tilt camera is defined into the following four sections:
section a: setting a pitch angle for the cradle head camera according to the length of the blade, and then enabling the cradle head camera to scan the top of the engine room to perform yaw reciprocating motion according to a scanning angle of 0-360 degrees;
b,: locking the root parts of the blades, and shooting by using a cradle head camera according to the preset sequence along with the movement of the root parts of the blades;
c, section: locking the middle part of each blade, and shooting by using a cradle head camera according to the preset sequence along with the movement of the middle part of each blade;
d,: and locking the blade tips of the blades, and shooting by using the cradle head camera according to the preset sequence along with the movement of the blade tips of the blades.
As a further explanation of the method for monitoring the running state of the wind turbine blade, the number of the load sensors is preferably 4-8, and the load sensors are uniformly distributed on the section in a circumferential direction.
As a further explanation of the method for monitoring the running state of a wind turbine blade according to the present invention, preferably, the planning of the section b includes the following steps:
b1, controlling a pan-tilt camera to yaw, wherein the yaw direction points to the middle position of the blade root area;
b2, determining a time interval t of a blade scanning the field of view of the cradle head camera by using an optical flow method, and matching with a measurement result of an impeller rotating speed encoder;
b3, planning a tracking path of the pan-tilt camera to the blade according to the rotating speed of the impeller, wherein the planning constraint is that the sight line center of the pan-tilt camera points to the center point of the root of the blade;
b4, repeating the steps b1 to b3, and tracking other blades of the large wind turbine generator in sequence;
the planning of the section c comprises the following steps:
c1, controlling a pan-tilt camera to yaw, wherein the yaw direction points to the middle position of the area in the leaf;
c2, determining a time interval t of a blade scanning the field of view of the cradle head camera by using an optical flow method, and matching with a measurement result of an impeller rotating speed encoder;
c3, planning a tracking path of the pan-tilt camera to the blade according to the rotating speed of the impeller, wherein the planning constraint is that the sight line center of the pan-tilt camera points to the center point of the middle part of the blade;
and c4, repeating the steps c1 to c3, and tracking other blades of the large wind turbine generator in sequence.
As a further explanation of the method for monitoring the running state of a wind turbine blade according to the present invention, preferably, the planning of the d segment includes the following steps:
d1, controlling a pan-tilt camera to yaw, wherein the yaw direction points to the middle position of the blade tip region;
d2, determining a time interval t of a blade scanning the field of view of the cradle head camera by using an optical flow method, and matching with a measurement result of an impeller rotating speed encoder;
d3, planning a tracking path of the pan-tilt camera to the blade according to the rotating speed of the impeller, wherein the planning constraint is that the sight line center of the pan-tilt camera points to the center point of the tip of the blade;
and d4, repeating the steps d1 to d3, and tracking other blades of the large wind turbine generator in sequence.
As a further explanation of the method for monitoring the running state of the wind turbine blade, preferably, the method for filtering the audio data adopts a Butterworth band-pass filter, the band-pass filtering range is set as [500 5000], the direct current signal is removed, the influence of environmental noise is reduced, and the filtering frequency range can be set according to requirements.
As a further explanation of the method for monitoring the running state of a wind turbine blade according to the present invention, preferably, the envelope spectrum analysis calculates an audio signal envelope spectrum by hilbert transformation, takes a time corresponding to a value when a first envelope maximum point of the envelope spectrum is attenuated to a% near a data start point side as a cycle time start point T0, in this specific embodiment, a=10, the intercepting duration is a wind wheel rotation time T, at this time, t=60/R ms is taken, and a cutting start point of the next cycle data is an end point of the previous cycle; the time domain synchronous averaging is that the divided audio periodic signals are overlapped and averaged, the number of the periodic audio signals is 3-6, and finally the audio data X of one period is obtained, and the operation can further reduce the influence of random interference.
The technical scheme of the embodiment of the invention has at least the following advantages and beneficial effects:
1. according to the invention, under the condition of sufficient light, the camera of the cradle head is utilized for tracking control shooting, so that the problem of backlight shooting is avoided, and the surface texture of the blade can be shot clearly.
2. The multiple sensors can monitor multiple states of the blade during running and collect multiple characteristic quantities
And the linkage is subjected to statistical analysis, the characteristic quantity change trend under each working condition is predicted, early warning and predictive operation and maintenance of the wind turbine generator blade faults are realized, and the running safety and stability of the wind farm are ensured.
3. According to the invention, by establishing the method and the system for diagnosing the blade audio and video faults, filtering, time averaging and data segmentation are carried out on the blade audio data, three pieces of blade audio data are obtained, the blade faults are judged by applying cross correlation, and further the fault identification is carried out on the blades with faults.
Drawings
Fig. 1 is a flow chart of a method for monitoring the running state of a wind turbine blade according to embodiment 1 of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Example 1
Referring to fig. 1, a method for monitoring the running state of a wind turbine blade includes the following steps:
step one: acquiring unit operation condition data, pneumatic audio data and path planning for a cradle head camera in real time, and storing and transmitting blade image data shot by the cradle head camera to a data preprocessing unit;
step two: analyzing the stable working condition of the collected unit operation information, and if the unit operation information is judged to be stable, further filtering, envelope spectrum analysis, time domain synchronous averaging and data segmentation are carried out on the unit operation audio data;
step three: performing cross-correlation analysis on the audio data of three blades separated in the previous step, setting a threshold value, and judging that the blades have faults when the cross-correlation coefficient is lower than the threshold value;
step four: extracting a feature matrix from fault audio data, importing a single or three blade feature matrix into a trained neural network model to perform fault identification, and simultaneously acquiring a fault picture by a tripod head camera, wherein the fault picture is assisted with manual discrimination to determine the fault type and degree;
step five: and comparing the model identification result with the picture diagnosis result and the degree, and sending fault alarm information if the results are consistent, wherein the results are different from the picture judgment result.
The unit operation condition data comprise data acquired by an acceleration sensor, a lightning stroke sensor and a load sensor, wherein the acceleration sensor and the load sensor are arranged on the inner surface of the blade, and the lightning stroke sensor is arranged on a drainage cable of the blade; the acceleration sensor, the optical fiber MEMS lightning stroke sensor and the optical fiber MEMS load sensor are respectively connected with a demodulator, the demodulator is in wireless communication with a wireless module, and the wireless module is connected with a server through a plurality of switches.
The cradle head camera is arranged at the top of a cabin of the large wind turbine generator and used for recording the running state video of the blades of the large wind turbine generator, the central controller comprises a GPU and a nerve calculation unit, and the central controller is in communication connection with the cradle head camera and used for controlling the cradle head camera to track the movement of the blades, intercept video streams and conduct detailed video analysis.
The data sampling rate of the unit operation condition is 1Hz, and data are continuously collected in real time; the sampling rate of the pneumatic audio data is t seconds when the unit operates, and the unit is ensured to at least comprise three rotation periods within the operating rotating speed range; the pneumatic audio data sampling rate is 44100Hz; the frequency of the images shot by the cradle head camera is 10Hz, so that the camera can be guaranteed to shoot pictures of downward rotation of the blades when the machine set operates.
The motion path of the pan-tilt camera is defined into the following four sections:
section a: setting a pitch angle for the cradle head camera according to the length of the blade, and then enabling the cradle head camera to scan the top of the engine room to perform yaw reciprocating motion according to a scanning angle of 0-360 degrees;
b,: locking the root parts of the blades, and shooting by using a cradle head camera according to the preset sequence along with the movement of the root parts of the blades;
c, section: locking the middle part of each blade, and shooting by using a cradle head camera according to the preset sequence along with the movement of the middle part of each blade;
d,: and locking the blade tips of the blades, and shooting by using the cradle head camera according to the preset sequence along with the movement of the blade tips of the blades.
The number of the load sensors is 4-8, and the load sensors are uniformly distributed on the section in a circumferential direction.
The planning of the section b comprises the following steps:
b1, controlling a pan-tilt camera to yaw, wherein the yaw direction points to the middle position of the blade root area;
b2, determining a time interval t of a blade scanning the field of view of the cradle head camera by using an optical flow method, and matching with a measurement result of an impeller rotating speed encoder;
b3, planning a tracking path of the pan-tilt camera to the blade according to the rotating speed of the impeller, wherein the planning constraint is that the sight line center of the pan-tilt camera points to the center point of the root of the blade;
b4, repeating the steps b1 to b3, and tracking other blades of the large wind turbine generator in sequence;
the planning of the section c comprises the following steps:
c1, controlling a pan-tilt camera to yaw, wherein the yaw direction points to the middle position of the area in the leaf;
c2, determining a time interval t of a blade scanning the field of view of the cradle head camera by using an optical flow method, and matching with a measurement result of an impeller rotating speed encoder;
c3, planning a tracking path of the pan-tilt camera to the blade according to the rotating speed of the impeller, wherein the planning constraint is that the sight line center of the pan-tilt camera points to the center point of the middle part of the blade;
and c4, repeating the steps c1 to c3, and tracking other blades of the large wind turbine generator in sequence.
The planning of the d section comprises the following steps:
d1, controlling a pan-tilt camera to yaw, wherein the yaw direction points to the middle position of the blade tip region;
d2, determining a time interval t of a blade scanning the field of view of the cradle head camera by using an optical flow method, and matching with a measurement result of an impeller rotating speed encoder;
d3, planning a tracking path of the pan-tilt camera to the blade according to the rotating speed of the impeller, wherein the planning constraint is that the sight line center of the pan-tilt camera points to the center point of the tip of the blade;
and d4, repeating the steps d1 to d3, and tracking other blades of the large wind turbine generator in sequence.
According to the audio data filtering method, a Butterworth band-pass filter is adopted, the band-pass filtering range is set to be [500 5000], the direct-current signals are removed, the influence of environmental noise is reduced, and the filtering frequency range can be set according to requirements.
The method comprises the steps that the envelope spectrum analysis calculates an audio signal envelope spectrum by using Hilbert transformation, a period time starting point T0 is taken as a time corresponding to a value that a% is attenuated to a side, close to a data starting point, of a first envelope maximum value point of the envelope spectrum, in the specific embodiment, a=10 is taken, intercepting time is taken as a period of time T for rotating a wind wheel, at the moment, T=60/R ms is taken, and a cutting starting point of next period data is taken as an end point of a previous period; the time domain synchronous averaging is that the divided audio periodic signals are overlapped and averaged, the number of the periodic audio signals is 3-6, and finally the audio data X of one period is obtained, and the operation can further reduce the influence of random interference.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The method for monitoring the running state of the wind turbine blade is characterized by comprising the following steps of:
step one: acquiring unit operation condition data, pneumatic audio data and path planning for a cradle head camera in real time, and storing and transmitting blade image data shot by the cradle head camera to a data preprocessing unit;
step two: analyzing the stable working condition of the collected unit operation information, and if the unit operation information is judged to be stable, further filtering, envelope spectrum analysis, time domain synchronous averaging and data segmentation are carried out on the unit operation audio data;
step three: performing cross-correlation analysis on the audio data of three blades separated in the previous step, setting a threshold value, and judging that the blades have faults when the cross-correlation coefficient is lower than the threshold value;
step four: extracting a feature matrix from fault audio data, importing a single or three blade feature matrix into a trained neural network model to perform fault identification, and simultaneously acquiring a fault picture by a tripod head camera, wherein the fault picture is assisted with manual discrimination to determine the fault type and degree;
step five: and comparing the model identification result with the picture diagnosis result and the degree, and sending fault alarm information if the results are consistent, wherein the results are different from the picture judgment result.
2. The method for monitoring the running state of the wind turbine blade according to claim 1, wherein the turbine running condition data comprise data acquired by an acceleration sensor, a lightning stroke sensor and a load sensor, the acceleration sensor and the load sensor are arranged on the inner surface of the blade, and the lightning stroke sensor is arranged on a drainage cable of the blade; the acceleration sensor, the optical fiber MEMS lightning stroke sensor and the optical fiber MEMS load sensor are respectively connected with a demodulator, the demodulator is in wireless communication with a wireless module, and the wireless module is connected with a server through a plurality of switches.
3. The method for monitoring the running state of the blades of the wind turbine generator according to claim 2, wherein the cradle head camera is arranged at the top of a cabin of the large wind turbine generator and used for recording the running state video of the blades of the large wind turbine generator, and the central controller comprises a GPU and a nerve computing unit and is in communication connection with the cradle head camera and used for controlling the cradle head camera to track the movement of the blades, intercept video streams and conduct detailed video analysis.
4. The method for monitoring the running state of the wind turbine generator blade according to claim 3, wherein the sampling rate of the data of the running condition of the wind turbine generator is 1Hz, and the data are continuously collected in real time; the sampling rate of the pneumatic audio data is t seconds when the unit operates, and the unit is ensured to at least comprise three rotation periods within the operating rotating speed range; the pneumatic audio data sampling rate is 44100Hz; the frequency of the images shot by the cradle head camera is 10Hz, so that the camera can be guaranteed to shoot pictures of downward rotation of the blades when the machine set operates.
5. The method for monitoring the running state of the blades of the wind turbine generator according to claim 4, wherein the motion path of the tripod head camera is defined into the following four sections:
section a: setting a pitch angle for the cradle head camera according to the length of the blade, and then enabling the cradle head camera to scan the top of the engine room to perform yaw reciprocating motion according to a scanning angle of 0-360 degrees;
b,: locking the root parts of the blades, and shooting by using a cradle head camera according to the preset sequence along with the movement of the root parts of the blades;
c, section: locking the middle part of each blade, and shooting by using a cradle head camera according to the preset sequence along with the movement of the middle part of each blade;
d,: and locking the blade tips of the blades, and shooting by using the cradle head camera according to the preset sequence along with the movement of the blade tips of the blades.
6. The method for monitoring the running state of the wind turbine blade according to claim 5, wherein the number of the load sensors is 4-8, and the load sensors are uniformly distributed on the cross section in a circumferential direction.
7. The method for monitoring the running state of a wind turbine blade according to claim 6, wherein the planning of the b section comprises the following steps:
b1, controlling a pan-tilt camera to yaw, wherein the yaw direction points to the middle position of the blade root area;
b2, determining a time interval t of a blade scanning the field of view of the cradle head camera by using an optical flow method, and matching with a measurement result of an impeller rotating speed encoder;
b3, planning a tracking path of the pan-tilt camera to the blade according to the rotating speed of the impeller, wherein the planning constraint is that the sight line center of the pan-tilt camera points to the center point of the root of the blade;
b4, repeating the steps b1 to b3, and tracking other blades of the large wind turbine generator in sequence;
the planning of the section c comprises the following steps:
c1, controlling a pan-tilt camera to yaw, wherein the yaw direction points to the middle position of the area in the leaf;
c2, determining a time interval t of a blade scanning the field of view of the cradle head camera by using an optical flow method, and matching with a measurement result of an impeller rotating speed encoder;
c3, planning a tracking path of the pan-tilt camera to the blade according to the rotating speed of the impeller, wherein the planning constraint is that the sight line center of the pan-tilt camera points to the center point of the middle part of the blade;
and c4, repeating the steps c1 to c3, and tracking other blades of the large wind turbine generator in sequence.
8. The method for monitoring the running state of the blades of the wind turbine generator according to claim 7, wherein the planning of the d section comprises the following steps:
d1, controlling a pan-tilt camera to yaw, wherein the yaw direction points to the middle position of the blade tip region;
d2, determining a time interval t of a blade scanning the field of view of the cradle head camera by using an optical flow method, and matching with a measurement result of an impeller rotating speed encoder;
d3, planning a tracking path of the pan-tilt camera to the blade according to the rotating speed of the impeller, wherein the planning constraint is that the sight line center of the pan-tilt camera points to the center point of the tip of the blade;
and d4, repeating the steps d1 to d3, and tracking other blades of the large wind turbine generator in sequence.
9. The method for monitoring the running state of the wind turbine blade according to claim 8, wherein the audio data is filtered by using a butterworth band-pass filter, the band-pass filter range is set to [500 5000], the direct current signal is removed, the influence of environmental noise is reduced, and the filter frequency range can be set according to requirements.
10. The method for monitoring the running state of a wind turbine blade according to claim 9, wherein the envelope spectrum analysis calculates an audio signal envelope spectrum by using hilbert transformation, takes a time corresponding to a value that a maximum value point of a first envelope of the envelope spectrum is attenuated to a% near a data start point side as a period time start point T0, takes a=10 in this specific embodiment, takes a time length of interception as a period of time T for a wind wheel to rotate, takes t=60/R ms at this time, and takes a cutting start point of next period data as an end point of a previous period; the time domain synchronous averaging is that the divided audio periodic signals are overlapped and averaged, the number of the periodic audio signals is 3-6, and finally the audio data X of one period is obtained, and the operation can further reduce the influence of random interference.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310796980.XA CN117072380A (en) | 2023-06-30 | 2023-06-30 | Wind turbine generator blade running state monitoring method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310796980.XA CN117072380A (en) | 2023-06-30 | 2023-06-30 | Wind turbine generator blade running state monitoring method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117072380A true CN117072380A (en) | 2023-11-17 |
Family
ID=88712248
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310796980.XA Pending CN117072380A (en) | 2023-06-30 | 2023-06-30 | Wind turbine generator blade running state monitoring method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117072380A (en) |
-
2023
- 2023-06-30 CN CN202310796980.XA patent/CN117072380A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11549492B2 (en) | Method of condition monitoring one or more wind turbines and parts thereof and performing instant alarm when needed | |
CN111911364B (en) | Blade tip tower barrel clearance monitoring method | |
CN110282143B (en) | Inspection method for offshore wind farm unmanned aerial vehicle | |
CN110261394A (en) | Online fan blade damages real-time diagnosis system and method | |
CN112360699A (en) | Intelligent inspection and diagnosis analysis method for blades of full-automatic wind generating set | |
CN108956640A (en) | Vehicle-mounted detection apparatus and detection method suitable for distribution line inspection | |
CN112727704B (en) | Method and system for monitoring corrosion of leading edge of blade | |
CN111127806A (en) | Comprehensive forest fire prevention monitoring system and method based on multiple sensors | |
CN111038721A (en) | Wind turbine blade inspection unmanned aerial vehicle and inspection method based on image recognition | |
CN115218801B (en) | Wind driven generator clearance distance measuring method and device based on machine vision | |
CN112329584A (en) | Method, system and equipment for automatically identifying foreign matters in power grid based on machine vision | |
CN116877358B (en) | Vibration monitoring and analyzing system of wind generating set | |
CN117072380A (en) | Wind turbine generator blade running state monitoring method | |
CN112727703B (en) | Fan blade protective film damage monitoring method and system based on audio signal | |
CN113898537A (en) | Remote intelligent inspection system for wind power plant | |
CN105203315A (en) | Air blower blade monitoring device arranged on inspection vehicle | |
CN116906276A (en) | Intelligent inspection method for fan blade | |
CN111340747B (en) | Method, equipment and system for processing blade image of wind generating set | |
CA3231410A1 (en) | Unmanned airborne visual diagnosis of an operating wind turbine generator | |
CN114240235A (en) | Device and method for monitoring fan blade state of wind generating set | |
CN114442658A (en) | Automatic inspection system for unmanned aerial vehicle of power transmission and distribution line and operation method thereof | |
CN205049341U (en) | Establish fan thick liquid leaf monitoring devices on patrolling and examining car | |
CN217002157U (en) | Blade state monitoring system based on infrared imaging | |
KR102541382B1 (en) | Apparatus for controlling wind power generator and method for inspecting the blades of wind power generator | |
CN112780503B (en) | Fan blade protective paint damage monitoring method and system based on audio signals |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |