CN114439702A - Blade state monitoring method and device of wind driven generator - Google Patents
Blade state monitoring method and device of wind driven generator Download PDFInfo
- Publication number
- CN114439702A CN114439702A CN202210108182.9A CN202210108182A CN114439702A CN 114439702 A CN114439702 A CN 114439702A CN 202210108182 A CN202210108182 A CN 202210108182A CN 114439702 A CN114439702 A CN 114439702A
- Authority
- CN
- China
- Prior art keywords
- blade
- signal
- image
- envelope signal
- equipment
- 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 40
- 238000012544 monitoring process Methods 0.000 title claims abstract description 27
- 230000005236 sound signal Effects 0.000 claims abstract description 76
- 230000002159 abnormal effect Effects 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims description 36
- 230000009194 climbing Effects 0.000 claims description 16
- 238000012806 monitoring device Methods 0.000 claims description 9
- 238000007689 inspection Methods 0.000 claims description 8
- 238000003709 image segmentation Methods 0.000 claims description 5
- 230000007547 defect Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 13
- 238000004590 computer program Methods 0.000 description 7
- 238000013135 deep learning Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 230000002547 anomalous effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000001680 brushing effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000001066 destructive effect Effects 0.000 description 2
- 238000012850 discrimination method Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000002269 spontaneous effect Effects 0.000 description 1
Images
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
-
- 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
- F03D80/00—Details, components or accessories not provided for in groups F03D1/00 - F03D17/00
- F03D80/50—Maintenance or repair
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
- G10L25/57—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for processing of video signals
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Computational Linguistics (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 application discloses a method and a device for monitoring the blade state of a wind driven generator, in particular to the method for monitoring the blade state of the wind driven generator, which is used for acquiring the image and audio signal of each blade of the wind driven generator; detecting an envelope signal of the audio signal of each blade; when the abnormal envelope signal is detected, the image of the current blade generating the abnormal envelope signal is detected to determine whether the current blade generates a fault. Once the corresponding fault is found, the blade can be maintained, and the situation that the fault is further developed to cause the fracture failure of the whole blade is avoided.
Description
Technical Field
The application relates to the technical field of wind power, in particular to a method and a device for monitoring the state of a blade of a wind driven generator.
Background
The wind power industry is rapidly developed around the world as clean energy, but with the increase of the number of installed wind power equipment, wind power equipment which is put into operation earlier begins to age, so that severe accidents such as overturning of a tower barrel, breakage of blades, overspeed, spontaneous combustion of a fan and the like are frequent, property loss is brought to power generation enterprises at a low rate, and serious personal casualty events are caused at a high rate.
Major accidents occurring in the industry are comprehensively analyzed, the reasons mainly include design defects, installation quality problems, component quality problems and the like, but faults induced by any reasons are mostly gradual-change faults, and the reasons for major malignant accidents are mostly imperfect monitoring means or untimely information feedback. If a relatively perfect monitoring system can be established in the early stage of equipment failure and failure information can be timely fed back to related personnel, the equipment can be subjected to predictive maintenance, so that catastrophic consequences caused by equipment accidents can be prevented, and the safe and effective operation of the equipment can be fully ensured.
The blade is a key part of the wind generating set and also a disaster area where faults occur. During the rotation of the blade, when the blade tip rotates from the upper part to the lower part, the stress changes and changes alternately, and the blade can vibrate violently under the unstable wind condition. The severe vibration of the blade can lead to the generation of cracks or other faults, possibly causing the fracture failure of the whole blade, so that effective monitoring of the blade condition is necessary.
Disclosure of Invention
In view of the above, the present application provides a method and an apparatus for monitoring a blade condition of a wind turbine generator, which are used for monitoring the condition of the blade.
In order to achieve the above object, the following solutions are proposed:
a blade condition monitoring method of a wind power generator, the blade condition monitoring method comprising the steps of:
acquiring an audio signal and an image of each blade of the wind driven generator;
detecting an envelope signal of an audio signal of each of the blades;
when an abnormal envelope signal is detected, detecting the image of the current blade generating the abnormal envelope signal so as to determine whether the current blade generates a fault.
Optionally, the image and audio signals of each blade of the wind turbine are collected;
acquiring the audio signal collected by the fixed-position recording equipment;
and acquiring the images collected by the fixed camera position photographic equipment and the mobile camera position photographic equipment.
Optionally, the fixed camera position photographing device comprises a fixed photographing device mounted at the tail of the wind turbine cabin;
the mobile camera position photographing equipment comprises mobile photographing equipment arranged on an unmanned aerial vehicle, a ground inspection robot or a tower climbing robot.
Optionally, the detecting an envelope signal of the audio signal of each of the blades includes:
extracting the envelope signal from the audio signal, wherein the envelope signal comprises a short-time average amplitude of each frame signal in the audio signal;
and detecting the envelope signal based on a sound data template to determine whether the envelope signal is abnormal, wherein the sound data template comprises the envelope signal of the pneumatic audio signal of the normal blade.
Optionally, the detecting the image of the current blade generating the abnormal envelope signal includes:
carrying out image segmentation on the image to obtain a plurality of image areas;
and identifying each image area based on a fault identification model, and judging whether a fault area exists or not.
A blade condition monitoring device of a wind power generator, the blade condition monitoring device comprising:
the signal acquisition equipment is used for acquiring audio signals and images of each blade of the wind driven generator;
an audio processing device for detecting an envelope signal of an audio signal of each of the blades;
the video processing equipment is used for detecting the image of the current blade generating the abnormal envelope signal when the abnormal envelope signal is detected so as to determine whether the current blade generates a fault.
Optionally, the image and audio signals of each blade of the wind turbine are collected;
the first receiving unit is used for receiving the audio signals collected by the fixed machine position recording equipment;
and the second receiving unit is used for acquiring the images acquired by the fixed camera position photographing equipment and the mobile camera position photographing equipment.
Optionally, the fixed camera position photographing device comprises a fixed photographing device mounted at the tail of the wind turbine cabin;
the mobile camera position photographing equipment comprises mobile photographing equipment arranged on an unmanned aerial vehicle, a ground inspection robot or a tower climbing robot.
Optionally, the audio processing apparatus includes:
a first processing unit, configured to extract the envelope signal from the audio signal, where the envelope signal includes a short-time average amplitude of each frame signal in the audio signal;
and the second processing unit is used for detecting the envelope signal based on a sound data template and determining whether the envelope signal is abnormal, wherein the sound data template comprises the envelope signal of the pneumatic audio signal of the normal blade.
Optionally, the video processing module includes:
the third processing unit is used for carrying out image segmentation on the image to obtain a plurality of image areas;
and the fourth processing unit is used for identifying each image area based on a fault identification model and judging whether a fault area exists or not.
According to the technical scheme, the application discloses a method and a device for monitoring the blade state of a wind driven generator, and particularly aims to obtain the image and audio signals of each blade of the wind driven generator; detecting an envelope signal of the audio signal of each blade; when the abnormal envelope signal is detected, the image of the current blade generating the abnormal envelope signal is detected to determine whether the current blade generates a fault. Once the corresponding fault is found, the blade can be maintained, and the situation that the fault is further developed to cause the fracture failure of the whole blade is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart illustrating a method for monitoring a blade condition of a wind turbine according to an embodiment of the present disclosure;
FIG. 2 is a block diagram of a blade condition monitoring device of a wind turbine according to an embodiment of the present disclosure;
FIG. 3 is a block diagram of another wind turbine blade condition monitoring apparatus according to an embodiment of the present disclosure;
FIG. 4 is a block diagram of a blade condition monitoring device of a wind turbine according to an embodiment of the present application;
FIG. 5 is a block diagram of a blade condition monitoring device of a wind turbine according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Example one
Fig. 1 is a flowchart of a method for monitoring a blade condition of a wind turbine according to an embodiment of the present disclosure.
As shown in fig. 1, the blade state detection method provided by the embodiment is applied to a wind turbine generator, and is used for monitoring any blade of the wind turbine generator so as to find a fault in time, and the blade state detection method includes the following steps:
and S1, acquiring audio signals and images of each blade of the wind driven generator.
The method comprises the steps of acquiring corresponding audio signals and images on the basis of acquiring audio signals and images of all or one blade of the wind driven generator through corresponding signal acquisition equipment, namely receiving the corresponding audio signals and images from the signal acquisition equipment. For images, the corresponding signal acquisition equipment is photographic equipment or camera equipment, and for audio signals, the signal acquisition equipment is recording equipment. Correspondingly, the specific acquisition process is as follows:
and acquiring the audio signal acquired by the fixed-position recording equipment.
And acquiring images collected by the fixed camera position photographing equipment and the mobile camera position photographing equipment. The fixed camera position photographic equipment is fixed photographic equipment arranged at the tail part of the fan cabin; the mobile camera position photographing equipment comprises, but is not limited to, mobile photographing equipment arranged on an unmanned aerial vehicle, a ground inspection robot and a tower climbing robot.
The unmanned aerial vehicle is subjected to flight shooting along a preset air route by a wind power station patrol worker, the spatial position information of each shot image is recorded according to the air route, the blade area information of each shot image is determined according to the locking state and the spatial position information of the fan blade, and the stored image and the stored position information are transmitted to a patrol worker operating the unmanned aerial vehicle to perform image processing analysis at the background.
The tower climbing robot acquires a fan blade surface damage image. This scheme is fixed through centre gripping fixing device and can be used for the centre gripping on drive arrangement on aerogenerator stand, and the climbing from top to bottom of reuse drive arrangement drive robot uses the robotic arm centre gripping camera device that stretches out to carry out image acquisition, has replaced the pylon climbing step that the manual work was patrolled and examined through this device, has avoided climbing the potential safety hazard that the pylon appears because of the manpower, can be used for carrying out the image acquisition feedback at the blade of different positions to the fan and other devices with the help of climbing the robot moreover.
And the photographic equipment on the ground inspection robot acquires the damage image of the surface of the fan blade. The scheme is provided with the crawler-type transmission mechanism, adapts to the complex terrain condition of the wind power plant, and can efficiently move. And the fixed photographic equipment arranged at the tail part of the fan cabin shoots the state of the fan blade. The scheme has the advantages that the installation is convenient, and the image and sound data are convenient to synchronize; it is determined that only a partial area of the blade can be photographed.
S2, detecting an envelope signal of the audio signal of each blade.
When the surface of the fan blade is damaged, the fan blade can affect the normal aerodynamic noise signal, the relevant characteristics of the noise signal are changed, the working state of the blade can be judged by analyzing and comparing the normal and destructive noise signals, but considering the complexity of the field environment, the method is mainly embodied in the complexity of background noise, such as roadside car singing and aerial bird singing, if the fan blade is collected together with the aerodynamic noise of the blade, the judgment of the result can be interfered, scholars in the relevant field do a lot of research on denoising, but the calculation is complex, the wind driven generators with different single machine capacities are lack of universal applicability in different environments, therefore, the fan aerodynamic audio signal in the normal operation state is stored as historical data for different wind driven generators, and is used as a sound data template of the normal signal for comparing the subsequently collected blade aerodynamic noise with the wind driven generators, in addition, as for the blade aerodynamic signals, the aerodynamic noise of the three blades under the normal condition has similarity, and the abnormal operation state of the blades can be detected by comparing the similarity of different blades.
The three-leaf envelope signals are clearly distinguishable in shape for each period of leaf audio signal, and in fact, in the event of greater damage to the leaves, the leaves are stroked in air, often with a more pronounced "swishing" sound, which is clearly distinguishable from normal leaves in terms of tone and loudness. Based on the difference in the amplitude of the time domain sound signal, the difference in the shape of different envelope segment signals on the time domain signal is identified by a method for measuring the similarity of the time domain characteristics of the different envelope segment signals in the sound signal, and a time domain characteristic parameter is provided.
The short-time average amplitude is selected as the time domain characteristic parameter, namely the short-time average amplitude of each frame signal is calculated, the short-time average amplitude is calculated based on the fact that the sound signals are stable in a short time, the purpose of compressing data is achieved, the calculation amount of a subsequent identification algorithm is reduced, the shape of the whole envelope section can be well represented, then a characteristic vector is constructed in the whole envelope time, the dimension of the characteristic vector is different due to the fact that the number length of each section of envelope frame is inconsistent, a dynamic time warping method is used in the text, template matching among data with different lengths is carried out, and the purpose of detecting and identifying damaged blades is achieved.
For damaged blades of a wind driven generator, experienced field workers can often distinguish the damaged blades in an ear-hearing mode, such as a noticeable "brushing" sound produced by the rotating degummed blades, a "swooshing" sound produced by the cracked blades, which also indicates that for a damaged and undamaged blade, the generated pneumatic audio signals have obvious difference, and the damage discrimination method based on dynamic time warping characterizes the similarity between two sequences by calculating the distance between the two sequences, therefore, the template data of the normal sound signal is required to be established to be used as the comparison and judgment basis of the subsequent damage signal, the data template of the normal sound signal is established by recording the historical normal leaf pneumatic audio signal, the envelope segment signal of the occurrence of the vane aerodynamic audio signal can be extracted from the original signal, so that the data templates of the subsequently established normal signals are the envelope signals of the individual vanes.
Based on the above analysis, the following steps are adopted in the present application to realize the detection of the audio signal, specifically:
first, an envelope signal including a short-time average amplitude of each frame signal in the audio signal is extracted from the audio signal.
The envelope signal is then detected based on the above-mentioned sound data template to determine whether the envelope signal is anomalous, and if so, it is marked as an anomalous envelope signal for further detection below.
And S3, detecting the image of the current blade corresponding to the abnormal envelope signal.
When the abnormal envelope signal is monitored, the image of the current blade corresponding to the abnormal envelope signal is detected to determine whether the current blade really has a corresponding fault.
The defect characteristics in the extracted image are the key for identifying the defect image of the blade, and when the blade has serious defects and the image is clear, whether the blade has faults or not can be accurately identified according to the color characteristics and the shape characteristics selected manually. But the early defects of the fan blade are fine; the inherent structure (such as a lightning receptor, a tip drain hole, a spoiler, a hub cover seam and the like) of the surface of the blade generates interference, and the image defect characteristics of the blade are complex and various under the influence of the change of a shooting angle, a focal length, illumination and shadow. The above problems lead to the difficulty of satisfying the requirement of identifying the blade defects by manually selected image characteristics. In view of this, the present application adopts the following scheme to implement the detection of the image, specifically as follows:
first, a video is image-divided to obtain a plurality of image regions. The size or position of the image area is determined according to engineering practice.
Then, each image area is detected based on a fault identification model, if any image area determines that a corresponding defect exists, the blade is judged to be in fault, and the type of the fault is output based on the fault identification model.
The fault recognition model is obtained by training a large number of samples acquired in advance based on a deep learning method, wherein the deep learning is an end-to-end machine learning method, and features can be automatically extracted layer by layer. Compared with the manually selected features, the features extracted by deep learning are more abstract, contain more implicit information and have stronger expression capability.
According to the technical scheme, the embodiment provides the blade state monitoring method of the wind driven generator, and particularly obtains the image and audio signals of each blade of the wind driven generator; detecting an envelope signal of the audio signal of each blade; when the abnormal envelope signal is detected, the image of the current blade generating the abnormal envelope signal is detected to determine whether the current blade generates a fault. Once the corresponding fault is found, the blade can be maintained, and the situation that the fault is further developed to cause the fracture failure of the whole blade is avoided.
Example two
Fig. 2 is a block diagram of a blade condition monitoring device of a wind turbine according to an embodiment of the present application.
As shown in fig. 2, the blade state detecting device provided in this embodiment is applied to a wind turbine for monitoring any blade of the wind turbine so as to find a fault in time, and includes a signal acquiring apparatus 10, an audio processing apparatus 20, and a video processing apparatus 30.
The signal acquisition equipment is used for acquiring audio signals and images of each blade of the wind driven generator.
The method comprises the steps of acquiring corresponding audio signals and images on the basis of acquiring audio signals and images of all or one blade of the wind driven generator through corresponding signal acquisition equipment, namely receiving the corresponding audio signals and images from the signal acquisition equipment. For images, the corresponding signal acquisition equipment is photographic equipment or camera equipment, and for audio signals, the signal acquisition equipment is recording equipment. The signal acquisition device comprises a first receiving unit 11 and a second receiving unit 12, as shown in fig. 3.
The first receiving unit is used for acquiring the audio signal collected by the fixed-position recording equipment.
The second receiving unit is used for acquiring images collected by the fixed camera position shooting equipment and the mobile camera position shooting equipment. The fixed camera position photographic equipment is fixed photographic equipment arranged at the tail part of the fan cabin; the mobile camera position photographing equipment comprises, but is not limited to, mobile photographing equipment arranged on an unmanned aerial vehicle, a ground inspection robot and a tower climbing robot.
The unmanned aerial vehicle is subjected to flight shooting along a preset air route by a wind power station patrol worker, the spatial position information of each shot image is recorded according to the air route, the blade area information of each shot image is determined according to the locking state and the spatial position information of the fan blade, and the stored image and the stored position information are transmitted to a patrol worker operating the unmanned aerial vehicle to perform image processing analysis at the background.
The tower climbing robot acquires a fan blade surface damage image. This scheme is fixed through centre gripping fixing device and can be used for the centre gripping on drive arrangement on aerogenerator stand, and the climbing from top to bottom of reuse drive arrangement drive robot uses the robotic arm centre gripping camera device that stretches out to carry out image acquisition, has replaced the pylon climbing step that the manual work was patrolled and examined through this device, has avoided climbing the potential safety hazard that the pylon appears because of the manpower, can be used for carrying out the image acquisition feedback at the blade of different positions to the fan and other devices with the help of climbing the robot moreover.
And the photographic equipment on the ground inspection robot acquires the damage image of the surface of the fan blade. The scheme is provided with the crawler-type transmission mechanism, adapts to the complex terrain condition of the wind power plant, and can efficiently move. And the fixed photographic equipment arranged at the tail part of the fan cabin shoots the state of the fan blade. The scheme has the advantages that the installation is convenient, and the image and sound data are convenient to synchronize; it is determined that only a partial area of the blade can be photographed.
The audio processing device is used for detecting an envelope signal of the audio signal of each blade.
When the surface of the fan blade is damaged, the fan blade can affect the normal aerodynamic noise signal, the relevant characteristics of the noise signal are changed, the working state of the blade can be judged by analyzing and comparing the normal and destructive noise signals, but considering the complexity of the field environment, the method is mainly embodied in the complexity of background noise, such as roadside car singing and aerial bird singing, if the fan blade is collected together with the aerodynamic noise of the blade, the judgment of the result can be interfered, scholars in the relevant field do a lot of research on denoising, but the calculation is complex, the wind driven generators with different single machine capacities are lack of universal applicability in different environments, therefore, the fan aerodynamic audio signal in the normal operation state is stored as historical data for different wind driven generators, and is used as a sound data template of the normal signal for comparing the subsequently collected blade aerodynamic noise with the wind driven generators, in addition, as for the blade aerodynamic signals, the aerodynamic noise of the three blades under the normal condition has similarity, the abnormal operation state of the blades can be detected by comparing the similarity of different blades, and the method has certain self-adaption capability aiming at different wind turbine generators.
The three-leaf envelope signals are clearly distinguishable in shape for each period of leaf audio signal, and in fact, in the event of greater damage to the leaves, the leaves are stroked in air, often with a more pronounced "swishing" sound, which is clearly distinguishable from normal leaves in terms of tone and loudness. Based on the difference in the amplitude of the time domain sound signal, the difference in the shape of different envelope segment signals on the time domain signal is identified by a method for measuring the similarity of the time domain characteristics of the different envelope segment signals in the sound signal, and a time domain characteristic parameter is provided.
The short-time average amplitude is selected as the time domain characteristic parameter, namely the short-time average amplitude of each frame signal is calculated, the short-time average amplitude is calculated based on the fact that the sound signals are stable in a short time, the purpose of compressing data is achieved, the calculation amount of a subsequent identification algorithm is reduced, the shape of the whole envelope section can be well represented, then a characteristic vector is constructed in the whole envelope time, the dimension of the characteristic vector is different due to the fact that the number length of each section of envelope frame is inconsistent, a dynamic time warping method is used in the text, template matching among data with different lengths is carried out, and the purpose of detecting and identifying damaged blades is achieved.
For damaged blades of a wind driven generator, experienced field workers can often distinguish the damaged blades in an ear-hearing mode, such as a noticeable "brushing" sound produced by the rotating degummed blades, a "swooshing" sound produced by the cracked blades, which also indicates that for a damaged and undamaged blade, the generated pneumatic audio signals have obvious difference, and the damage discrimination method based on dynamic time warping characterizes the similarity between two sequences by calculating the distance between the two sequences, therefore, the template data of the normal sound signal is required to be established to be used as the comparison and judgment basis of the subsequent damage signal, the data template of the normal sound signal is established by recording the historical normal leaf pneumatic audio signal, the envelope segment signal of the occurrence of the vane aerodynamic audio signal can be extracted from the original signal, so that the data templates of the subsequently established normal signals are the envelope signals of the individual vanes.
The audio processing device of the present application includes a first processing unit 21 and a second processing unit 22, as shown in fig. 4.
The first processing unit is used for extracting an envelope signal from the audio signal, wherein the envelope signal comprises the short-time average amplitude of each frame signal in the audio signal.
The second processing unit is adapted to detect the envelope signal based on the above mentioned sound data template to determine whether the envelope signal is abnormal, and if so, to mark it as an abnormal envelope signal for further detection below.
The video processing equipment is used for detecting the image of the current blade corresponding to the abnormal envelope signal.
When the abnormal envelope signal is monitored, the image of the current blade corresponding to the abnormal envelope signal is detected to determine whether the current blade really has a corresponding fault.
The defect characteristics in the extracted image are the key for identifying the defect image of the blade, and when the blade has serious defects and the image is clear, whether the blade has faults or not can be accurately identified according to the color characteristics and the shape characteristics selected manually. But the early defects of the fan blade are fine; the inherent structure (such as a lightning receptor, a tip drain hole, a spoiler, a hub cover seam and the like) of the surface of the blade generates interference, and the image defect characteristics of the blade are complex and various under the influence of the change of a shooting angle, a focal length, illumination and shadow. The above problems lead to the difficulty of satisfying the requirement of identifying the blade defects by manually selected image characteristics. The video processing apparatus of the present application includes a third processing unit 31 and a fourth processing unit 32, as shown in fig. 5.
The third processing unit is used for carrying out image segmentation on the image to obtain a plurality of image areas. The size or position of the image area is determined according to engineering practice.
And the fourth processing unit is used for detecting each image area based on the fault identification model, judging that the blade has a fault if any image area determines that a corresponding defect exists, and outputting the type of the fault based on the fault identification model.
The fault recognition model is obtained by training a large number of samples acquired in advance based on a deep learning method, wherein the deep learning is an end-to-end machine learning method, and features can be automatically extracted layer by layer. Compared with the manually selected features, the features extracted by deep learning are more abstract, contain more implicit information and have stronger expression capability.
According to the technical scheme, the embodiment provides the blade state monitoring method of the wind driven generator, and particularly obtains the image and audio signals of each blade of the wind driven generator; detecting an envelope signal of the audio signal of each blade; when the abnormal envelope signal is detected, the image of the current blade generating the abnormal envelope signal is detected to determine whether the current blade generates a fault. Once the corresponding fault is found, the blade can be maintained, and the situation that the fault is further developed to cause the fracture failure of the whole blade is avoided.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The technical solutions provided by the present invention are described in detail above, and the principle and the implementation of the present invention are explained in this document by applying specific examples, and the descriptions of the above examples are only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method for monitoring the condition of a blade of a wind turbine, comprising the steps of:
acquiring an audio signal and an image of each blade of the wind driven generator;
detecting an envelope signal of an audio signal of each of the blades;
when an abnormal envelope signal is detected, detecting the image of the current blade generating the abnormal envelope signal so as to determine whether the current blade generates a fault.
2. The blade condition monitoring method of claim 1, wherein said acquiring image and audio signals of each blade of said wind turbine;
acquiring the audio signal collected by the fixed-position recording equipment;
and acquiring the images collected by the fixed camera position photographic equipment and the mobile camera position photographic equipment.
3. The blade condition monitoring method of claim 2, wherein the stationary camera position camera equipment comprises stationary camera equipment mounted to an aft portion of a wind turbine nacelle;
the mobile camera position photographing equipment comprises mobile photographing equipment arranged on an unmanned aerial vehicle, a ground inspection robot or a tower climbing robot.
4. The blade condition monitoring method according to claim 1, wherein said detecting an envelope signal of an audio signal of each of said blades comprises the steps of:
extracting the envelope signal from the audio signal, wherein the envelope signal comprises a short-time average amplitude of each frame signal in the audio signal;
and detecting the envelope signal based on a sound data template to determine whether the envelope signal is abnormal, wherein the sound data template comprises the envelope signal of the pneumatic audio signal of the normal blade.
5. The blade condition monitoring method according to claim 1, wherein the detecting the image of the current blade generating the abnormal envelope signal comprises the steps of:
carrying out image segmentation on the image to obtain a plurality of image areas;
and identifying each image area based on a fault identification model, and judging whether a fault area exists or not.
6. A blade condition monitoring device of a wind power generator, characterized by comprising:
the signal acquisition equipment is used for acquiring audio signals and images of each blade of the wind driven generator;
an audio processing device for detecting an envelope signal of an audio signal of each of the blades;
the video processing equipment is used for detecting the image of the current blade generating the abnormal envelope signal when the abnormal envelope signal is detected so as to determine whether the current blade generates a fault.
7. The blade condition monitoring device of claim 1, wherein the signal acquisition apparatus comprises:
the first receiving unit is used for receiving the audio signals collected by the fixed machine position recording equipment;
and the second receiving unit is used for acquiring the images acquired by the fixed camera position photographing equipment and the mobile camera position photographing equipment.
8. The blade condition monitoring apparatus of claim 7, wherein the stationary camera position camera equipment comprises stationary camera equipment mounted to an aft portion of a wind turbine nacelle;
the mobile camera position photographing equipment comprises mobile photographing equipment arranged on an unmanned aerial vehicle, a ground inspection robot or a tower climbing robot.
9. The blade condition monitoring apparatus of claim 6, wherein the audio processing device comprises:
a first processing unit, configured to extract the envelope signal from the audio signal, where the envelope signal includes a short-time average amplitude of each frame signal in the audio signal;
and the second processing unit is used for detecting the envelope signal based on a sound data template and determining whether the envelope signal is abnormal, wherein the sound data template comprises the envelope signal of the pneumatic audio signal of the normal blade.
10. The blade condition monitoring device of claim 6, wherein the video processing module comprises:
the third processing unit is used for carrying out image segmentation on the image to obtain a plurality of image areas;
and the fourth processing unit is used for identifying each image area based on a fault identification model and judging whether a fault area exists or not.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210108182.9A CN114439702A (en) | 2022-01-28 | 2022-01-28 | Blade state monitoring method and device of wind driven generator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210108182.9A CN114439702A (en) | 2022-01-28 | 2022-01-28 | Blade state monitoring method and device of wind driven generator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114439702A true CN114439702A (en) | 2022-05-06 |
Family
ID=81372175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210108182.9A Pending CN114439702A (en) | 2022-01-28 | 2022-01-28 | Blade state monitoring method and device of wind driven generator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114439702A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115855461A (en) * | 2022-11-18 | 2023-03-28 | 中节能风力发电股份有限公司 | System and method for abnormal noise of fan blade of wind turbine generator |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008033532A (en) * | 2006-07-27 | 2008-02-14 | Denso Corp | Method and apparatus for detecting abnormality in equipment provided with movable part |
| CN105651780A (en) * | 2015-12-28 | 2016-06-08 | 新疆金风科技股份有限公司 | Method, apparatus and system for detecting state of blower blade through unmanned plane |
| CN109322796A (en) * | 2017-07-31 | 2019-02-12 | 上海绿孚科技有限公司 | The blade state monitoring system and detection method of wind power generating set based on video image processing |
| CN109900713A (en) * | 2019-04-17 | 2019-06-18 | 中国人民解放军国防科技大学 | Camera-guided unmanned aerial vehicle wind power blade defect dynamic detection system and method thereof |
| KR20190108832A (en) * | 2018-03-15 | 2019-09-25 | (주)니어스랩 | Apparatus and Method for Detecting/Analyzing Defect of Windturbine Blade |
| WO2019227438A1 (en) * | 2018-05-31 | 2019-12-05 | 深圳市大疆创新科技有限公司 | Image processing method and device, aircraft, system, and storage medium |
| CN112324629A (en) * | 2020-11-09 | 2021-02-05 | 华能陕西靖边电力有限公司 | Wind power blade early damage monitoring system and method based on vibration and sound |
| CN112360699A (en) * | 2020-10-22 | 2021-02-12 | 华能大理风力发电有限公司 | Intelligent inspection and diagnosis analysis method for blades of full-automatic wind generating set |
-
2022
- 2022-01-28 CN CN202210108182.9A patent/CN114439702A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008033532A (en) * | 2006-07-27 | 2008-02-14 | Denso Corp | Method and apparatus for detecting abnormality in equipment provided with movable part |
| CN105651780A (en) * | 2015-12-28 | 2016-06-08 | 新疆金风科技股份有限公司 | Method, apparatus and system for detecting state of blower blade through unmanned plane |
| CN109322796A (en) * | 2017-07-31 | 2019-02-12 | 上海绿孚科技有限公司 | The blade state monitoring system and detection method of wind power generating set based on video image processing |
| KR20190108832A (en) * | 2018-03-15 | 2019-09-25 | (주)니어스랩 | Apparatus and Method for Detecting/Analyzing Defect of Windturbine Blade |
| WO2019227438A1 (en) * | 2018-05-31 | 2019-12-05 | 深圳市大疆创新科技有限公司 | Image processing method and device, aircraft, system, and storage medium |
| CN109900713A (en) * | 2019-04-17 | 2019-06-18 | 中国人民解放军国防科技大学 | Camera-guided unmanned aerial vehicle wind power blade defect dynamic detection system and method thereof |
| CN112360699A (en) * | 2020-10-22 | 2021-02-12 | 华能大理风力发电有限公司 | Intelligent inspection and diagnosis analysis method for blades of full-automatic wind generating set |
| CN112324629A (en) * | 2020-11-09 | 2021-02-05 | 华能陕西靖边电力有限公司 | Wind power blade early damage monitoring system and method based on vibration and sound |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115855461A (en) * | 2022-11-18 | 2023-03-28 | 中节能风力发电股份有限公司 | System and method for abnormal noise of fan blade of wind turbine generator |
| CN115855461B (en) * | 2022-11-18 | 2023-09-05 | 中节能风力发电股份有限公司 | Wind turbine generator fan blade noise abnormity system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108416294B (en) | Fan blade fault intelligent identification method based on deep learning | |
| CN110282143B (en) | Inspection method for offshore wind farm unmanned aerial vehicle | |
| CN110261394A (en) | Online fan blade damages real-time diagnosis system and method | |
| US11361423B2 (en) | Artificial intelligence-based process and system for visual inspection of infrastructure | |
| CN112360699A (en) | Intelligent inspection and diagnosis analysis method for blades of full-automatic wind generating set | |
| CN111199213B (en) | Method and device for detecting defects of equipment for transformer substation | |
| CN109060826B (en) | Wind-powered electricity generation blade detection device that does not shut down | |
| JP2022552449A (en) | Methods and apparatus for inspecting wind turbine blades, and equipment and storage media therefor | |
| CN103442209A (en) | Video monitoring method of electric transmission line | |
| CN112660745B (en) | Intelligent diagnosis method and system for carrier roller fault and readable storage medium | |
| CN111400961B (en) | Wind generating set blade fault judging method and device | |
| CN110239914B (en) | Longitudinal tearing detection early warning device and method for infrared audio-visual frequency spectrum fusion conveying belt | |
| CN109209783A (en) | A kind of method and device of the lightning damage based on noise measuring blade | |
| CN111708380B (en) | Wind turbine generator appearance defect detection method, platform, unmanned aerial vehicle and system | |
| CN113406107B (en) | Fan blade defect detection system | |
| CN111127448B (en) | Method for detecting air spring fault based on isolated forest | |
| CN114439702A (en) | Blade state monitoring method and device of wind driven generator | |
| CN111833336B (en) | System and method for detecting surface sand hole faults of wind power blade based on hyperspectrum | |
| CN110107461B (en) | Fan fault early warning method, device, equipment and computer readable storage medium | |
| CN112465776A (en) | Intelligent crack detection method based on fuzzy image on surface of wind turbine | |
| CN114638060B (en) | Fault prediction method, system and electronic equipment | |
| CN114442658B (en) | Automatic inspection system for power transmission and distribution line unmanned aerial vehicle and operation method thereof | |
| CN105203315A (en) | Air blower blade monitoring device arranged on inspection vehicle | |
| CN114612763A (en) | Wind turbine generator pitch bearing crack monitoring method and computer program product | |
| CN115163426A (en) | Draught fan fault detection method and system based on AI auscultation and draught fan safety system |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220506 |