CN114183312A - System and method for monitoring state of blades of wind turbine generator - Google Patents
System and method for monitoring state of blades of wind turbine generator Download PDFInfo
- Publication number
- CN114183312A CN114183312A CN202111469505.9A CN202111469505A CN114183312A CN 114183312 A CN114183312 A CN 114183312A CN 202111469505 A CN202111469505 A CN 202111469505A CN 114183312 A CN114183312 A CN 114183312A
- Authority
- CN
- China
- Prior art keywords
- wind turbine
- blade
- blades
- module
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000012545 processing Methods 0.000 claims abstract description 50
- 238000003745 diagnosis Methods 0.000 claims abstract description 21
- 230000015654 memory Effects 0.000 claims description 30
- 238000003860 storage Methods 0.000 claims description 19
- 238000004891 communication Methods 0.000 claims description 15
- 239000013307 optical fiber Substances 0.000 claims description 9
- 238000009434 installation Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000006378 damage Effects 0.000 abstract description 38
- 230000002159 abnormal effect Effects 0.000 abstract description 8
- 230000008569 process Effects 0.000 abstract description 8
- 230000000246 remedial effect Effects 0.000 abstract description 6
- 238000001514 detection method Methods 0.000 description 16
- 230000036541 health Effects 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 11
- 239000000835 fiber Substances 0.000 description 10
- 230000008859 change Effects 0.000 description 6
- 230000007547 defect Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000001228 spectrum Methods 0.000 description 5
- 238000001931 thermography Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000035882 stress Effects 0.000 description 4
- 241000239290 Araneae Species 0.000 description 3
- 238000005336 cracking Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000003763 carbonization Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000002405 diagnostic procedure Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000003862 health status Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 239000004576 sand Substances 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 208000025274 Lightning injury Diseases 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003628 erosive effect Effects 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000006355 external stress Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012933 kinetic analysis Methods 0.000 description 1
- 238000011068 loading method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000011241 protective layer Substances 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000010008 shearing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000004901 spalling Methods 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
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 discloses a system and a method for monitoring the state of a blade of a wind turbine generator, wherein the system comprises the following steps: the sound image acquisition module is used for acquiring the state information of the blades of the wind turbine generator and sending the state information to the data processing module; the data processing module is used for carrying out data processing on the received state information, determining target data meeting preset requirements and sending the target data to the diagnosis module; and the diagnosis module is used for judging the state of the received target data through an early warning algorithm and determining the fault type so as to realize the monitoring of the state of the blades of the wind turbine generator. The method adopts a mode of combining sound and image, and utilizes a pneumatic signal collector to collect abnormal signals generated in the operation process of the blades on the premise of not contacting the blades of the unit; the method can find faults under the condition of blade damage and small blade damage, early warn in advance, make corresponding remedial measures, effectively diagnose the state of the blades in real time and do not need manual operation.
Description
Technical Field
The invention relates to the technical field of blade health state monitoring, in particular to a system and a method for monitoring the blade state of a wind turbine generator.
Background
With the continuous development of new energy, the wind power integration machines are continuously increased, so that the later operation and maintenance of the wind generation set become new power of a wind power market, particularly, the problem of blade faults is always the problem of influencing the safe operation of the set, and the problem of the blade faults is continuously highlighted along with the increase of the service time of a fan. Therefore, a great deal of research has been conducted in the field of monitoring the health status of the blades and applied to field practice. However, the existing blade health state monitoring technology has the problems that all parts of the blade cannot be observed, the operation steps are complicated, the efficiency is low, and the monitoring technology is restricted by the problems of working environment and faults.
Disclosure of Invention
In view of this, the embodiment of the invention provides a system and a method for monitoring the state of a blade of a wind turbine generator, which solve the problems that in the prior art, the blade state monitoring process cannot be performed on all parts of the blade, the operation steps are complicated, and the problems of the working environment and the fault are restricted.
According to a first aspect, an embodiment of the present invention provides a system for monitoring a blade condition of a wind turbine, including: a sound image acquisition module, a data processing module and a diagnosis module, wherein,
the sound image acquisition module is used for acquiring the state information of the blades of the wind turbine generator and sending the state information to the data processing module;
the data processing module is used for carrying out data processing on the received state information, determining target data meeting preset requirements and sending the target data to the diagnosis module;
and the diagnosis module is used for carrying out state judgment on the received target data through an early warning algorithm and determining the fault type so as to realize monitoring of the state of the wind turbine blade.
The monitoring system for the state of the blades of the wind turbine generator set provided by the embodiment of the invention adopts a sound-image combination mode, and utilizes the pneumatic signal collector to collect abnormal signals appearing in the operation process of the blades on the premise of not contacting the blades of the wind turbine generator set; the method can find faults under the condition of blade damage and small blade damage, early warn in advance, make corresponding remedial measures, effectively diagnose the state of the blades in real time and do not need manual operation.
With reference to the first aspect, in a first embodiment of the first aspect, the sound image collection module includes: a noise collector and an image collector, wherein,
the noise collector consists of a microphone array, is arranged on the image collector and is used for collecting the pneumatic noise of the blades of the wind turbine generator;
and the image collector is used for collecting the image data of the wind turbine blade according to the collection signal.
With reference to the first embodiment of the first aspect, in a second embodiment of the first aspect, the image collector consists of two cameras,
the image collector is provided with a holder device and is used for integrally shooting the blades of the wind turbine generator;
the installation direction of the image collector is towards the direction of the blades of the wind turbine generator, the image collector is connected with the blades through bolts and is fixed on a wind direction indicator support at the top of the cabin.
With reference to the first implementation manner of the first aspect, in a third implementation manner of the first aspect, the data processing module includes: a pneumatic noise processing sub-module and an image data processing sub-module, wherein,
the pneumatic noise processing submodule is used for extracting the characteristics of the pneumatic noise and determining the noise characteristics;
the pneumatic noise processing submodule is also used for analyzing the noise characteristics through a fault type recognition model to determine the fault type, and the fault type recognition model is a model obtained through neural network training;
the image data processing submodule is used for collecting the fault type of the pneumatic noise processing submodule and feeding back the acquisition signal corresponding to the fault type to the image collector so as to drive the image collector to acquire the image data of the corresponding wind turbine blade and determine the target data.
With reference to the first aspect, in a fourth implementation of the first aspect, the diagnostic module includes: a storage sub-module and an early warning sub-module, wherein,
the storage submodule is used for performing appointed storage on the received target data according to a preset storage rule;
and the early warning submodule is used for judging whether the fault type is an alarm type according to an early warning algorithm and alarming the fault of the damaged blade according to a judgment result.
With reference to the first aspect, in a fifth embodiment of the first aspect, the image acquisition module is powered up in a cabin control cabinet to ensure the operation of the image acquisition module.
With reference to the first aspect, in a sixth implementation manner of the first aspect, the system further includes: and the communication module is used for receiving the target data and transmitting the target data to the diagnosis module through an optical fiber.
According to a second aspect, the method for monitoring the state of the blades of the wind turbine generator provided by the embodiment of the invention comprises the following steps:
acquiring state information of blades of the wind turbine generator;
performing data processing on the state information to determine target data;
judging the state of the target data according to an early warning algorithm, and determining the fault type;
and judging whether the wind turbine generator blade corresponding to the target data is a damaged blade or not by using the fault type so as to determine an alarm signal, and carrying out fault alarm on the damaged blade according to the alarm signal.
According to the monitoring method for the state of the blades of the wind turbine generator, provided by the embodiment of the invention, the abnormal signals generated in the operation process of the blades are collected by the pneumatic signal collector in a mode of combining sound and image on the premise of not contacting the blades of the generator; the method can find faults under the condition of blade damage and small blade damage, early warn in advance, make corresponding remedial measures, effectively diagnose the state of the blades in real time and do not need manual operation.
According to a third aspect, an embodiment of the present invention provides an electronic device, including: the monitoring method for the blade state of the wind turbine generator set comprises a memory and a processor, wherein the memory and the processor are connected in a communication mode, computer instructions are stored in the memory, and the processor executes the computer instructions so as to execute the monitoring method for the blade state of the wind turbine generator set in the second aspect or any one embodiment of the second aspect.
According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the method for monitoring the state of a wind turbine blade according to the second aspect or any one of the embodiments of the second aspect.
Drawings
In order to more clearly illustrate the embodiments of the present invention 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, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic view of a monitoring system for wind turbine blade condition according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a sound image collection module in a monitoring system for the condition of a wind turbine blade according to a preferred embodiment of the invention;
FIG. 3 is a schematic view of the installation position of the sound image collection device in the monitoring system for the condition of the blades of the wind turbine generator according to another preferred embodiment of the present invention;
FIG. 4 is a flow chart of another method of monitoring a condition of a wind turbine blade according to a preferred embodiment of the present invention;
fig. 5 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. 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 invention.
The new energy is developed rapidly, particularly, the occurrence of 'rush installation tide' in recent two years, and the wind power accumulation grid-connected installation reaches 2.1 hundred million kilowatts. Therefore, the later operation and maintenance of the wind turbine generator becomes new power of the wind power market, especially the problem of blade fault always affects the safe operation of the wind turbine generator, and along with the increase of the service time of the fan, the problem of blade fault is continuously highlighted, and the damage types and mechanisms of blade fault are shown in the following table:
TABLE 1 blade Fault Damage mechanism and types
| Failure damage mechanism | Type of fault damage |
| Friction of | Surface friction, sand hole |
| Etching of | Spalling of the protective layer, pitting and erosion of the front end |
| High temperature radiation | Carbonization, embrittlement, fracture of materials |
| Low temperature | Icing, cracking |
| Vibration of machine set | Cracks, splits, breaks |
| Lightning stroke | Carbonization of material, cracking of trailing edge, breakdown |
Foreign wind power industry starts earlier, and various methods are researched for the problem of fault diagnosis of blades of a wind turbine, such as: smith et al have developed blade fault detection methods based on vibration and acoustic emission, as well as methods for diagnosing damage to composite blade structures using contact infrared thermometers. In 2000, GhoshalA, and the like collect blade vibration signals through a piezoelectric ceramic sensor and a laser Doppler vibrometer, and extract state information of the blades of the unit from sound signals collected by four different algorithms. Yanfeng Wang et al monitor the position and degree of blade damage using a diagnostic method based on kinetic analysis and a vibration pattern difference curve. Tang collects the blade acoustic emission signals through the sensor arranged in the fan blade, and determines the damage position of the blade by utilizing the signals collected by various sensors and time delay, so as to obtain an ideal test result. In 2010, a blade fault method based on fiber bragg gratings is developed, and a relatively ideal effect is achieved. At present, companies abroad also have corresponding monitoring systems, such as a windcon3.0 system developed by the swedish SKF company, a TCM system developed by the danish ram & Juhl company, an RMS system developed by the Moog Insensys Ltd company, and the like, which perform health detection on components of the wind turbine generator, such as blades, main shafts, wheel boxes, generators, and the like, in different monitoring modes.
The wind power generation industry in China starts late, but thick, thin and thin, colleges and universities, enterprise research institutes, wind power complete machine manufacturers, wind power owners, third-party operation and maintenance service units and the like develop a lot of research in the field of monitoring the health state of blades and are applied to field practice. In addition, a blade health state monitoring method based on a fiber grating sensor is also developed in recent years. A grating Bragg sensor and a strain gauge are laid in the blade, and the feasibility of the grating sensor on the health monitoring of the fan blade is verified through single-point and multi-point loading tests of the blade; acquiring an impact response signal of the blade through a fiber grating sensor arranged on the outer surface of the blade, extracting signal characteristics by combining a wavelet packet energy spectrum algorithm, and preliminarily identifying the damage of the fan blade; and the fiber bragg grating sensors are distributed on the inner sides of the fan blades, and the fault of the fan blades is detected by combining a wavelet packet method. The intelligent measurement and control limited company breaks through the technical limit in foreign countries, and develops a wind power blade optical fiber monitoring system with independent intellectual property rights.
Besides the detection methods, a small number of scientific researchers carry out blade fault diagnosis by methods such as infrared thermal imaging and pneumatic analysis. Aiming at the defects of fan blade infrared thermal imaging detection, a processing algorithm capable of improving the signal-to-noise ratio of an image and enhancing a crack image is provided, and a foundation is laid for subsequent fan blade crack depth detection. And moreover, the aeroelasticity analysis is carried out on the fan blade by using an energy method and an EMD method, the crack fault of the blade is identified, and the effectiveness of the method is verified in a laboratory environment. Mongolian new energy development limited company introduces unmanned aerial vehicle technique in the state electricity, and unmanned aerial vehicle utilizes high definition camera to shoot the whole situation and the detail image of fan blade, and detection personnel observes blade surface state and carries out fault diagnosis through the real-time image that receives, provides new thinking for fan blade intelligent monitoring.
In the present embodiment, a monitoring system for the condition of the blades of the wind turbine is also provided, and as used below, the term "module" may implement a combination of software and/or hardware for a predetermined function. While the system described in the embodiments below is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.
In the prior art, the wind turbine generator blade state is monitored mainly by adopting a direct observation method, a blade acoustic emission monitoring technology, a blade vibration detection technology, a blade health monitoring technology based on a fiber grating sensor, a resistance strain detection technology and a blade fault diagnosis technology by an infrared thermal imaging method.
The direct observation method is a diagnosis method for judging the state of the blade by directly observing the surface condition of the wind turbine blade by a patrol inspector with naked eyes, and the real-time surface condition of the blade is acquired by a high-power telescope, a spider man, an unmanned aerial vehicle and the like. The mode can directly and effectively diagnose the state of the blade in real time, but the blade state is realized by manual operation, the labor cost is high, and the development direction of production automation is not met. Various observation modes also have corresponding defects, and the high power telescope has a visual field blind area and cannot observe all parts of the blade; the steps of the spider man are complicated, and the efficiency is low; unmanned aerial vehicles then receive the restriction of operational environment and trouble problem.
The acoustic emission detection method is one of the deepest researched and most widely applied methods in the current blade health diagnosis technology. When the conditions such as the aerodynamic and mechanical properties, the external stress, the temperature and the like of the blade change, the original vibration mode of the blade is also influenced, and the internal energy of the blade is released in the form of transient elastic waves, namely, the acoustic emission phenomenon is formed. Any physical changes of the blade, including abrasion, deformation, cracking and the like, generate different acoustic emission waves, so that dynamic changes of blade stress changes, crack extension, surface corrosion and the like can be known through real-time detection of the acoustic emission waves.
The blade is subjected to factors such as shearing wind, unit variable pitch and yaw, self pneumatic performance and the like in the operation process, and an excitation source appears, so that lower-amount regular vibration is generated, the associated phenomenon is generated when the blade operates, and the blade contains rich blade operation state information. When the aerodynamic performance of the blade is affected due to the fault damage of the blade, the vibration characteristic of the blade also changes correspondingly, so to speak, the type and the position of the fault of the blade are different, and the vibration characteristic of the blade is also different. Therefore, the vibration diagnosis method can accurately identify the corresponding fault type and position according to the real-time vibration signals of the blades. Thereby monitoring the health and operating conditions of the blades.
The fiber grating diagnostic method is characterized in that fiber grating sensors are adhered or embedded in each part of the blade in advance, when the blade is deformed under the influence of external force deformation or temperature change, grating constants of the fiber sensors can be changed, so that the wavelength and the reflection propagation path of reflected waves in the optical fiber are changed, and the health diagnosis of the blade is realized by collecting reflection spectrum information and combining a corresponding signal analysis method.
The resistance strain detection technology is characterized in that a resistance strain gauge is adhered to the surface of a blade to serve as a sensing component, and the stress condition of the blade is determined by monitoring the change of a resistance value according to the principle that the resistance value changes along with the stress deformation of the blade. Because the deformation and stress change of the blades with different defects are different under the same external force, the change condition of the resistance value can reflect whether the blade is damaged or not.
The infrared thermal imaging detection technology captures electromagnetic waves radiated by the fan blade through an infrared detector, so that the temperature field of the blade is calculated to form a thermal image. If the interior of the blade has defects or faults, the surface temperature field of the blade is distributed abnormally, and the health condition of the blade can be judged by continuously acquiring and comparing the thermal image change condition of the temperature field of the blade by a thermal imager. In addition, the defect area can be quantitatively calculated by combining a professional infrared image processing technology.
However, the above methods have certain problems, such as: the direct observation method can directly and effectively diagnose the state of the blade in real time, but the direct observation method needs manual operation, has higher labor cost and does not conform to the development direction of production automation. Various observation modes also have corresponding defects, and the high power telescope has a visual field blind area and cannot observe all parts of the blade; the steps of the spider man are complicated, and the efficiency is low; unmanned aerial vehicles then receive the restriction of operational environment and trouble problem. Acoustic emission detects and need punch the installation sensor on the blade with vibration detection, not only can cause the destruction of the original structure of blade, and the installation and the later maintenance of sensor are comparatively difficult moreover, and required sensor is more. In addition, due to the influence of vibration of an engine and a transmission chain in the engine room, the acquired vibration signals and the acoustic emission signals easily contain various complex and changeable noises, and the work of signal denoising processing and the like in the later period has great difficulty. The fiber grating detection and the resistance strain gauge detection need to embed a fiber grating sensor in the material or paste the sensor on the surface of the blade in the blade manufacturing process, the integrated manufacturing of the sensor and the blade is difficult to realize, the influence of the number and the arrangement positions of the sensors on the monitoring result is large, the contact type sensor has limitations, the sensor can fall, lose efficacy, damage and other conditions possibly after long-time operation, and the sensor cannot be maintained in the operation process of the fan blade. The infrared thermal imaging detection has low detection sensitivity to deeper damage positions, is greatly influenced by environmental factors, and has certain difficulty in real-time health monitoring of the blades.
Therefore, in order to solve the above problem, the present invention discloses a monitoring system for the blade state of a wind turbine, as shown in fig. 1, including: a sound image collection module 01, a data processing module 02, and a diagnosis module 03, wherein,
the sound image acquisition module 01 is used for acquiring the state information of the blades of the wind turbine generator and sending the state information to the data processing module 02; the data processing module 02 is used for performing data processing on the received state information, determining target data meeting preset requirements, and sending the target data to the diagnosis module 03; and the diagnosis module 03 is used for performing state judgment on the received target data through an early warning algorithm and determining a fault type so as to monitor the state of the blades of the wind turbine generator.
The monitoring system for the state of the blades of the wind turbine generator set provided by the embodiment adopts a sound-image combination mode, and acquires abnormal signals generated in the operation process of the blades by using a pneumatic signal collector on the premise of not contacting the blades of the wind turbine generator set; the method can find faults under the condition of blade damage and small blade damage, early warn in advance, make corresponding remedial measures, effectively diagnose the state of the blades in real time and do not need manual operation.
In another embodiment, the sound image collection module 01 includes: the noise collector consists of a microphone array, is arranged on the image collector and is used for collecting the pneumatic noise of the blades of the wind turbine generator; and the image collector is used for collecting the image data of the wind turbine blade according to the collection signal. The image collector consists of two cameras, and is provided with a holder device for integrally shooting the blades of the wind turbine generator; the image collector is installed in the direction facing the blades of the wind turbine generator system, is connected through bolts and is fixed on a wind direction indicator support at the top of the cabin.
Specifically, a structure diagram of the acousto-optic monitoring device is specifically given as shown in fig. 2 for a pneumatic noise collector (microphone array 2) and an image collector (high-definition dual-camera 1), wherein the structure diagram is specifically installed as shown in fig. 3, the microphone array is configured on the image collector device, and a set of integral monitoring device is integrated. The microphone arrays are arranged at intervals of 90 degrees in the direction around the image collector equipment, and are totally arranged by 4, so that the pneumatic noise collection of the monitoring blades in any wind direction is realized. High definition double camera has the full-color function of day night and is equipped with cloud platform device, can realize the whole shooting to unit blade day night. The whole set of monitoring equipment is powered up in the cabin control cabinet.
The sufficient IP67 protection level of a whole set of monitoring facilities installs rain-proof cover, dust screen and lightning protection device additional, can fully protect equipment, can stand the examination of bad weather such as wind, rain, snow, thunder and lightning to prevent the destruction of sand and dust to equipment. The high-definition camera device with the microphone array is installed towards the blades and connected through bolts, AB glue is evenly coated at the bottom of the high-definition camera device, and the high-definition camera device is fixed on a wind direction instrument support at the top of the cabin.
In this embodiment, the data processing module 02 includes: the device comprises a pneumatic noise processing submodule and an image data processing submodule, wherein the pneumatic noise processing submodule is used for extracting characteristics of pneumatic noise and determining noise characteristics; the pneumatic noise processing submodule is also used for analyzing the noise characteristics through a fault type recognition model to determine the fault type, and the fault type recognition model is a model obtained through neural network training; and the image data processing submodule is used for collecting the fault type of the pneumatic noise processing submodule and feeding back an acquisition signal corresponding to the fault type to the image acquisition device so as to drive the image acquisition device to acquire the image data of the corresponding wind turbine blade and determine target data.
Specifically, the monitoring system for the state of the wind turbine blade provided by this embodiment further includes: and the communication module is used for receiving the target data and transmitting the target data to the diagnostic module 03 through the optical fiber. The wind power plant operation monitoring system is mainly responsible for communication between front-end sound signal data and image data and a monitoring and diagnosing module 03 server, optical fiber communication from an engine room control cabinet to a tower-based control cabinet switch in a wind turbine is utilized, and then the data are input to a wind power plant operation monitoring center through an optical fiber ring network of a wind field in the tower-based control cabinet switch.
The acousto-optic signal collected by the acousto-optic monitoring equipment is transmitted to the switch of the control cabinet in the engine room through the communication optical fiber, the switch is connected with the data collection and processing industrial personal computer, and then the data is input to the wind power plant operation monitoring center through the optical fiber ring network of the wind field in the tower-based control cabinet switch.
Specifically, the diagnostic module 03 in the system in this embodiment includes: the early warning system comprises a storage submodule and an early warning submodule, wherein the storage submodule is used for appointing and storing received target data according to a preset storage rule; and the early warning submodule is used for judging whether the fault type is an alarm type according to an early warning algorithm and alarming the fault of the damaged blade according to a judgment result.
In this embodiment, the pneumatic noise data processing module 02: intercepting characteristic frequency and reducing and eliminating noise of a wind turbine blade pneumatic noise processing module (a band-pass filter); the measuring frequency range of the pneumatic noise collector is as follows: 20-20000Hz, the sampling frequency is set as: 48000 Hz. Preprocessing the data such as noise reduction and beam forming; then, carrying out Mel spectrum feature extraction on the noise data; and a characteristic frequency analysis module (fault damage type identification model-obtained by training a neural network model). Wherein, the image data processing module 02: according to the calculation result of the characteristic frequency analysis module, the mode of the fault damage identification module is identified by the fault damage identification module, the identification signal is fed back to the image collector, the high-definition double-camera positioning is adopted, the blade damage image is shot, the fan blade can be focused faster and more accurately in the running state, the day-night full-color function is achieved, and the good effect can be achieved in the low-light environment.
The monitoring system of wind turbine generator system blade state that this embodiment provided adopts the mode that the acoustic image combines, under the prerequisite of contactless unit blade, utilize the pneumatic signal collector to gather the abnormal signal that appears in the blade operation process, the abnormal signal that the high accuracy image collector was gathered and is monitored according to sound sensor carries out type discernment and accurate positioning to the fault damage through the fault damage model, and then carry out real-time supervision to the health status of blade, and can discover the trouble under the blade damage and little condition, early warning in advance, make corresponding remedial measure. The blade state can be effectively diagnosed in real time without manual operation, the sound image acquisition module is fixed at the top of the cabin and is monitored in a non-contact mode with the blade, holes do not need to be punched on the blade or the sensor does not need to be pasted on the blade, the problems that the sensor falls off, loses efficacy and is damaged after long-time operation do not exist, and the original structure of the blade cannot be damaged. The front-end data processing module can effectively remove noise, filter and position blade fault damage signals and image acquisition signals, and the monitoring and diagnosing module can effectively monitor and diagnose blade fault damage and provide early warning reports.
The embodiment provides a method for monitoring the state of a blade of a wind turbine generator, which can be used for electronic equipment such as a computer, a mobile phone, a tablet computer and the like. Fig. 4 is a flowchart of a method for monitoring the condition of a wind turbine blade according to an embodiment of the present invention, and as shown in fig. 4, the flowchart includes the following steps:
and S1, acquiring the state information of the wind turbine blade. The state information of the blades of the wind turbine generator can be acquired by referring to the acquisition equipment in the system embodiment, and mainly comprises aerodynamic noise, images of the blades and the like.
And S2, performing data processing on the state information and determining target data.
In this embodiment, the data processing may be performed on the state information obtained in the above steps, and may include noise reduction, beam forming and other pre-processing, and mel spectrum feature extraction is performed on noise data to determine final target data. It should be noted that the present embodiment is described by taking the above processing method as an example, and is not limited thereto.
And S3, performing state judgment on the target data according to the early warning algorithm, and determining the fault type.
In this embodiment, the determination may be performed by referring to a table of matching the target data of the damage and the fault type. And after the target data is determined, searching the corresponding fault type in the corresponding table.
And S4, judging whether the wind turbine generator blade corresponding to the target data is a damaged blade or not by utilizing the fault type to determine an alarm signal, and carrying out fault alarm on the damaged blade according to the alarm signal.
After receiving the preprocessed target data, storing the data at a designated position according to a preset storage rule; when the monitoring and diagnosing system sends a data calling request, the data of the data storage system can be accessed by a service with authority; the monitoring and diagnosing system can read, edit, search and delete data on the data storage system; the monitoring and diagnosing system inputs the preprocessed Mel spectrum characteristic data into an early warning algorithm of a neural network to judge the state of the blades of the unit; and comparing the established normal blade acoustic model with the fault acoustic characteristic model, and judging and confirming the fault type of the blade so as to achieve early warning, alarming and the like of the damage fault of the blade.
The monitoring method for the state of the blades of the wind turbine generator set provided by the embodiment adopts a mode of combining sound and image, under the premise of not contacting the blades of the wind turbine generator set, the pneumatic signal collector is used for collecting abnormal signals appearing in the operation process of the blades, the high-precision image collector carries out type recognition and accurate positioning on fault damage through the fault damage model according to the abnormal signals collected and monitored by the sound sensor, then real-time monitoring is carried out on the health state of the blades, faults can be found under the conditions of blade damage and small damage, early warning is carried out in advance, and corresponding remedial measures are taken. The blade state can be effectively diagnosed in real time without manual operation, the sound image acquisition module is fixed at the top of the cabin and is monitored in a non-contact mode with the blade, holes do not need to be punched on the blade or the sensor does not need to be pasted on the blade, the problems that the sensor falls off, loses efficacy and is damaged after long-time operation do not exist, and the original structure of the blade cannot be damaged. The method can effectively perform denoising, filtering and positioning on the blade fault damage signal and the image acquisition signal, effectively monitor and diagnose the blade fault damage, and provide an early warning report.
An embodiment of the present invention further provides an electronic device, please refer to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an alternative embodiment of the present invention, and as shown in fig. 5, the electronic device may include: at least one processor 601, such as a CPU (Central Processing Unit), at least one communication interface 603, memory 604, and at least one communication bus 602. Wherein a communication bus 602 is used to enable the connection communication between these components. The communication interface 603 may include a Display (Display) and a Keyboard (Keyboard), and the optional communication interface 603 may also include a standard wired interface and a standard wireless interface. The Memory 604 may be a random access Memory (random-access Memory) or a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The memory 604 may optionally be at least one storage device located remotely from the processor 601. Wherein the processor 601 may be associated with the system described in fig. 1, an application program is stored in the memory 604 and the processor 601 calls the program code stored in the memory 604 for performing any of the above-mentioned method steps.
The communication bus 602 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The communication bus 602 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 5, but this is not intended to represent only one bus or type of bus.
The memory 604 may include a volatile memory (RAM), such as a random-access memory (RAM); the memory may also include a non-volatile memory (english: non-volatile memory), such as a flash memory (english: flash memory), a hard disk (english: hard disk drive, abbreviated: HDD) or a solid-state drive (english: SSD); the memory 604 may also comprise a combination of the above types of memory.
The processor 601 may be a Central Processing Unit (CPU), a Network Processor (NP), or a combination of a CPU and an NP.
The processor 601 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a Programmable Logic Device (PLD), or a combination thereof. The PLD may be a Complex Programmable Logic Device (CPLD), a field-programmable gate array (FPGA), a General Array Logic (GAL), or any combination thereof.
Optionally, the memory 604 is also used for storing program instructions. The processor 601 may call a program instruction to implement the method for monitoring the state of the wind turbine blade as shown in the embodiment of the present application.
The embodiment of the invention also provides a non-transient computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the monitoring method for the state of the blades of the wind turbine generator in any method embodiment. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope defined by the appended claims.
Claims (10)
1. A monitoring system for the state of a wind turbine blade is characterized by comprising: a sound image acquisition module, a data processing module and a diagnosis module, wherein,
the sound image acquisition module is used for acquiring the state information of the blades of the wind turbine generator and sending the state information to the data processing module;
the data processing module is used for carrying out data processing on the received state information, determining target data meeting preset requirements and sending the target data to the diagnosis module;
and the diagnosis module is used for carrying out state judgment on the received target data through an early warning algorithm and determining the fault type so as to realize monitoring of the state of the wind turbine blade.
2. The system of claim 1, wherein the image acquisition module comprises: a noise collector and an image collector, wherein,
the noise collector consists of a microphone array, is arranged on the image collector and is used for collecting the pneumatic noise of the blades of the wind turbine generator;
and the image collector is used for collecting the image data of the wind turbine blade according to the collection signal.
3. The system of claim 2, wherein the image collector consists of two cameras,
the image collector is provided with a holder device and is used for integrally shooting the blades of the wind turbine generator;
the installation direction of the image collector is towards the direction of the blades of the wind turbine generator, the image collector is connected with the blades through bolts and is fixed on a wind direction indicator support at the top of the cabin.
4. The system of claim 2, wherein the data processing module comprises: a pneumatic noise processing sub-module and an image data processing sub-module, wherein,
the pneumatic noise processing submodule is used for extracting the characteristics of the pneumatic noise and determining the noise characteristics;
the pneumatic noise processing submodule is also used for analyzing the noise characteristics through a fault type recognition model to determine the fault type, and the fault type recognition model is a model obtained through neural network training;
the image data processing submodule is used for collecting the fault type of the pneumatic noise processing submodule and feeding back the acquisition signal corresponding to the fault type to the image collector so as to drive the image collector to acquire the image data of the corresponding wind turbine blade and determine the target data.
5. The system of claim 1, wherein the diagnostic module comprises: a storage sub-module and an early warning sub-module, wherein,
the storage submodule is used for performing appointed storage on the received target data according to a preset storage rule;
and the early warning submodule is used for judging whether the fault type is an alarm type according to an early warning algorithm and alarming the fault of the damaged blade according to a judgment result.
6. The system of claim 1, wherein the image acquisition module is powered up in a cabin control cabinet to ensure operation of the image acquisition module.
7. The system of claim 1, further comprising: and the communication module is used for receiving the target data and transmitting the target data to the diagnosis module through an optical fiber.
8. A method for monitoring the state of a blade of a wind turbine generator is characterized by comprising the following steps:
acquiring state information of blades of the wind turbine generator;
performing data processing on the state information to determine target data;
judging the state of the target data according to an early warning algorithm, and determining the fault type;
and judging whether the wind turbine generator blade corresponding to the target data is a damaged blade or not by using the fault type so as to determine an alarm signal, and carrying out fault alarm on the damaged blade according to the alarm signal.
9. An electronic device, comprising:
a memory and a processor, the memory and the processor are communicatively connected with each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the monitoring method for the condition of the wind turbine blade according to any one of the claims 8.
10. A computer-readable storage medium storing computer instructions for causing a computer to perform the method for monitoring the condition of a wind turbine blade according to claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111469505.9A CN114183312A (en) | 2021-12-03 | 2021-12-03 | System and method for monitoring state of blades of wind turbine generator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111469505.9A CN114183312A (en) | 2021-12-03 | 2021-12-03 | System and method for monitoring state of blades of wind turbine generator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114183312A true CN114183312A (en) | 2022-03-15 |
Family
ID=80542199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111469505.9A Pending CN114183312A (en) | 2021-12-03 | 2021-12-03 | System and method for monitoring state of blades of wind turbine generator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114183312A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114753976A (en) * | 2022-05-11 | 2022-07-15 | 北京唐智科技发展有限公司 | Method, device, equipment and medium for monitoring high-strength bolt fault of wind turbine generator |
| CN115163429A (en) * | 2022-07-26 | 2022-10-11 | 明阳产业技术研究院(沈阳)有限公司 | Wind power fan blade monitoring system and method and related equipment |
| CN115450858A (en) * | 2022-10-18 | 2022-12-09 | 山东大学 | Fan blade state detection method and system based on digital twinning |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10065314A1 (en) * | 2000-12-30 | 2002-07-18 | Igus Ingenieurgemeinschaft Umw | Method for condition monitoring of wind turbine rotor blades in which sound and vibration sensors are used to generate signals that can be compared with an existing database of signals so that rapid damage assessment can be made |
| CN103234585A (en) * | 2013-04-16 | 2013-08-07 | 内蒙古航天亿久科技发展有限责任公司 | Online monitoring and fault diagnosis system of large wind turbine units |
| WO2015005663A1 (en) * | 2013-07-10 | 2015-01-15 | 주식회사 글로비즈 | Signal measurement diagnosis monitoring system and method therefor, and method and system for applying same to individual device |
| 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 |
| 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 |
| WO2021159919A1 (en) * | 2020-02-10 | 2021-08-19 | 中国海洋大学 | System and method for monitoring health state of offshore wind power wind turbine and sound waves of sea waves |
| CN113623144A (en) * | 2021-09-01 | 2021-11-09 | 五凌电力有限公司 | Blade state monitoring system based on acoustic algorithm and monitoring method thereof |
-
2021
- 2021-12-03 CN CN202111469505.9A patent/CN114183312A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10065314A1 (en) * | 2000-12-30 | 2002-07-18 | Igus Ingenieurgemeinschaft Umw | Method for condition monitoring of wind turbine rotor blades in which sound and vibration sensors are used to generate signals that can be compared with an existing database of signals so that rapid damage assessment can be made |
| CN103234585A (en) * | 2013-04-16 | 2013-08-07 | 内蒙古航天亿久科技发展有限责任公司 | Online monitoring and fault diagnosis system of large wind turbine units |
| WO2015005663A1 (en) * | 2013-07-10 | 2015-01-15 | 주식회사 글로비즈 | Signal measurement diagnosis monitoring system and method therefor, and method and system for applying same to individual device |
| 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 |
| WO2021159919A1 (en) * | 2020-02-10 | 2021-08-19 | 中国海洋大学 | System and method for monitoring health state of offshore wind power wind turbine and sound waves of sea waves |
| 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 |
| CN113623144A (en) * | 2021-09-01 | 2021-11-09 | 五凌电力有限公司 | Blade state monitoring system based on acoustic algorithm and monitoring method thereof |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114753976A (en) * | 2022-05-11 | 2022-07-15 | 北京唐智科技发展有限公司 | Method, device, equipment and medium for monitoring high-strength bolt fault of wind turbine generator |
| CN115163429A (en) * | 2022-07-26 | 2022-10-11 | 明阳产业技术研究院(沈阳)有限公司 | Wind power fan blade monitoring system and method and related equipment |
| CN115450858A (en) * | 2022-10-18 | 2022-12-09 | 山东大学 | Fan blade state detection method and system based on digital twinning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114183312A (en) | System and method for monitoring state of blades of wind turbine generator | |
| US20170241957A1 (en) | Laser ultrasonic imaging system for a rotating object and method thereof | |
| CN109869286B (en) | Vibration state monitoring method for wind generating set | |
| KR100798006B1 (en) | Integrated monitoring/diagnosis method for nuclear device and system using the same | |
| US11828267B2 (en) | Wind turbine blade monitoring systems | |
| CN109186744B (en) | Turbine blade crack evaluation system and turbine blade crack early warning method | |
| Sun et al. | In-situ condition monitoring of wind turbine blades: A critical and systematic review of techniques, challenges, and futures | |
| CN109209783A (en) | A kind of method and device of the lightning damage based on noise measuring blade | |
| CN109236587B (en) | Alarm system for detecting abnormal work of wind driven generator | |
| US20190178852A1 (en) | Structural health monitoring of cyclically loaded structures | |
| CN106706241B (en) | Active self-checking device and method for damage of wind turbine blade | |
| CN113406107B (en) | Fan blade defect detection system | |
| CN115374959A (en) | Health management method and system for aircraft engine | |
| CN111311872A (en) | Long-term monitoring and alarming system for stress of hull structure | |
| CN114565571A (en) | Fan blade defect detection method and device based on computer vision | |
| KR101410923B1 (en) | Laser ultrasonic imaging of a rotating blade | |
| CN105784364A (en) | Bearing fault diagnosis method based on total experience mode decomposition and fractal box dimensions | |
| CN117647526A (en) | Wind driven generator blade surface defect detection method and device | |
| CN113504302B (en) | Method and system for monitoring fan blade state, electronic equipment and storage medium | |
| CN116794447A (en) | Cable line fixed-point abnormality detection system and method based on unmanned equipment | |
| EP3882599B1 (en) | Detection of transient events | |
| CN114233581A (en) | Intelligent patrol alarm system for fan engine room | |
| CN112362751A (en) | Online monitoring method and system for power transformation framework | |
| CN113763679B (en) | Method and device for monitoring abnormal sound of gas insulated enclosed type combined electrical apparatus | |
| CN114549436A (en) | Multi-mode-based fan blade defect detection method, system, equipment and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221012 Address after: No. 2, xizhuan Hutong, Caishikou street, Xicheng District, Beijing 100052 Applicant after: Datang renewable energy test and Research Institute Co.,Ltd. Address before: 100041 room a-1725, 2nd floor, building 3, yard 30, Shixing street, Shijingshan District, Beijing Applicant before: CHINA DATANG CORPORATION NEW ENERGY SCIENCE AND TECHNOLOGY RESEARCH INSTITUTE Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| 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 |
Application publication date: 20220315 |
|
| RJ01 | Rejection of invention patent application after publication |