CN113623144A - Blade state monitoring system based on acoustic algorithm and monitoring method thereof - Google Patents
Blade state monitoring system based on acoustic algorithm and monitoring method thereof Download PDFInfo
- Publication number
- CN113623144A CN113623144A CN202111022668.2A CN202111022668A CN113623144A CN 113623144 A CN113623144 A CN 113623144A CN 202111022668 A CN202111022668 A CN 202111022668A CN 113623144 A CN113623144 A CN 113623144A
- Authority
- CN
- China
- Prior art keywords
- data
- noise
- blade
- monitoring
- module
- 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 56
- 238000000034 method Methods 0.000 title claims description 14
- 238000013500 data storage Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000001228 spectrum Methods 0.000 claims abstract description 10
- 238000013528 artificial neural network Methods 0.000 claims abstract description 7
- 230000002452 interceptive effect Effects 0.000 claims abstract description 7
- 238000010438 heat treatment Methods 0.000 claims description 20
- 239000000919 ceramic Substances 0.000 claims description 4
- 230000005236 sound signal Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000007499 fusion processing Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 8
- 230000007613 environmental effect Effects 0.000 abstract description 6
- 230000010354 integration Effects 0.000 abstract description 2
- 238000012423 maintenance Methods 0.000 description 14
- 238000009434 installation Methods 0.000 description 8
- 239000013307 optical fiber Substances 0.000 description 4
- 208000025274 Lightning injury Diseases 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000009413 insulation Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 239000012528 membrane Substances 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 2
- 238000000576 coating method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 239000004576 sand Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 239000010963 304 stainless steel Substances 0.000 description 1
- 229910000589 SAE 304 stainless steel Inorganic materials 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual 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
-
- 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)
- 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)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention relates to the technical field of noise acquisition for a fan, in particular to a blade state monitoring system based on an acoustic algorithm, which comprises noise acquisition equipment arranged below a fan tower, wherein fan blade noise signals acquired by the noise acquisition equipment are transmitted to a data acquisition system through a network for uniform processing, and the acquired data are temporarily stored through a data storage system; fan noise data temporarily stored in the data storage system are analyzed by a monitoring and early warning system, Mel spectrum features of noise are extracted through the monitoring and early warning system and are compared with standard values in a neural network, accordingly fault reasons of the blades are identified, and finally the analyzed data are displayed through an interactive interface. The invention effectively reduces the influence of severe working environment and complex environmental noise on the collector, and simultaneously meets the requirements of acoustic performance and environmental reliability; the problem of insufficient fault samples is solved by applying a model integration technology based on unsupervised and weakly supervised models.
Description
Technical Field
The invention relates to the technical field of noise collection for fans, in particular to a blade state monitoring system based on an acoustic algorithm and a monitoring method thereof.
Background
At present, fault detection of key components such as wind power plant blades mainly depends on manual on-site listening and visual observation, and as wind power plants are often arranged in remote areas such as mountains, islands and the like, maintenance personnel are difficult to observe on site in time under the influence of traffic and weather, so that faults are difficult to discover in time, and destructive consequences are often caused during discovery. Generally, the local climate environment where the collectors are arranged is a severe field environment, severe weather such as high wind, sand and dust, rainstorm, low-temperature freezing, high-temperature solarization and thunderstorm brings great challenges to the reliability and stability of the collectors, in addition, the power supply of the wind power plant is unstable to cause power supply noise interference, and the box-type transformer under the tower drum and electromagnetic interference caused by other electronic devices in the collectors.
In the prior art, the following technical routes are mainly used for monitoring the fan blade:
(1) based on the vibration sensor: the sensor is mainly used for fault monitoring and icing monitoring, and a vibration sensor is arranged on the surface of a blade, so that when a mechanical structure is in fault, the machine or a unit usually shows abnormal vibration in operation. The blade is provided with a vibration sensor, so that parameters such as modal frequency, modal vibration mode and modal damping of blade vibration are obtained, and the dynamic characteristic change condition of the blade is obtained by analyzing the parameters, so that the health state of the blade is judged, and the fault early warning of the blade is carried out. The main disadvantages are: the hardware cost is high; sensors are required to be installed and wired in the blades, power is supplied to the engine room, data is transmitted, and installation and maintenance are complex; the application condition is limited, and the sensor has high sensitivity to the environment and is easily influenced by temperature and humidity; is insensitive to vane surface wear.
(2) Based on the acoustic emission technology: the method is used for detecting the condition that the wind power blade generates defects inside under the condition of applying loads. By installing a sensor at a specific part (vulnerable part) of the blade, and by amplifying and filtering, the acoustic emission refers to a phenomenon that elastic energy released when a material is broken propagates in a structure in the form of stress waves. With the discovery of the piezoelectric effect, a stress wave can be converted from a force signal to an electric signal through the piezoelectric effect of a piezoelectric material (such as piezoelectric ceramics PZT), and the electric signal is received by a system, and the damage detection of the material is realized by analyzing the signal characteristics of the stress wave, such as waveform, frequency, amplitude, time course, wave number and the like. The main disadvantages are: the hardware cost is high; the rapid attenuation of the acoustic emission technology requires that the acoustic emission sensor is deployed near a damaged position, and the installation and maintenance are complex; the application condition is limited, and the sensor has high sensitivity to the environment and is easily influenced by temperature and humidity.
(3) Based on image recognition: the method is used for fault monitoring, lightning stroke monitoring and icing monitoring. The top of the tower barrel is provided with a long-focus high-definition camera; the top of the tower barrel is provided with a long-focus high-definition camera, video shooting is carried out on the blades in the view, and fault identification of the blades is carried out through an image identification technology. The main disadvantages are: the installation degree of difficulty is high. The installation and wiring are required to be carried out by climbing out of the engine room, and the installation and maintenance are complex; the visibility is greatly influenced, and the device is easily influenced by cloud, light and the like.
(4) Based on the blade tip timing technology: the method is used for measuring blade flutter, blade stress, blade fatigue, blade vibration abnormity and the like. A plurality of blade tip timing sensors are installed on the outer side of a blade tip rotating track along the radial direction; the time of the blade tip sweeping the same position is measured through the multi-pulse sensor, and due to the vibration of the blade, the end part of the blade deviates forwards or backwards relative to the rotating direction, so that the actual time of the blade reaching the sensor each time is not equal to the time of the blade reaching the sensor when the blade is supposed to have no vibration, a time difference is generated, and the time difference is converted into the time for carrying out fault early warning on the vibration measurement of the blade through an algorithm. The main disadvantages are: the influence of the sensor precision is large; the application condition is limited, and the sensor has high sensitivity to the environment and is easily influenced by temperature and humidity; the method has good identification effect on synchronous and asynchronous vibration of the blade, and is insensitive to unconventional vibration states such as flutter and stall.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a blade state monitoring system based on an acoustic algorithm and a monitoring method thereof.
In order to achieve the purpose, the invention is realized by the following technical scheme: the invention provides a blade state monitoring system based on an acoustic algorithm, which comprises noise acquisition equipment arranged below a fan tower drum, wherein fan blade noise signals acquired by the noise acquisition equipment are transmitted to a data acquisition system through a network for uniform processing, and acquired data are temporarily stored through a data storage system; fan noise data temporarily stored in the data storage system are analyzed by a monitoring and early warning system, Mel spectrum features of noise are extracted through the monitoring and early warning system and are compared with standard values in a neural network, accordingly fault reasons of the blades are identified, and finally the analyzed data are displayed through an interactive interface.
According to the technical scheme, in the blade state monitoring system based on the acoustic algorithm, the noise acquisition equipment comprises an acquisition module, a network module, a protection module and a power supply module which are arranged in an acquisition device main body box, and the acquisition device main body box is arranged below a fan tower cylinder through a fixed support; the collecting module consists of a microphone array and an audio collecting board, sound signals collected by the microphone array are processed by the audio collecting board and then transmitted to the outside by the network module, and the protecting module comprises a heating sheet and a dehumidifying device which are arranged in the collector main body box; the power module adopts a combination of a self-reset lightning protection device and an industrial power supply, and the industrial power supply supplies power to the network module, the protection module and the acquisition module.
In the blade state monitoring system based on the acoustic algorithm, the microphone array is mounted on the support plate at the top of the collector main body box, an annular buffer net is arranged outside the microphone array, and a sound-proof cover is further arranged outside the microphone array; the audio acquisition board is arranged on the back of the microphone array, and a processing chip of the audio acquisition board adopts FPGA or STM32 MCU; and an electromagnetic shielding cover is arranged on the outer side of the audio acquisition board.
In the blade state monitoring system based on the acoustic algorithm, a support column is arranged on the side wall of the collector main body box, and a DIN rail is mounted on the support column and used for mounting and fixing the network module, the protection module and the power module; the microphone array is adhered with the heating sheet; the heating plate is a plastic heating plate or a ceramic heating plate.
According to the blade state monitoring system based on the acoustic algorithm, the data acquisition system, the data storage system and the monitoring and early warning system are connected and communicated through the industrial Ethernet.
In the blade state monitoring system based on the acoustic algorithm, the audio collector of the noise collection device measures a frequency range that is: 20-20000Hz, the sampling frequency is set as: 48000 Hz.
A monitoring method of a blade state monitoring system based on an acoustic algorithm comprises the following steps:
(1) the noise signal is collected by the noise collecting equipment, is sent to a data collecting system through network service, is subjected to primary fusion processing on collected data, meteorological information and unit information, and then is sent to a data storage system;
(2) the data storage system stores the data at a designated position according to a preset storage rule; when the monitoring and early warning system sends a data calling request, the data of the data storage system can be accessed by a service with permission;
(3) the monitoring and early warning system can read, edit, search and delete data on the data storage system;
(4) after the monitoring and early warning system acquires the collected noise data in real time, the following operations are respectively executed:
preprocessing the data such as noise reduction and beam forming;
carrying out Mel spectrum feature extraction on the noise data;
inputting Mel spectrum characteristic data into early warning algorithm of neural network to judge state of target;
(5) and displaying the analyzed and judged data through an interactive interface.
The collector can be arranged under a tower drum of a wind power plant, collects noise generated when a field fan operates, sends the noise to the centralized control center through a network to perform blade fault identification and early warning based on big data and artificial intelligence, can help an operation and maintenance team and an operation and maintenance system to realize tracking and monitoring of the health state of the fan blades, and provides scientific decision support.
The invention provides the following beneficial effects: the invention effectively reduces the influence of severe working environment and complex environmental noise on the collector, and simultaneously meets the requirements of acoustic performance and environmental reliability; the problem of insufficient fault samples is solved by applying a model integration technology and based on unsupervised and weakly supervised models; the working noise of the fan blade is monitored to find various abnormal conditions such as blade coating damage, blade bulging, blade cracking, lightning stroke events, blade icing and the like, and the abnormity is early warned.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention.
FIG. 2 is a schematic diagram of a data processing flow according to the present invention.
Fig. 3 is a schematic structural diagram of the noise collecting device of the present invention.
Fig. 4 is a schematic view of the internal structure of fig. 3.
Fig. 5 is a partially enlarged view of the collector.
In fig. 3-5:
1. the collector comprises a collector main body box, 2 sound insulation covers, 3 buffer nets, 4 supporting columns, 5 supporting plates, 6 DIN guide rails, 7 heating sheets, 8 microphone arrays, 9 audio collecting plates, 10 self-resetting lightning protection devices, 11 industrial power supplies, 12 dehumidifying devices and 13 optical fiber switches.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. 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 embodiment provides a blade state monitoring system based on an acoustic algorithm, which comprises a noise acquisition device installed below a fan tower, wherein a fan blade noise signal acquired by the noise acquisition device is transmitted to a data acquisition system through a network for uniform processing, and the acquired data is temporarily stored through a data storage system, as shown in fig. 1-2; the fan noise data temporarily stored in the data storage system are analyzed by the monitoring and early warning system, Mel spectrum features of noise are extracted through the monitoring and early warning system and are compared with standard values in a neural network, accordingly fault reasons of the blades are identified, and finally the analyzed data are displayed through an interactive interface.
The monitoring method comprises the following steps:
(1) the noise signal is collected by the noise collecting equipment, is sent to the data collecting system through network service, carries out primary fusion processing on the collected data, meteorological information and unit information, and then sends the processed data to the data storage system;
(2) the data storage system stores the data at a designated position according to a preset storage rule; when the monitoring and early warning system sends a data calling request, the data of the data storage system can be accessed by a service with permission;
(3) the monitoring and early warning system can read, edit, search and delete data on the data storage system;
(4) after the monitoring and early warning system acquires the collected noise data in real time, the following operations are respectively executed:
preprocessing the data such as noise reduction and beam forming;
carrying out Mel spectrum feature extraction on the noise data;
inputting Mel spectrum characteristic data into early warning algorithm of neural network to judge state of target;
(5) and displaying the analyzed and judged data through an interactive interface.
The noise collection device of the embodiment is shown in fig. 3-5, and comprises a collection module, a network module, a protection module and a power module which are arranged in a collector main body box 1, wherein the collector main body box is installed below a fan tower cylinder through a fixing support, the network module supports communication of optical fibers or network cables, the system can be used for networking in a chain type single network or a ring network, the system can be used for networking in the chain type single network or the ring network, the collector main body box is completely processed by 304 stainless steel, and the fixing support and an acoustic shield 2 are non-standard parts and are installed and adjusted according to the field use environment.
The collector main body box 1 panel top installation microphone array 8 of this embodiment is provided with the sound insulation cover 2 with the height of about 250mm, so as to eliminate the phenomenon on the ground such as: noise interference of a box type transformer and a water chilling unit. The outer side of the microphone array 8 is provided with an annular buffer net 3, the impact of rainwater on the waterproof sound-transmitting membrane is relieved, and the damage of birds or high-altitude falling objects on the sound-transmitting membrane is prevented. The collector body 1 is internally provided with four supporting upright posts 4 for supporting various electronic devices and components required by the collector without forming holes on a panel to increase the risk of water permeation. The top end of the supporting column 4 is provided with a supporting plate 5 for installing a microphone array 8 and an audio collecting plate 9, so that the microphone is as close to the panel as possible, the sound-transmitting membrane is broken to prevent rainwater from flowing to various internal electronic devices, and the noise generated when the dehumidifying device 12 operates can be effectively isolated. The microphone array 8 adopts an annular planar array design, and can meet the directivity requirement of a wave beam. The microphone array 8 is adhered with the heating sheet 7, and the heating sheet starts to heat when the ambient temperature is lower than the set temperature, so that the sound listening hole of the collector panel can be prevented from being covered by ice and snow. The DIN guide rail 6 is arranged on the supporting upright post 4, and various electronic devices in the collector can be quickly installed and disassembled, so that the maintenance is convenient. A self-reset lightning protection device 10 is installed in the collector main body box 1, when lightning surge exceeds a set value, a power supply is automatically cut off, and after lightning stroke, the collector is automatically reset without manual reset. A dehumidifying device 12 is arranged in the collector main body box 1, and when the humidity in the collector reaches or exceeds a set value, the dehumidifying function is automatically started. The acquisition module of this embodiment comprises microphone array 8 and audio acquisition board 9, and the microphone array is not limited to the annular array that this embodiment used, and the processing chip of audio acquisition board 9 is FPGA or STM32 MCU. The network module adopts an industrial optical fiber switch 13; the power module adopts the self-reset lightning protection device 10 and the industrial power supply 11, and the self-reset lightning protection device 10 can automatically cut off the power supply in case of overvoltage and overcurrent and then automatically recover. The industrial power supply 11 has the characteristics of small ripple current and noise, wide environment temperature and input voltage, overcurrent, overtemperature, overvoltage shutoff function and the like. The protection module comprises a heating sheet 7, a dehumidifying device 12 and an electromagnetic shielding cover of the audio acquisition board 9. The heating plate 7 can adopt a plastic heating plate or a ceramic heating plate, the temperature control form adopts a PTC (positive temperature coefficient) self-temperature control heating plate, and the self-temperature control heating plate can be free of a temperature controller. The dehumidifying device 12 can make the humidity inside the collector meet the humidity requirements of the power module and the network module, and the electromagnetic shielding cover can shield the electromagnetic interference of other modules to the collecting module.
The embodiment selects the optimal installation place near the wind power equipment, and generally meets the following conditions: the collector and the wind power equipment are not separated; no serious environmental noise interference exists around; the distance from the power supply facility is short; is convenient for installation and maintenance. Noise collection equipment is installed and is fixed in the assigned position through the support post, and the microphone array faces the blade position, and the microphone array is furnished with sound insulation cover, buffer net and heating plate protection, reduces the microphone array and receives the interference of environmental factor.
When the wind power equipment normally operates, the noise collection equipment can collect sound signals generated when the blades work, and the sound signals are collected through the annular microphone array and transmitted to the system through the optical fibers for processing. The audio collector measures the frequency range as follows: 20-20000Hz, the sampling frequency is set as: 48000 Hz. The system carries out data cleaning, signal processing, characteristic engineering and other work on the transmitted signal data, and realizes prediction and early warning on blade faults through a deep learning method.
The embodiment carries out preventive maintenance to key parts such as blades, reduces the part loss and reduces the downtime caused by the part damage, effectively reduces the whole maintenance cost and improves the actual working life of the wind field with the production efficiency. And monitoring the damage fault of the coating on the outer surface of the blade, and qualitatively evaluating the fault position, the fault type and the fault stage. The blade fault is continuously tracked, and production safety accidents such as blade fracture and collapse caused by blade damage are avoided.
The economic benefit of this embodiment effectively reduces because of the shut down duration that the blade trouble leads to, and after the technique can be promoted and implemented and the optimization of cooperation operation and maintenance business flow, the estimated because of the shut down duration that the blade trouble leads to can reduce 60%, reduces the power generation loss because of shutting down by a wide margin. The maintenance and hoisting times of the blade are effectively reduced, the blade is timely repaired by finding the fault of the blade in the early stage, and the high cost caused by large-scale hoisting construction is avoided. According to research of manufacturing education and technology (CoMET) mechanisms of NREL composite materials, the blade replacement rate of a unit for more than 5 years in the wind power industry is up to 1%, namely the annual average blade replacement number of a 25-unit wind field reaches 0.75, the blade monitoring and early warning technology is expected to be applied to a single wind field, and the blade replacement cost saved in 5 years can reach more than 200 ten thousand yuan on average. Through predictive maintenance of the blades, the pneumatic efficiency of the working of the blades is guaranteed, the long-term power generation yield is improved by up to 5%, the annual energy generation amount is improved by 500 ten thousand degrees by calculating the annual 2000 effective power generation time of a 50MW wind field.
The safety benefit is that the fan blade works at high altitude and is often affected by air media, atmospheric rays, sand and dust, thunder and lightning, rainstorm and ice and snow, the failure rate of the fan blade is about more than one third of that of the whole fan blade, and great potential safety hazards also exist in the process of manual inspection and maintenance, and the wind power blade real-time monitoring system taking artificial intelligence as means can find blade abnormality and make early warning in all weather for 24 hours, so that the safety guarantee for people and machines is greatly improved.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (7)
1. Blade state monitoring system based on acoustic algorithm, its characterized in that: the noise collection device collects fan blade noise signals, transmits the fan blade noise signals to the data collection system through a network for uniform processing, and temporarily stores the collected data through the data storage system; fan noise data temporarily stored in the data storage system are analyzed by a monitoring and early warning system, Mel spectrum features of noise are extracted through the monitoring and early warning system and are compared with standard values in a neural network, accordingly fault reasons of the blades are identified, and finally the analyzed data are displayed through an interactive interface.
2. The acoustic algorithm-based blade condition monitoring system of claim 1, wherein: the noise collection equipment comprises a collection module, a network module, a protection module and a power supply module which are arranged in a collector main body box (1), wherein the collector main body box (1) is arranged below a fan tower cylinder through a fixed support; the acquisition module consists of a microphone array (8) and an audio acquisition board (9), sound signals acquired by the microphone array are processed by the audio acquisition board and then transmitted to the outside by the network module, and the protection module comprises a heating sheet (7) and a dehumidifying device (12) which are arranged in the acquisition device main body box; the power module adopts a combination of a self-reset lightning protection device (10) and an industrial power supply (11), and the industrial power supply (11) supplies power to the network module, the protection module and the acquisition module.
3. An acoustic algorithm based blade condition monitoring system according to claim 2, wherein: the microphone array is arranged on a supporting plate (5) at the top of the collector main body box, an annular buffer net is arranged outside the microphone array, and a sound-proof cover is also arranged outside the microphone array; the audio acquisition board is arranged on the back of the microphone array, and a processing chip of the audio acquisition board adopts FPGA or STM32 MCU; and an electromagnetic shielding cover is arranged on the outer side of the audio acquisition board (9).
4. An acoustic algorithm based blade condition monitoring system according to claim 2, wherein: a support upright post (4) is arranged on the side wall of the collector main body box (1), and a DIN guide rail (6) is arranged on the support upright post (4) and used for installing and fixing the network module, the protection module and the power supply module; the microphone array (8) is bonded with the heating sheet (7); the heating plate (7) is a plastic heating plate or a ceramic heating plate.
5. The acoustic algorithm-based blade condition monitoring system of claim 1, wherein: and the data acquisition system, the data storage system and the monitoring and early warning system are connected and communicated through an industrial Ethernet.
6. The acoustic algorithm-based blade condition monitoring system of claim 1, wherein: the audio collector of the noise collection device measures the frequency range as follows: 20-20000Hz, the sampling frequency is set as: 48000 Hz.
7. A monitoring method of a blade state monitoring system based on an acoustic algorithm is characterized by comprising the following steps:
(1) the noise signal is collected by the noise collecting equipment, is sent to a data collecting system through network service, is subjected to primary fusion processing on collected data, meteorological information and unit information, and then is sent to a data storage system;
(2) the data storage system stores the data at a designated position according to a preset storage rule; when the monitoring and early warning system sends a data calling request, the data of the data storage system can be accessed by a service with permission;
(3) the monitoring and early warning system can read, edit, search and delete data on the data storage system;
(4) after the monitoring and early warning system acquires the collected noise data in real time, the following operations are respectively executed:
preprocessing the data such as noise reduction and beam forming;
carrying out Mel spectrum feature extraction on the noise data;
inputting Mel spectrum characteristic data into early warning algorithm of neural network to judge state of target;
(5) and displaying the analyzed and judged data through an interactive interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111022668.2A CN113623144A (en) | 2021-09-01 | 2021-09-01 | Blade state monitoring system based on acoustic algorithm and monitoring method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111022668.2A CN113623144A (en) | 2021-09-01 | 2021-09-01 | Blade state monitoring system based on acoustic algorithm and monitoring method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113623144A true CN113623144A (en) | 2021-11-09 |
Family
ID=78388758
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111022668.2A Pending CN113623144A (en) | 2021-09-01 | 2021-09-01 | Blade state monitoring system based on acoustic algorithm and monitoring method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113623144A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114183312A (en) * | 2021-12-03 | 2022-03-15 | 中国大唐集团新能源科学技术研究院有限公司 | System and method for monitoring state of blades of wind turbine generator |
| CN114414037A (en) * | 2022-01-18 | 2022-04-29 | 华能湖北新能源有限责任公司 | Health monitoring device and monitoring method for blades of wind generating set |
| CN114818815A (en) * | 2022-05-05 | 2022-07-29 | 西安交通大学 | Method and system for acquiring timed arrival time of blade tip for blade vibration measurement |
| CN114992063A (en) * | 2022-05-06 | 2022-09-02 | 国能信控互联技术有限公司 | Automatic fan blade fault detection method and system |
| CN117031183A (en) * | 2023-10-09 | 2023-11-10 | 北京谛声科技有限责任公司 | Intelligent voiceprint terminal equipment and industrial equipment operation state monitoring method |
| CN117870846A (en) * | 2023-02-22 | 2024-04-12 | 张引 | Correlation type blade arrival detection device and detection method for blade tip timing system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5528224A (en) * | 1994-05-03 | 1996-06-18 | Scientific Technology, Inc. | Optical and acoustic weather identification system |
| CN109763944A (en) * | 2019-01-28 | 2019-05-17 | 中国海洋大学 | A kind of contactless monitoring system of offshore wind turbine blade fault and monitoring method |
| CN210837163U (en) * | 2019-09-25 | 2020-06-23 | 杭州晓龙科技有限公司 | Intelligent array microphone audio device |
| 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 |
| CN112702669A (en) * | 2020-12-21 | 2021-04-23 | 西安讯飞超脑信息科技有限公司 | Sound pickup apparatus, method, apparatus, system, and storage medium |
-
2021
- 2021-09-01 CN CN202111022668.2A patent/CN113623144A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5528224A (en) * | 1994-05-03 | 1996-06-18 | Scientific Technology, Inc. | Optical and acoustic weather identification system |
| CN109763944A (en) * | 2019-01-28 | 2019-05-17 | 中国海洋大学 | A kind of contactless monitoring system of offshore wind turbine blade fault and monitoring method |
| CN210837163U (en) * | 2019-09-25 | 2020-06-23 | 杭州晓龙科技有限公司 | Intelligent array microphone audio device |
| 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 |
| CN112702669A (en) * | 2020-12-21 | 2021-04-23 | 西安讯飞超脑信息科技有限公司 | Sound pickup apparatus, method, apparatus, system, and storage medium |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114183312A (en) * | 2021-12-03 | 2022-03-15 | 中国大唐集团新能源科学技术研究院有限公司 | System and method for monitoring state of blades of wind turbine generator |
| CN114414037A (en) * | 2022-01-18 | 2022-04-29 | 华能湖北新能源有限责任公司 | Health monitoring device and monitoring method for blades of wind generating set |
| CN114818815A (en) * | 2022-05-05 | 2022-07-29 | 西安交通大学 | Method and system for acquiring timed arrival time of blade tip for blade vibration measurement |
| CN114992063A (en) * | 2022-05-06 | 2022-09-02 | 国能信控互联技术有限公司 | Automatic fan blade fault detection method and system |
| CN117870846A (en) * | 2023-02-22 | 2024-04-12 | 张引 | Correlation type blade arrival detection device and detection method for blade tip timing system |
| CN117031183A (en) * | 2023-10-09 | 2023-11-10 | 北京谛声科技有限责任公司 | Intelligent voiceprint terminal equipment and industrial equipment operation state monitoring method |
| CN117031183B (en) * | 2023-10-09 | 2024-01-09 | 北京谛声科技有限责任公司 | Intelligent voiceprint terminal equipment and industrial equipment operation state monitoring method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113623144A (en) | Blade state monitoring system based on acoustic algorithm and monitoring method thereof | |
| Wymore et al. | A survey of health monitoring systems for wind turbines | |
| CN101989767B (en) | Comprehensive measuring and controlling device of high voltage pole tower | |
| CN107781118B (en) | Blade of wind-driven generator health status monitoring system based on multi-sensor information | |
| EP3757386B1 (en) | Wind turbine blade monitoring systems | |
| US20110192212A1 (en) | System and method of counting and analyzing animal impacts on a wind turbine blade | |
| CN112324629A (en) | Wind power blade early damage monitoring system and method based on vibration and sound | |
| CN104215640A (en) | Wind-generator blade defect damage inspection method and inspection system based on unmanned helicopter | |
| KR102347238B1 (en) | Operation and management system of photovoltaic power plant and method thereof | |
| CN106706241B (en) | Active self-checking device and method for damage of wind turbine blade | |
| US20190032641A1 (en) | Method for monitoring a wind turbine | |
| KR102084783B1 (en) | System for managing the operation of Photovoltaic Power Generation based on machine learning | |
| CN204719531U (en) | A kind of failure monitoring early warning system of Wind turbines equipment | |
| US20220074896A1 (en) | Apparatus and Method of Detecting Anomalies in an Acoustic Signal | |
| CN114669569A (en) | Big data-based automatic cleaning system for photovoltaic module | |
| Papasalouros et al. | Acoustic Emission Monitoring of Composite Blade of NM48/750 NEG-MICON Wind Turbine. | |
| CN202748054U (en) | Power line ice coating on-line monitoring system | |
| CN112324628A (en) | Wind turbine generator system hanger rail formula cabin system of patrolling and examining | |
| CN117375226A (en) | Power grid operation monitoring device | |
| CN112583115A (en) | System for collecting lightning parameters of wind power plant cluster | |
| CN215492058U (en) | Fan blade noise collector | |
| JP2016217252A (en) | Wind generator system and flying bird prediction device | |
| CN115560733A (en) | Wetland ecological safety detection and early warning integrated equipment and control method thereof | |
| CN220036839U (en) | Acoustic acquisition device for nondestructive health monitoring of wind turbine blade | |
| CN112435445A (en) | Debris flow monitoring and alarming device based on infrasonic waves |
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 |