CN112729783A - Fan blade fault diagnosis method, device, equipment and computer storage medium - Google Patents
Fan blade fault diagnosis method, device, equipment and computer storage medium Download PDFInfo
- Publication number
- CN112729783A CN112729783A CN202011398195.1A CN202011398195A CN112729783A CN 112729783 A CN112729783 A CN 112729783A CN 202011398195 A CN202011398195 A CN 202011398195A CN 112729783 A CN112729783 A CN 112729783A
- Authority
- CN
- China
- Prior art keywords
- state information
- blade
- fault diagnosis
- sample
- blade 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012549 training Methods 0.000 claims abstract description 48
- 238000013528 artificial neural network Methods 0.000 claims abstract description 15
- 230000001133 acceleration Effects 0.000 claims description 29
- 238000000354 decomposition reaction Methods 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 19
- 238000001914 filtration Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 239000013307 optical fiber Substances 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000002405 diagnostic procedure Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 17
- 238000004891 communication Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 239000000835 fiber Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
Abstract
The application provides a fan blade fault diagnosis method, device and equipment and a computer storage medium. The fan blade fault diagnosis method comprises the following steps: acquiring blade state information of a fan blade; inputting the blade state information into a fault diagnosis model and outputting a fault diagnosis result; the fault diagnosis model is obtained by performing model training on a preset neural network structure by using a training sample set, wherein each training sample in the training sample set comprises sample leaf state information and a label of the sample leaf state information. According to the embodiment of the application, the fault diagnosis of the fan blade can be more accurately carried out.
Description
Technical Field
The application belongs to the technical field of fan blade fault diagnosis, and particularly relates to a fan blade fault diagnosis method and device, electronic equipment and a computer storage medium.
Background
The installed capacity of wind power generation equipment in China is increased year by year, and the working environment of the fan blade is also severe, so that the fan blade is easy to fail. The current fault diagnosis scheme comprises an off-line mode and an on-line mode, wherein the off-line mode comprises a manual visual diagnosis mode, a mode of collecting blade pictures to diagnose blade cracks and a mode of collecting and diagnosing faults by adopting a sound pressure sensor. The online mode is to use an online monitor to diagnose faults.
Because the off-line mode can not carry out real-time monitoring for fault diagnosis, and the on-line mode can only carry out monitoring in a control room for fault diagnosis, the two modes can not carry out fault diagnosis on the fan blade accurately.
Therefore, how to more accurately perform the fault diagnosis of the fan blade is a technical problem that needs to be solved urgently by the technical personnel in the field.
Disclosure of Invention
The embodiment of the application provides a fan blade fault diagnosis method and device, electronic equipment and a computer storage medium, and fan blade fault diagnosis can be performed more accurately.
In a first aspect, an embodiment of the present application provides a method for diagnosing a fan blade fault, including:
acquiring blade state information of a fan blade;
inputting the blade state information into a fault diagnosis model and outputting a fault diagnosis result; the fault diagnosis model is obtained by performing model training on a preset neural network structure by using a training sample set, wherein each training sample in the training sample set comprises sample leaf state information and a label of the sample leaf state information.
Optionally, obtaining blade state information of the fan blade includes:
receiving blade state information sent by a data acquisition device; wherein, the data acquisition device acquires the blade state information through the sensor.
Optionally, the receiving of the blade state information sent by the data acquisition device includes:
receiving the blade state information sent by the data acquisition device through the data processing device; the data processing device performs at least one of filtering, feature extraction and frequency band decomposition on the blade state information.
Optionally, the industrial personal computer sends blade state information to the server through WIFI or optical fibers.
Optionally, the sensor includes at least one of an acoustic emission sensor and an acceleration sensor.
Optionally, before inputting the blade state information into the fault diagnosis model and outputting the fault diagnosis result, the method includes:
acquiring initial blade state information of samples of at least two fan blades at different moments;
sequentially filtering, feature extraction and frequency band decomposition are carried out on the initial blade state information of the sample by using an industrial personal computer, and energy ratio in each frequency band is calculated; the energy ratio comprises an acoustic emission energy ratio and an acceleration energy ratio;
combining the acoustic emission energy ratio and the acceleration energy ratio to obtain a two-dimensional signal or a three-dimensional signal;
determining the two-dimensional signal or the three-dimensional signal as sample blade state information;
and performing model training on the neural network structure by using the sample blade state information and the label of the sample blade state information to obtain a fault diagnosis model.
Optionally, the industrial personal computer is used to perform frequency band decomposition on the initial blade state information of the sample, and calculate the energy ratio in each frequency band, including:
carrying out frequency band decomposition on the initial blade state information of the sample by adopting a wavelet packet algorithm, and calculating a wavelet packet coefficient in each frequency band;
and determining the wavelet packet coefficient as an energy ratio.
In a second aspect, an embodiment of the present application provides a fan blade fault diagnosis device, including:
the first acquisition module is used for acquiring blade state information of the fan blade;
the output module is used for inputting the blade state information into the fault diagnosis model and outputting a fault diagnosis result; the fault diagnosis model is obtained by performing model training on a preset neural network structure by using a training sample set, wherein each training sample in the training sample set comprises sample leaf state information and a label of the sample leaf state information.
Optionally, the first obtaining module includes:
the receiving unit is used for receiving the blade state information sent by the data acquisition device; wherein, the data acquisition device acquires the blade state information through the sensor.
Optionally, the receiving unit includes:
the receiving subunit is used for receiving the blade state information sent by the data acquisition device through the data processing device; the data processing device performs at least one of filtering, feature extraction and frequency band decomposition on the blade state information.
Optionally, the industrial personal computer sends blade state information to the server through WIFI or optical fibers.
Optionally, the sensor includes at least one of an acoustic emission sensor and an acceleration sensor.
Optionally, the apparatus comprises:
the second acquisition module is used for acquiring initial blade state information of samples of at least two fan blades at different moments;
the preprocessing module is used for sequentially carrying out filtering, feature extraction and frequency band decomposition on the initial blade state information of the sample by using an industrial personal computer and calculating the energy ratio in each frequency band; the energy ratio comprises an acoustic emission energy ratio and an acceleration energy ratio;
the combination module is used for combining the acoustic emission energy ratio and the acceleration energy ratio to obtain a two-dimensional signal or a three-dimensional signal;
the determining module is used for determining the two-dimensional signal or the three-dimensional signal as the sample blade state information;
and the model training module is used for performing model training on the neural network structure by using the sample blade state information and the label of the sample blade state information to obtain a fault diagnosis model.
Optionally, the preprocessing module includes:
the frequency band decomposition unit is used for carrying out frequency band decomposition on the initial blade state information of the sample by adopting a wavelet packet algorithm and calculating a wavelet packet coefficient in each frequency band;
and the determining unit is used for determining the wavelet packet coefficient as the energy ratio.
In a third aspect, an embodiment of the present application provides an electronic device, where the electronic device includes: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements a method of fan blade fault diagnosis as shown in the first aspect.
In a fourth aspect, the present application provides a computer storage medium, on which computer program instructions are stored, and when executed by a processor, the method for diagnosing a fan blade fault according to the first aspect is implemented.
The fan blade fault diagnosis method and device, the electronic equipment and the computer storage medium can be used for more accurately diagnosing the fan blade fault. According to the fan blade fault diagnosis method, after blade state information of a fan blade is obtained, the blade state information is input into a fault diagnosis model, and a fault diagnosis result is output. The fault diagnosis model is obtained by performing model training on a preset neural network structure by using a training sample set, and each training sample in the training sample set comprises sample blade state information and a label of the sample blade state information, so that the fault diagnosis model can be used for more accurately diagnosing the fault of the fan blade compared with the prior art.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic structural diagram of a wind turbine blade fault diagnosis system provided by one embodiment of the present application;
FIG. 2 is a schematic structural diagram of a wind turbine blade fault diagnostic system provided by another embodiment of the present application;
FIG. 3 is a schematic flow chart diagram of a method for diagnosing a failure of a wind turbine blade according to an embodiment of the present application;
FIG. 4 is a schematic diagram of acceleration signals at a measurement point provided by one embodiment of the present application;
FIG. 5 is a schematic diagram of a wavelet packet decomposition level according to an embodiment of the present application;
FIG. 6 is a schematic diagram illustrating an energy ratio of each frequency band at a survey point according to an embodiment of the present disclosure;
FIG. 7 is a schematic structural diagram of a wind turbine blade fault diagnosis device provided by an embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Features and exemplary embodiments of various aspects of the present application will be described in detail below, and in order to make objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are intended to be illustrative only and are not intended to be limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by illustrating examples thereof.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
In order to solve the prior art problems, embodiments of the present application provide a method, an apparatus, a device, and a computer storage medium for diagnosing a fan blade fault. Before introducing the method for diagnosing the fault of the fan blade, the system for diagnosing the fault of the fan blade provided by the present application is introduced, as shown in fig. 1, and the system for diagnosing the fault of the fan blade includes: data induction system, data acquisition device, data processing device, communication device and server. The data sensing device can comprise various sensors, specifically, an acoustic emission sensor and an acceleration sensor; the data acquisition device may comprise a data acquisition card; the data processing device may comprise an industrial personal computer; the communication device may include WIFI and fiber optics; the server may be embodied as a central server.
In one embodiment, the wind turbine blade fault diagnosis system is shown in fig. 2, the sensor 1 and the sensor 2 in fig. 2 are an acoustic emission sensor and an acceleration sensor, respectively, hub WIFI means that WIFI is arranged at a hub of a wind turbine, and a tower footing optical fiber means that an optical fiber is arranged at a tower footing of the wind turbine.
Illustratively, the measuring points are arranged at the blade length 1/3 from the root on the blade, and 1 acoustic emission sensor and 1 acceleration sensor are respectively arranged at the measuring points as the sources of the blade state monitoring data. And arranging an industrial personal computer at the hub of the fan blade to acquire data and preprocess the data of the sensor. WIFI is arranged at the bottom of the fan hub and the fan tower, data processed by the industrial personal computer are transmitted to the bottom of the tower, optical fibers are arranged at the tower base of the fan, collected data are uploaded to the server through the optical fibers, the server is responsible for displaying the data, meanwhile, fan faults are judged based on a machine learning algorithm, and blade state information is sent to relevant workers through the cloud end to be overhauled in time.
The fan blade fault diagnosis system has been described above, and a fan blade fault diagnosis method will be described below, based on which fan blade fault diagnosis can be performed.
Fig. 3 is a schematic flow chart of a fan blade fault diagnosis method according to an embodiment of the present application, and as shown in fig. 3, the fan blade fault diagnosis method includes:
s301, obtaining blade state information of the fan blade.
In one embodiment, obtaining blade status information for a wind turbine blade comprises:
receiving blade state information sent by a data acquisition device; wherein, the data acquisition device acquires the blade state information through the sensor. Optionally, the data acquisition device may be a data acquisition card.
In one embodiment, the receiving of the blade state information sent by the data acquisition device comprises:
receiving the blade state information sent by the data acquisition device through the data processing device; the data processing device performs at least one of filtering, feature extraction and frequency band decomposition on the blade state information. Optionally, the data processing device may be an industrial personal computer.
In one embodiment, the industrial personal computer sends blade status information to the server through WIFI or optical fibers.
In one embodiment, the sensor includes at least one of an acoustic emission sensor, an acceleration sensor.
S302, inputting the blade state information into a fault diagnosis model and outputting a fault diagnosis result; the fault diagnosis model is obtained by performing model training on a preset neural network structure by using a training sample set, wherein each training sample in the training sample set comprises sample leaf state information and a label of the sample leaf state information.
In one embodiment, before inputting the blade state information into the fault diagnosis model and outputting the fault diagnosis result, the method comprises the following steps:
acquiring initial blade state information of samples of at least two fan blades at different moments;
sequentially filtering, feature extraction and frequency band decomposition are carried out on the initial blade state information of the sample by using an industrial personal computer, and energy ratio in each frequency band is calculated; the energy ratio comprises an acoustic emission energy ratio and an acceleration energy ratio;
combining the acoustic emission energy ratio and the acceleration energy ratio to obtain a two-dimensional signal or a three-dimensional signal;
determining the two-dimensional signal or the three-dimensional signal as sample blade state information;
and performing model training on the neural network structure by using the sample blade state information and the label of the sample blade state information to obtain a fault diagnosis model.
In one embodiment, the method for decomposing the frequency bands of the initial blade state information of the sample by using the industrial personal computer and calculating the energy ratio in each frequency band comprises the following steps:
carrying out frequency band decomposition on the initial blade state information of the sample by adopting a wavelet packet algorithm, and calculating a wavelet packet coefficient in each frequency band;
and determining the wavelet packet coefficient as an energy ratio.
For example, according to the working condition analysis of the fan, the noise borne by the fan blade is generally low-frequency noise, and the signal generated by the fan blade fault is generally a high-frequency signal, so that the collected fan blade data is firstly filtered, and the low-frequency component of the signal is filtered. Classifying the fault information and extracting features, according to the analysis embodiment, adopting a wavelet packet algorithm to carry out different frequency band decomposition on acoustic emission and acceleration data collected by the fan, and calculating wavelet packet coefficients in different frequency band ranges to serve as energy ratios in all frequency bands. The rotating speed of the fan is low relative to the sampling frequency, and a plurality of groups of fan blades at different moments are continuously collected for analysis. And (3) aiming at each blade, carrying out the processing on the data acquired at each moment, namely filtering and extracting the energy ratio in each frequency band. In order to fuse information among blades, acoustic emission energy ratios and acceleration energy ratios of three blades at different moments are combined to form a two-dimensional signal. And training the collected fault data to obtain a fault diagnosis model.
According to the fan blade fault diagnosis method, after blade state information of a fan blade is obtained, the blade state information is input into a fault diagnosis model, and a fault diagnosis result is output. The fault diagnosis model is obtained by performing model training on a preset neural network structure by using a training sample set, and each training sample in the training sample set comprises sample blade state information and a label of the sample blade state information, so that the fault diagnosis model can be used for more accurately diagnosing the fault of the fan blade compared with the prior art.
The method for diagnosing the fault of the fan blade is described in an embodiment.
And 1 acoustic emission sensor and 1 acceleration sensor are arranged on each blade of the fan, and the distances between the acoustic emission sensors and the acceleration sensors are 15m and 10m from the root of each blade. The specific mounting distance may be defined in terms of blade length.
When data acquisition is carried out, because signals generated by crack faults of the fan blades are generally high-frequency signals, the sampling frequency is set to be 10000 Hz.
Considering that the sampling frequency is too large and the internal memory of the industrial personal computer is used, the acquisition time is about 14s, and the data acquired in one acquisition time is taken as a group. And 5 groups of data are collected by combining the rotating speed of the fan, wherein one group of data is shown in figure 4.
And marking signals collected by the sensors as s (N), wherein N is 0,1, … N-1, and N is the nth group of data.
And filtering the signals lower than 100Hz by adopting a Butterworth filter for each group of data through the industrial personal computer to obtain filtered signals.
And carrying out wavelet packet decomposition on each group of signals, wherein the decomposition level is 3. The wavelet packet decomposition series are shown in fig. 5, and the Initial Signal (Initial Signal) is decomposed by 3 stages (corresponding to Layer1, Layer2 and Layer3 in fig. 5, respectively) to determine 8 frequency bands (corresponding to SSS, dSS, SdS, ddS, SSd, dSd, Sdd and ddd in fig. 5, respectively).
Calculating the square sum of the wavelet packet coefficients of each level, calculating the energy ratio of each level, and respectively obtaining the energy ratio of the acceleration signal and the energy ratio of the acoustic emission signal as
Wherein ac represents an acceleration signal, acou represents an acoustic emission signal, i represents ith group data, j represents a blade number, and energy occupation ratios of frequency bands at a measuring point can be seen in fig. 6.
In the process of constructing the input signal, the energy ratios of 5 groups of data are combined in sequence to obtain a two-dimensional array SiginputArray dimension 30X 8.
In the process of training data, Sig is trainedinputThe combination is performed so that the input signal becomes three-dimensional with dimensions 3X9X 9. The sample data is acquired for many times to obtain a sample database, and the sample data is mainly divided into two types, namely fault and no fault. And (4) carrying out model training on the event 18 by using the sample database, determining model parameters, and further obtaining a trained fault diagnosis model.
And preprocessing the newly acquired data and inputting the preprocessed data into the trained fault diagnosis model to obtain a fault diagnosis result.
The present embodiment enables the fault signal to be monitored to the greatest possible extent by arranging the sensor at the fan blade 1/3; by adopting the mode of acoustic emission and acceleration sensors, the failure of the fan blade can be effectively detected when the crack of the fan blade is generated and expanded in the early stage; when fault data are analyzed, characteristic differences between fan blades are fused, so that the model can more accurately identify blade cracks; the energy occupation ratio of each frequency band of the signal is obtained based on wavelet packet decomposition, the separability characteristic is achieved, and meanwhile, the model has strong expansibility by combining with a deep learning algorithm.
Fig. 7 is a schematic structural diagram of a fan blade fault diagnosis device according to an embodiment of the present application, and as shown in fig. 7, the fan blade fault diagnosis device includes:
a first obtaining module 701, configured to obtain blade state information of a fan blade;
an output module 702, configured to input the blade state information into a fault diagnosis model, and output a fault diagnosis result; the fault diagnosis model is obtained by performing model training on a preset neural network structure by using a training sample set, wherein each training sample in the training sample set comprises sample leaf state information and a label of the sample leaf state information.
In one embodiment, the first obtaining module 701 includes:
the receiving unit is used for receiving the blade state information sent by the data acquisition device; wherein, the data acquisition device acquires the blade state information through the sensor.
In one embodiment, a receiving unit includes:
the receiving subunit is used for receiving the blade state information sent by the data acquisition device through the data processing device; the data processing device performs at least one of filtering, feature extraction and frequency band decomposition on the blade state information.
In one embodiment, the industrial personal computer sends blade status information to the server through WIFI or optical fibers.
In one embodiment, the sensor includes at least one of an acoustic emission sensor, an acceleration sensor.
In one embodiment, an apparatus comprises: the second acquisition module is used for acquiring initial blade state information of samples of at least two fan blades at different moments;
the preprocessing module is used for sequentially carrying out filtering, feature extraction and frequency band decomposition on the initial blade state information of the sample by using an industrial personal computer and calculating the energy ratio in each frequency band; the energy ratio comprises an acoustic emission energy ratio and an acceleration energy ratio;
the combination module is used for combining the acoustic emission energy ratio and the acceleration energy ratio to obtain a two-dimensional signal or a three-dimensional signal;
the determining module is used for determining the two-dimensional signal or the three-dimensional signal as the sample blade state information;
and the model training module is used for performing model training on the neural network structure by using the sample blade state information and the label of the sample blade state information to obtain a fault diagnosis model.
In one embodiment, a pre-processing module comprises:
the frequency band decomposition unit is used for carrying out frequency band decomposition on the initial blade state information of the sample by adopting a wavelet packet algorithm and calculating a wavelet packet coefficient in each frequency band;
and the determining unit is used for determining the wavelet packet coefficient as the energy ratio.
Each module/unit in the apparatus shown in fig. 7 has a function of implementing each step in fig. 3, and can achieve the corresponding technical effect, and for brevity, no further description is provided herein.
Fig. 8 shows a schematic structural diagram of an electronic device provided in an embodiment of the present application.
The electronic device may include a processor 801 and a memory 802 that stores computer program instructions.
Specifically, the processor 801 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.
In one example, the Memory 802 may be a Read Only Memory (ROM). In one example, the ROM may be mask programmed ROM, programmable ROM (prom), erasable prom (eprom), electrically erasable prom (eeprom), electrically rewritable ROM (earom), or flash memory, or a combination of two or more of these.
The processor 801 reads and executes computer program instructions stored in the memory 802 to implement any of the fan blade fault diagnosis methods in the above embodiments.
In one example, the electronic device can also include a communication interface 803 and a bus 810. As shown in fig. 8, the processor 801, the memory 802, and the communication interface 803 are connected via a bus 810 to complete communication therebetween.
The communication interface 803 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiments of the present application.
In addition, the embodiment of the application can be realized by providing a computer storage medium. The computer storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement any of the fan blade fault diagnosis methods of the above embodiments.
It is to be understood that the present application is not limited to the particular arrangements and instrumentality described above and shown in the attached drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions or change the order between the steps after comprehending the spirit of the present application.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
Aspects of the present application are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As described above, only the specific embodiments of the present application are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application.
Claims (16)
1. A fan blade fault diagnosis method is characterized by comprising the following steps:
acquiring blade state information of a fan blade;
inputting the blade state information into a fault diagnosis model and outputting a fault diagnosis result; the fault diagnosis model is obtained by performing model training on a preset neural network structure by using a training sample set, wherein each training sample in the training sample set comprises sample leaf state information and a label of the sample leaf state information.
2. The method of claim 1, wherein the obtaining blade status information of the wind turbine blade comprises:
receiving the blade state information sent by a data acquisition device; the data acquisition device acquires the blade state information through a sensor.
3. The wind turbine blade fault diagnosis method according to claim 2, wherein the receiving the blade state information sent by the data acquisition device includes:
receiving the blade state information sent by the data acquisition device through a data processing device; wherein the data processing device performs at least one of filtering, feature extraction and frequency band decomposition on the blade state information.
4. The fan blade fault diagnosis method according to claim 3, wherein the industrial personal computer sends the blade state information to a server through WIFI or optical fibers.
5. The wind turbine blade fault diagnosis method of claim 2, wherein the sensor comprises at least one of an acoustic emission sensor, an acceleration sensor.
6. The fan blade fault diagnosis method according to claim 1, wherein before inputting the blade state information into a fault diagnosis model and outputting a fault diagnosis result, the method comprises:
acquiring initial blade state information of samples of at least two fan blades at different moments;
sequentially carrying out filtering, feature extraction and frequency band decomposition on the initial blade state information of the sample by using an industrial personal computer, and calculating energy ratio in each frequency band; wherein the energy fraction comprises an acoustic emission energy fraction and an acceleration energy fraction;
combining the acoustic emission energy ratio and the acceleration energy ratio to obtain a two-dimensional signal or a three-dimensional signal;
determining the two-dimensional signal or the three-dimensional signal as the sample blade status information;
and performing model training on the neural network structure by using the sample blade state information and the label of the sample blade state information to obtain the fault diagnosis model.
7. The fan blade fault diagnosis method according to claim 6, wherein the performing of frequency band decomposition on the initial blade state information of the sample by using an industrial personal computer and calculating energy ratios in each frequency band comprises:
carrying out frequency band decomposition on the initial blade state information of the sample by adopting a wavelet packet algorithm, and calculating a wavelet packet coefficient in each frequency band;
determining the wavelet packet coefficients as the energy fraction.
8. A fan blade fault diagnostic device, comprising:
the first acquisition module is used for acquiring blade state information of the fan blade;
the output module is used for inputting the blade state information into a fault diagnosis model and outputting a fault diagnosis result; the fault diagnosis model is obtained by performing model training on a preset neural network structure by using a training sample set, wherein each training sample in the training sample set comprises sample leaf state information and a label of the sample leaf state information.
9. The wind turbine blade fault diagnostic device of claim 8, wherein the first obtaining module comprises:
the receiving unit is used for receiving the blade state information sent by the data acquisition device; the data acquisition device acquires the blade state information through a sensor.
10. The fan blade fault diagnostic device of claim 9, wherein the receiving unit comprises:
the receiving subunit is used for receiving the blade state information sent by the data acquisition device through the data processing device; wherein the data processing device performs at least one of filtering, feature extraction and frequency band decomposition on the blade state information.
11. The fan blade fault diagnosis device of claim 10, wherein the industrial personal computer sends the blade state information to a server through WIFI or optical fiber.
12. The wind turbine blade fault diagnostic device of claim 9, wherein the sensor comprises at least one of an acoustic emission sensor, an acceleration sensor.
13. The wind turbine blade fault diagnostic device of claim 8, wherein the device comprises:
the second acquisition module is used for acquiring initial blade state information of samples of at least two fan blades at different moments;
the preprocessing module is used for sequentially carrying out filtering, feature extraction and frequency band decomposition on the initial blade state information of the sample by using an industrial personal computer, and calculating the energy ratio in each frequency band; wherein the energy fraction comprises an acoustic emission energy fraction and an acceleration energy fraction;
the combination module is used for combining the acoustic emission energy ratio and the acceleration energy ratio to obtain a two-dimensional signal or a three-dimensional signal;
a determining module for determining the two-dimensional signal or the three-dimensional signal as the sample blade state information;
and the model training module is used for performing model training on the neural network structure by using the sample blade state information and the label of the sample blade state information to obtain the fault diagnosis model.
14. The wind turbine blade fault diagnostic device of claim 13, wherein the preprocessing module comprises:
the frequency band decomposition unit is used for carrying out frequency band decomposition on the initial blade state information of the sample by adopting a wavelet packet algorithm and calculating a wavelet packet coefficient in each frequency band;
a determining unit, configured to determine the wavelet packet coefficient as the energy fraction.
15. An electronic device, characterized in that the electronic device comprises: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements a wind turbine blade fault diagnosis method as defined in any of claims 1-7.
16. A computer storage medium having computer program instructions stored thereon that, when executed by a processor, implement a fan blade fault diagnostic method as recited in any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011398195.1A CN112729783A (en) | 2020-12-04 | 2020-12-04 | Fan blade fault diagnosis method, device, equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011398195.1A CN112729783A (en) | 2020-12-04 | 2020-12-04 | Fan blade fault diagnosis method, device, equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112729783A true CN112729783A (en) | 2021-04-30 |
Family
ID=75598472
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011398195.1A Pending CN112729783A (en) | 2020-12-04 | 2020-12-04 | Fan blade fault diagnosis method, device, equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112729783A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102706885A (en) * | 2012-05-15 | 2012-10-03 | 广东电网公司电力科学研究院 | On-line damage detecting system of blade of wind generating set |
| CN106124982A (en) * | 2016-06-14 | 2016-11-16 | 都城绿色能源有限公司 | Automatic expert's resultant fault diagnostic system of a kind of Wind turbines and diagnostic method |
| CN109376801A (en) * | 2018-12-04 | 2019-02-22 | 西安电子科技大学 | Blade of wind-driven generator icing diagnostic method based on integrated deep neural network |
| US20200209109A1 (en) * | 2018-12-28 | 2020-07-02 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for fault diagnosis |
| CN111855816A (en) * | 2020-06-15 | 2020-10-30 | 内蒙古工业大学 | Fan blade fault identification method integrating probability model and cnn network |
-
2020
- 2020-12-04 CN CN202011398195.1A patent/CN112729783A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102706885A (en) * | 2012-05-15 | 2012-10-03 | 广东电网公司电力科学研究院 | On-line damage detecting system of blade of wind generating set |
| CN106124982A (en) * | 2016-06-14 | 2016-11-16 | 都城绿色能源有限公司 | Automatic expert's resultant fault diagnostic system of a kind of Wind turbines and diagnostic method |
| CN109376801A (en) * | 2018-12-04 | 2019-02-22 | 西安电子科技大学 | Blade of wind-driven generator icing diagnostic method based on integrated deep neural network |
| US20200209109A1 (en) * | 2018-12-28 | 2020-07-02 | Shanghai United Imaging Intelligence Co., Ltd. | Systems and methods for fault diagnosis |
| CN111855816A (en) * | 2020-06-15 | 2020-10-30 | 内蒙古工业大学 | Fan blade fault identification method integrating probability model and cnn network |
Non-Patent Citations (2)
| Title |
|---|
| 曲弋等: "基于声发射和神经网络的风机叶片裂纹识别研究", 《机械设计与制造》 * |
| 袁洪芳等: "基于声发射信号的风机叶片裂纹定位分析", 《计算机工程与设计》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113469060A (en) | Multi-sensor fusion convolution neural network aeroengine bearing fault diagnosis method | |
| CN110688617B (en) | Fan vibration abnormity detection method and device | |
| CA2874991A1 (en) | Methods and apparatuses for defect diagnosis in a mechanical system | |
| CN110398384A (en) | The machine health monitoring of rotating machinery | |
| JP2002090267A (en) | Failure diagnosis method | |
| CN114112398A (en) | Fault diagnosis method for rolling bearing under variable speed working condition | |
| CN109238727A (en) | A kind of engine failure monitoring and warning system | |
| CN114993640A (en) | Equipment state monitoring method, device, equipment and computer storage medium | |
| CN104568132B (en) | Reference signal constraint-based mechanical characteristic acoustic signal frequency-domain semi-blind extraction method | |
| CN113776794A (en) | Fault diagnosis method, device and system for embedded edge computing | |
| CN115640503A (en) | Wind turbine generator blade abnormity detection method and device | |
| CN114061743A (en) | Vibration monitoring method, device, equipment and medium for wind generating set | |
| CN111173687B (en) | On-line monitoring device and method for crack damage of wind power fan blade | |
| CN115905341A (en) | Data quality abnormity detection method and device, electronic equipment and storage medium | |
| CN112729783A (en) | Fan blade fault diagnosis method, device, equipment and computer storage medium | |
| CN116861369A (en) | Air compressor health assessment method and system for industrial internet heterogeneous data fusion | |
| CN113958463A (en) | Online monitoring method, system and device for fan blade | |
| CN114689298A (en) | Fault detection method and device for walking part of coal mining machine | |
| CN114689321A (en) | Bearing fault diagnosis method and device for wind generating set and electronic equipment | |
| CN110307899A (en) | Sound anomaly detection system based on deep learning | |
| CN113139430A (en) | Acoustic signal analysis method for fault detection, and method and device for fault detection | |
| CN114687955A (en) | Blade fault diagnosis method and device for wind generating set and electronic equipment | |
| CN109357830A (en) | Highway transportation test measurement equipment | |
| CN111980900B (en) | Water pump fault diagnosis method based on multi-source data fusion analysis | |
| CN113049250B (en) | Motor fault diagnosis method and system based on MPU6050 and decision tree |
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 | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20231117 |
|
| AD01 | Patent right deemed abandoned |