CN116625683A - Wind turbine generator system bearing fault identification method, system and device and electronic equipment - Google Patents
Wind turbine generator system bearing fault identification method, system and device and electronic equipment Download PDFInfo
- Publication number
- CN116625683A CN116625683A CN202310406239.8A CN202310406239A CN116625683A CN 116625683 A CN116625683 A CN 116625683A CN 202310406239 A CN202310406239 A CN 202310406239A CN 116625683 A CN116625683 A CN 116625683A
- Authority
- CN
- China
- Prior art keywords
- data set
- fault
- bearing
- fusion
- wind turbine
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 230000004927 fusion Effects 0.000 claims description 102
- 230000007547 defect Effects 0.000 claims description 32
- 238000012549 training Methods 0.000 claims description 29
- 230000015654 memory Effects 0.000 claims description 26
- 238000007499 fusion processing Methods 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000008859 change Effects 0.000 claims description 10
- 238000012423 maintenance Methods 0.000 abstract description 7
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 238000010248 power generation Methods 0.000 abstract description 5
- 238000003745 diagnosis Methods 0.000 description 14
- 238000000605 extraction Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000003062 neural network model Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000013139 quantization Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 238000005299 abrasion Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007373 indentation Methods 0.000 description 2
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
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
- G01M13/04—Bearings
- G01M13/045—Acoustic or vibration analysis
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
- G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- 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)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Sustainable Energy (AREA)
- Sustainable Development (AREA)
- Acoustics & Sound (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a wind turbine generator bearing fault identification method, a system, a device and electronic equipment. Therefore, by implementing the method and the device, early fault early warning and intelligent monitoring can be carried out on the bearing of the wind turbine generator, the internal fault characteristics of the bearing can be completely mastered, and the method and the device have very important significance for improving the power generation efficiency, reducing significant economic loss and saving operation and maintenance cost of the offshore wind turbine generator.
Description
Technical Field
The invention relates to the technical field of offshore wind power detection, in particular to a wind turbine generator bearing fault identification method, a system and a device and electronic equipment.
Background
The construction of the offshore wind farm is in a high-speed development construction stage, and challenges are brought to the inspection and maintenance of the offshore wind farm fans. The wind turbine generator consists of a large number of large components which are closely connected with each other, and converts wind energy into electric energy under the coordination of a control system.
At present, the offshore wind turbine is influenced by factors such as environment, the operation working condition is complex, various faults are more easily caused, the coupling between different components is tighter, and the continuous existence of a tiny fault can finally cause catastrophic fault occurrence, so that the wind turbine is stopped and even damaged. The bearing is one of the equipment with the highest mechanical failure rate in the wind power generation system, and the failure has the largest influence and the longest maintenance time.
At present, in the actual fault signal acquisition process of the bearing, one such situation may be encountered: the damage at the bearing failure is undergoing an increasing change while the acquisition instrument receives vibration information from the acceleration sensor, in which case the acquired signal is referred to as a dynamic failure signal. This causes the acquired bearing vibration signal to contain vibration information of the same type of fault but with different degrees of damage. The characteristic of the signal can cause the amplitude fluctuation of the vibration signal to change in a trend, so that the diagnosis result is wrong when the bearing fault diagnosis is carried out.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a method, a system, a device and electronic equipment for identifying bearing faults of a wind turbine generator, which are used for solving the technical problem of low accuracy of bearing fault diagnosis in the prior art.
The technical scheme provided by the invention is as follows:
in a first aspect, an embodiment of the present invention provides a method for identifying a bearing failure of a wind turbine, where the method for identifying a bearing failure of a wind turbine includes: acquiring a vibration data set and a voiceprint data set of a bearing of a wind turbine to be diagnosed; performing fusion processing on the vibration data set and the voiceprint data set to obtain a first fusion data set; based on the first fusion data set, obtaining at least one fault defect grade relation through a preset bearing fault identification model, wherein the fault defect grade relation is used for reflecting the corresponding relation between the fusion data in the first fusion data set and the fault defect grade; and determining the fault type of the wind turbine generator bearing to be diagnosed based on each fault defect grade relation.
With reference to the first aspect, in a possible implementation manner of the first aspect, before the obtaining at least one fault defect level relation through a preset bearing fault identification model based on the first fused data set, the method further includes: acquiring a historical vibration data set and a historical voiceprint data set of a preset fault database and a wind turbine generator bearing; performing fusion processing on the historical vibration data set and the historical voiceprint data set to obtain a second fusion data set; and preprocessing the second fusion data set and the preset fault database, and inputting the preprocessed second fusion data set and the preset fault database into a hidden Markov neural network for training until the preset bearing fault recognition model is obtained.
With reference to the first aspect, in another possible implementation manner of the first aspect, the preprocessing the second fused data set and the preset fault database, and then inputting the preprocessed second fused data set and the preprocessed preset fault database into a hidden markov neural network for training until the preset bearing fault recognition model is obtained, includes: based on the second fusion data set, obtaining a fusion average data set through an average value calculation method; performing feature matching on the fusion average value data set and the preset fault database to obtain a feature fault parameter set; and training through a hidden Markov neural network based on the second fusion data set and the characteristic fault parameter set to obtain the preset bearing fault recognition model.
With reference to the first aspect, in a further possible implementation manner of the first aspect, after performing a fusion process on the vibration data set and the voiceprint data set to obtain a first fusion data set, the method further includes: preprocessing the first fusion data set to obtain a target characteristic parameter set; based on the target characteristic parameter set, obtaining a target characteristic parameter mean value, a target characteristic parameter root mean square value and a target characteristic parameter peak value through a preset calculation method; and predicting the state of the wind turbine bearing to be diagnosed based on the target characteristic parameter mean value, the target characteristic parameter root mean square value and the target characteristic parameter peak value to obtain the state change condition of the wind turbine bearing to be diagnosed.
In a second aspect, an embodiment of the present invention provides a wind turbine generator system bearing fault identification system, where the wind turbine generator system bearing fault identification system includes: the signal acquisition unit is used for acquiring a vibration data set and a voiceprint data set of the bearing of the wind turbine to be diagnosed and sending the vibration data set and the voiceprint data set to the identification unit; the identification unit is configured to obtain, based on the vibration data set and the voiceprint data set, a fault type of the wind turbine bearing to be diagnosed through the wind turbine bearing fault identification method according to the first aspect of the embodiment of the present invention and any one of the first aspect of the embodiment of the present invention.
In a third aspect, an embodiment of the present invention provides a wind turbine generator system bearing fault identification device, where the wind turbine generator system bearing fault identification device includes: the first acquisition module is used for acquiring a vibration data set and a voiceprint data set of the bearing of the wind turbine to be diagnosed; the first fusion processing module is used for carrying out fusion processing on the vibration data set and the voiceprint data set to obtain a first fusion data set; the identification module is used for obtaining at least one fault defect grade relation based on the first fusion data set through a preset bearing fault identification model, and the fault defect grade relation is used for reflecting the corresponding relation between the fusion data in the first fusion data set and the fault defect grade; and the determining module is used for determining the fault type of the wind turbine generator bearing to be diagnosed based on each fault defect grade relation.
With reference to the third aspect, in a possible implementation manner of the third aspect, the apparatus further includes: the second acquisition module is used for acquiring a preset fault database, a historical vibration data set and a historical voiceprint data set of the wind turbine generator bearing; the second fusion processing module is used for carrying out fusion processing on the historical vibration data set and the historical voiceprint data set to obtain a second fusion data set; and the training module is used for preprocessing the second fusion data set and the preset fault database and inputting the preprocessed second fusion data set and the preprocessed second fusion data set into a hidden Markov neural network for training until the preset bearing fault recognition model is obtained.
With reference to the third aspect, in another possible implementation manner of the third aspect, the training module includes: the calculation sub-module is used for obtaining a fusion average value data set through an average value calculation method based on the second fusion data set; the matching sub-module is used for carrying out characteristic matching on the fusion average value data set and the preset fault database to obtain a characteristic fault parameter set; and the training sub-module is used for obtaining the preset bearing fault recognition model through hidden Markov neural network training based on the second fusion data set and the characteristic fault parameter set.
In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium, where computer instructions are stored, where the computer instructions are configured to cause a computer to execute the method for identifying a bearing failure of a wind turbine generator according to the first aspect of the embodiment of the present invention.
In a fifth aspect, an embodiment of the present invention provides an electronic device, including: the wind turbine generator system bearing fault identification method comprises a memory and a processor, wherein the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the computer instructions so as to execute the wind turbine generator system bearing fault identification method according to any one of the first aspect and the first aspect of the embodiment of the invention.
The technical scheme provided by the invention has the following effects:
according to the wind turbine generator bearing fault identification method provided by the embodiment of the invention, the vibration data signals and the voiceprint data signals under different faults are collected and fused, and the fused data are input into the trained preset bearing fault identification model for identification, so that the corresponding relation between the fault data and the fault type of the marine wind turbine generator bearing can be rapidly identified, the fault type of the wind turbine generator bearing to be diagnosed is further obtained, and the fault diagnosis efficiency and accuracy are improved. Therefore, by implementing the method and the device, early fault early warning and intelligent monitoring can be carried out on the bearing of the wind turbine generator, the internal fault characteristics of the bearing can be completely mastered, and the method and the device have very important significance for improving the power generation efficiency, reducing significant economic loss and saving operation and maintenance cost of the offshore wind turbine generator.
According to the wind turbine generator bearing fault identification system provided by the embodiment of the invention, the obtained vibration dataset and voiceprint dataset of the wind turbine generator bearing to be diagnosed are identified by using the wind turbine generator bearing fault identification method provided by the embodiment of the invention, so that the accuracy of fault identification is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a wind turbine generator bearing fault identification method provided according to an embodiment of the invention;
FIG. 2 is a flow chart of a fault intelligent recognition algorithm provided according to an embodiment of the present invention;
FIG. 3 is a flow chart of vibration signal and voiceprint signal identification provided in accordance with an embodiment of the present invention;
FIG. 4 is a flow chart for diagnosing bearing faults of an offshore wind turbine provided according to an embodiment of the invention;
FIG. 5 is a general flow chart for identifying bearing faults of an offshore wind turbine based on multi-information fusion, which is provided by an embodiment of the invention;
FIG. 6 is a block diagram of a wind turbine bearing failure recognition system according to an embodiment of the present invention;
FIG. 7 is a diagnostic flow diagram of an intelligent fault diagnosis system provided in accordance with an embodiment of the present invention;
FIG. 8 is a block diagram of a wind turbine bearing failure recognition device according to an embodiment of the present invention;
FIG. 9 is a schematic diagram of a computer-readable storage medium provided according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiment of the invention provides a wind turbine generator bearing fault identification method, as shown in fig. 1, comprising the following steps:
step 101: and acquiring a vibration data set and a voiceprint data set of the bearing of the wind turbine to be diagnosed.
The vibration data set reflects vibration data of the wind turbine generator under different faults; the voiceprint data set reflects voiceprint data of the wind turbine generator under different faults.
Specifically, the corresponding vibration data set and voiceprint data set can be obtained by setting a plurality of bearing vibration and voiceprint signal acquisition points.
Step 102: and carrying out fusion processing on the vibration data set and the voiceprint data set to obtain a first fusion data set.
The bearing of the offshore wind turbine frequently fails due to severe operation environment and high temperature and high humidity, so that the fault identification is performed by adopting multi-signal fusion based on the vibration data set and the voiceprint data set.
Step 103: and obtaining at least one fault defect grade relation through a preset bearing fault identification model based on the first fusion data set.
The fault defect grade relation is used for reflecting the corresponding relation between the fusion data in the first fusion data set and the fault defect grade.
Specifically, the first fusion data set is input into a preset bearing fault recognition model for recognition, and the corresponding relation between each fusion average value and the fault defect level in the first fusion data set can be obtained.
Step 104: and determining the fault type of the wind turbine generator bearing to be diagnosed based on each fault defect grade relation.
Specifically, according to the obtained corresponding relation between each fusion average value and the fault defect grade, the fault type of the wind turbine generator bearing to be diagnosed can be obtained.
According to the wind turbine generator bearing fault identification method provided by the embodiment of the invention, the vibration data signals and the voiceprint data signals under different faults are collected and fused, and the fused data are input into the trained preset bearing fault identification model for identification, so that the corresponding relation between the fault data and the fault type of the marine wind turbine generator bearing can be rapidly identified, the fault type of the wind turbine generator bearing to be diagnosed is further obtained, and the fault diagnosis efficiency and accuracy are improved. Therefore, by implementing the method and the device, early fault early warning and intelligent monitoring can be carried out on the bearing of the wind turbine generator, the internal fault characteristics of the bearing can be completely mastered, and the method and the device have very important significance for improving the power generation efficiency, reducing significant economic loss and saving operation and maintenance cost of the offshore wind turbine generator.
As an optional implementation manner of the embodiment of the present invention, before step 103, the method further includes: acquiring a historical vibration data set and a historical voiceprint data set of a preset fault database and a wind turbine generator bearing; performing fusion processing on the historical vibration data set and the historical voiceprint data set to obtain a second fusion data set; and preprocessing the second fusion data set and the preset fault database, and inputting the preprocessed second fusion data set and the preset fault database into a hidden Markov neural network for training until the preset bearing fault recognition model is obtained.
The method comprises the steps of preprocessing the second fusion data set and the preset fault database, inputting the preprocessed second fusion data set and the preset fault database into a hidden Markov neural network for training until the preset bearing fault recognition model is obtained, and comprises the following steps: based on the second fusion data set, obtaining a fusion average data set through an average value calculation method; performing feature matching on the fusion average value data set and the preset fault database to obtain a feature fault parameter set; and training through a hidden Markov neural network based on the second fusion data set and the characteristic fault parameter set to obtain the preset bearing fault recognition model.
Specifically, a corresponding preset bearing fault identification model can be constructed by utilizing a historical vibration data set and a historical voiceprint data set of the wind turbine generator bearing and a preset fault database.
In an embodiment, the established network is trained repeatedly by collecting a large amount of wind power bearing fault defect sample data in advance, and the final output result is very close to the expected value by continuously modifying the weight and the threshold value, so that a corresponding identification model is finally obtained, and the identification operation process of the identification model is shown in fig. 2.
Firstly, carrying out fusion processing on a historical vibration data set and a historical voiceprint data set to obtain a second fusion data set;
secondly, calculating a fusion average value of a plurality of vibration information and voiceprint information in the second fusion data set to obtain a fusion average value data set;
then, carrying out feature matching on the fusion average value data set and a preset fault database, and inputting a hidden Markov neural network (HMM) to train by utilizing the feature fault parameter set and the second fusion data set formed after matching to obtain a preset bearing fault recognition model for fault recognition, namely, obtaining a corresponding relation between each fusion average value and a fault defect level in the fusion average value data set through the model, and obtaining according to the relation between the fusion average value data set and the second fusion data set: the fault defect grade corresponding to the fusion data in different value ranges can be obtained through the preset bearing fault identification model, and further, the fault type of the wind turbine generator bearing to be diagnosed is obtained.
In one embodiment, the basic principle of fusion of the vibration signal and the sound signal is adopted to collect data, individual features carried along with the vibration signal and the sound signal are extracted and then matched with training templates in a database according to a certain criterion, and different types of faults are identified or confirmed. The whole process consists of front-end processing, feature extraction, model training, pattern matching, etc., as shown in fig. 3.
As an optional implementation manner of the embodiment of the present invention, after step 102, the method further includes: preprocessing the first fusion data set to obtain a target characteristic parameter set; based on the target characteristic parameter set, obtaining a target characteristic parameter mean value, a target characteristic parameter root mean square value and a target characteristic parameter peak value through a preset calculation method; and predicting the state of the wind turbine bearing to be diagnosed based on the target characteristic parameter mean value, the target characteristic parameter root mean square value and the target characteristic parameter peak value to obtain the state change condition of the wind turbine bearing to be diagnosed.
Specifically, through preprocessing and signal analysis on the collected data (first fusion data set), analysis and calculation are carried out on some necessary parameters generated during bearing vibration, the mean value, the variance root mean square and the peak value of the necessary parameters are extracted, and when the bearing breaks down, the change amplitude of the characteristic parameters is larger, so that the weak fault detection of the bearing is more effective. According to the trend curves, the change rule of each parameter is further reflected, so that the change trend of the bearing state is accurately predicted.
In one embodiment, a bearing fault diagnosis method is provided, which comprises the following three stages: and detecting faults of the wind turbine, extracting main fault characteristics of the wind turbine and accurately identifying faults of the wind turbine. The running state and faults are accurately classified, fault detection is the basis of the whole stage, and obvious fault characteristics can be timely found and maintained by accurately detecting the change of the bearing. The accurate extraction of fault characteristics is a key point in the whole fault diagnosis process, and the accurate representation of fault states can be further realized through the analysis and the processing of the detected various types of signals, so that various fault types can be accurately classified and identified. The fault recognition stage is a core, the accuracy of fault feature recognition is improved through training, so that satisfactory accuracy is achieved, and a specific diagnosis flow is shown in fig. 4.
In yet another example, a method for diagnosing and identifying a failure of an offshore wind turbine bearing based on multi-information fusion is provided, which includes the following steps:
s1: setting a plurality of bearing vibration and voiceprint signal acquisition points, wherein the vibration signal and voiceprint signal acquisition points are used for acquiring information of the bearing, and the fusion information comprises data of vibration and voiceprint information;
s2: the fusion average value of the vibration information and the voiceprint information is x, and the fault diagnosis type of the bearing corresponding to the x is y;
s3: sample statistics were performed: taking N samples, wherein one fault diagnosis type yn corresponds to one fused information average value xn, and N represents a non-zero natural number;
s4: collecting vibration information and fused data information by using an information collecting and processing module, and denoising the N sample fused information to obtain N groups of qualified fused data information;
s5: transmitting N groups of qualified fusion data information to an HMM neural network model for training;
s6: and obtaining the bearing fault defect grade relation corresponding to the M x value ranges.
Further, an intelligent diagnosis method is provided, firstly, different types of fault grade relations corresponding to M x value ranges are obtained; secondly, through a training model of a large amount of data, according to the magnitude values of the fusion data after feature extraction, 5 grades of different types, namely stripping, abrasion, corrosion, indentation and rust are corresponding, and finally five different grade relations corresponding to probability values of a y value range are obtained, wherein the five different grade relations are as follows:
A. y is more than 0 and less than or equal to 0.2, and the judgment result of the HNN neural network model quantization index is stripping;
B. 02 < y is less than or equal to 0.4, and the judgment result of the HNN neural network model quantization index is abrasion;
C. y is more than 0.4 and less than or equal to 0.6, and the judgment result of the HNN neural network model quantization index is corrosion;
D. y is more than 0.6 and less than or equal to 0.8, and the judgment result of the HNN neural network model quantization index is an indentation;
E. y is more than 0.8 and less than or equal to 1, and the judgment result of the HNN neural network model quantization index is rust.
In another example, a method for identifying bearing faults of the offshore wind turbine generator based on multi-information fusion is further provided, and a specific flow is shown in fig. 5.
The embodiment of the invention also provides a wind turbine generator bearing fault recognition system, as shown in fig. 6, the wind turbine generator bearing fault recognition system 2 comprises: a signal acquisition unit 21 and an identification unit 22.
Wherein the signal acquisition unit 21 is in communication with the identification unit 22.
Further, the functions of the respective devices in the above system are described.
Specifically, the signal acquisition unit 21 is configured to acquire a vibration data set and a voiceprint data set of a bearing of a wind turbine to be diagnosed, and send the vibration data set and the voiceprint data set to the identification unit 22.
The identification unit 22 performs fault identification on the received vibration data set and voiceprint data set of the wind turbine bearing to be diagnosed by using the wind turbine bearing fault identification method provided by the embodiment of the invention, so as to obtain the fault type of the wind turbine bearing to be diagnosed.
According to the wind turbine generator bearing fault identification system provided by the embodiment of the invention, the obtained vibration dataset and voiceprint dataset of the wind turbine generator bearing to be diagnosed are identified by using the wind turbine generator bearing fault identification method provided by the embodiment of the invention, so that the accuracy of fault identification is improved.
In one example, an intelligent fault diagnosis system is provided, which is composed of three modules: the first is a signal acquisition module, which mainly selects a proper sensor and a data acquisition card to acquire signals to be analyzed; the second is a feature extraction module, which generally processes the feature extraction module by selecting an algorithm with proper signal characteristics, so as to obtain useful fault feature parameters; and thirdly, a state recognition module, wherein the state recognition module predicts the development trend of the bearing fault or classifies and recognizes the fault on the basis of the characteristic parameters extracted by the characteristic extraction module. A specific diagnostic flow chart is shown in fig. 7.
In another example, an intelligent fault recognition system is also provided, which comprises five parts, namely a vibration signal data and voiceprint data acquisition module, a vibration signal and voiceprint signal preprocessing module, a feature extraction module, a recognition module and a result output module. Wherein, vibration data and voiceprint data identification are mainly divided into three threads: vibration data and voiceprint data acquisition subsystem, main thread module and discernment submodule. The vibration data and voiceprint acquisition sub-thread is mainly responsible for calling hardware to acquire data, and then triggering the sub-function to transmit the data back to the main thread. The main thread is responsible for the operating logic of the entire software program and the invocation of various tool functions. The recognition output module is mainly used for extracting the characteristics of the data, matching the characteristics and recognizing the result.
According to the embodiment of the invention, the bearing faults of the offshore wind turbine can be effectively diagnosed, the intelligent state sensing and early fault early warning of the offshore wind turbine can be guided, and the technology and achievement support are provided for daily operation and maintenance, overhaul and safety monitoring of the offshore wind turbine.
The embodiment of the invention also provides a device for identifying the bearing faults of the wind turbine generator, as shown in fig. 8, which comprises the following steps:
the first acquisition module 301 is configured to acquire a vibration data set and a voiceprint data set of a bearing of a wind turbine to be diagnosed; for details, see the description of step 101 in the above method embodiment.
The first fusion processing module 302 is configured to perform fusion processing on the vibration data set and the voiceprint data set to obtain a first fusion data set; for details, see the description of step 102 in the method embodiment described above.
The identifying module 303 is configured to obtain at least one fault defect level relationship based on the first fusion data set through a preset bearing fault identifying model, where the fault defect level relationship is used to reflect a correspondence between fusion data in the first fusion data set and a fault defect level; for details, see the description of step 103 in the method embodiment described above.
A determining module 304, configured to determine a fault type of the wind turbine bearing to be diagnosed based on each fault defect level relationship; for details, see the description of step 104 in the method embodiment described above.
According to the wind turbine generator bearing fault identification device provided by the embodiment of the invention, the vibration data signals and the voiceprint data signals under different faults are collected and fused, and the fused data are input into the trained preset bearing fault identification model for identification, so that the corresponding relation between the fault data and the fault type of the marine wind turbine generator bearing can be rapidly identified, the fault type of the wind turbine generator bearing to be diagnosed is further obtained, and the fault diagnosis efficiency and accuracy are improved. Therefore, by implementing the method and the device, early fault early warning and intelligent monitoring can be carried out on the bearing of the wind turbine generator, the internal fault characteristics of the bearing can be completely mastered, and the method and the device have very important significance for improving the power generation efficiency, reducing significant economic loss and saving operation and maintenance cost of the offshore wind turbine generator.
As an alternative implementation manner of the embodiment of the present invention, the apparatus further includes: the second acquisition module is used for acquiring a preset fault database, a historical vibration data set and a historical voiceprint data set of the wind turbine generator bearing; the second fusion processing module is used for carrying out fusion processing on the historical vibration data set and the historical voiceprint data set to obtain a second fusion data set; and the training module is used for preprocessing the second fusion data set and the preset fault database and inputting the preprocessed second fusion data set and the preprocessed second fusion data set into a hidden Markov neural network for training until the preset bearing fault recognition model is obtained.
As an optional implementation manner of the embodiment of the present invention, the training module includes: the calculation sub-module is used for obtaining a fusion average value data set through an average value calculation method based on the second fusion data set; the matching sub-module is used for carrying out characteristic matching on the fusion average value data set and the preset fault database to obtain a characteristic fault parameter set; and the training sub-module is used for obtaining the preset bearing fault recognition model through hidden Markov neural network training based on the second fusion data set and the characteristic fault parameter set.
As an alternative implementation manner of the embodiment of the present invention, the apparatus further includes: the preprocessing module is used for preprocessing the first fusion data set to obtain a target characteristic parameter set; the computing module is used for obtaining a target characteristic parameter mean value, a target characteristic parameter root mean square value and a target characteristic parameter peak value through a preset computing method based on the target characteristic parameter set; the prediction module is used for predicting the state of the wind turbine generator bearing to be diagnosed based on the target characteristic parameter mean value, the target characteristic parameter root mean square value and the target characteristic parameter peak value to obtain the state change condition of the wind turbine generator bearing to be diagnosed.
The functional description of the wind turbine generator system bearing fault recognition device provided by the embodiment of the invention is detailed in the description of the wind turbine generator system bearing fault recognition method in the embodiment.
The embodiment of the present invention also provides a storage medium, as shown in fig. 9, on which is stored a computer program 401, which when executed by a processor, implements the steps of the method for identifying a failure of a wind turbine generator set bearing of the above embodiment. The storage medium may be a magnetic Disk, an optical disc, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a Flash Memory (Flash Memory), a Hard Disk (HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
It will be appreciated by those skilled in the art that implementing all or part of the above-described embodiment method may be implemented by a computer program to instruct related hardware, where the program may be stored in a computer readable storage medium, and the program may include the above-described embodiment method when executed. The storage medium may be a magnetic Disk, an optical disc, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a Flash Memory (Flash Memory), a Hard Disk (HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
The embodiment of the present invention further provides an electronic device, as shown in fig. 10, where the electronic device may include a processor 51 and a memory 52, where the processor 51 and the memory 52 may be connected by a bus or other means, and in fig. 10, the connection is exemplified by a bus.
The processor 51 may be a central processing unit (Central Processing Unit, CPU). The processor 51 may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations thereof.
The memory 52 serves as a non-transitory computer readable storage medium that may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as corresponding program instructions/modules in embodiments of the present invention. The processor 51 executes various functional applications and data processing of the processor by running non-transitory software programs, instructions and modules stored in the memory 52, i.e. implementing the wind turbine bearing failure recognition method in the above-described method embodiment.
The memory 52 may include a memory program area that may store an operating device, an application program required for at least one function, and a memory data area; the storage data area may store data created by the processor 51, etc. In addition, memory 52 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 52 may optionally include memory located remotely from processor 51, which may be connected to processor 51 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 52, which when executed by the processor 51, performs the wind turbine bearing failure identification method in the embodiments shown in fig. 1-5.
The specific details of the electronic device may be understood correspondingly with reference to the corresponding related descriptions and effects in the embodiments shown in fig. 1 to 5, which are not repeated here.
Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.
Claims (10)
1. The method for identifying the bearing faults of the wind turbine generator is characterized by comprising the following steps:
acquiring a vibration data set and a voiceprint data set of a bearing of a wind turbine to be diagnosed;
performing fusion processing on the vibration data set and the voiceprint data set to obtain a first fusion data set;
based on the first fusion data set, obtaining at least one fault defect grade relation through a preset bearing fault identification model, wherein the fault defect grade relation is used for reflecting the corresponding relation between the fusion data in the first fusion data set and the fault defect grade;
and determining the fault type of the wind turbine generator bearing to be diagnosed based on each fault defect grade relation.
2. The method according to claim 1, characterized in that it comprises: based on the first fusion data set, before obtaining at least one fault defect grade relation through a preset bearing fault identification model, the method further comprises:
acquiring a historical vibration data set and a historical voiceprint data set of a preset fault database and a wind turbine generator bearing;
performing fusion processing on the historical vibration data set and the historical voiceprint data set to obtain a second fusion data set;
and preprocessing the second fusion data set and the preset fault database, and inputting the preprocessed second fusion data set and the preset fault database into a hidden Markov neural network for training until the preset bearing fault recognition model is obtained.
3. The method of claim 2, wherein preprocessing the second fused dataset and the pre-set fault database before inputting a hidden markov neural network training until the pre-set bearing fault identification model is obtained, comprising:
based on the second fusion data set, obtaining a fusion average data set through an average value calculation method;
performing feature matching on the fusion average value data set and the preset fault database to obtain a feature fault parameter set;
and training through a hidden Markov neural network based on the second fusion data set and the characteristic fault parameter set to obtain the preset bearing fault recognition model.
4. The method of claim 1, wherein after fusing the vibration dataset and the voiceprint dataset to obtain a first fused dataset, the method further comprises:
preprocessing the first fusion data set to obtain a target characteristic parameter set;
based on the target characteristic parameter set, obtaining a target characteristic parameter mean value, a target characteristic parameter root mean square value and a target characteristic parameter peak value through a preset calculation method;
and predicting the state of the wind turbine bearing to be diagnosed based on the target characteristic parameter mean value, the target characteristic parameter root mean square value and the target characteristic parameter peak value to obtain the state change condition of the wind turbine bearing to be diagnosed.
5. A wind turbine bearing failure recognition system, the system comprising:
the signal acquisition unit is used for acquiring a vibration data set and a voiceprint data set of the bearing of the wind turbine to be diagnosed and sending the vibration data set and the voiceprint data set to the identification unit;
the identification unit is used for obtaining the fault type of the wind turbine bearing to be diagnosed through the wind turbine bearing fault identification method according to any one of claims 1-4 based on the vibration data set and the voiceprint data set.
6. A wind turbine bearing failure recognition device, the device comprising:
the first acquisition module is used for acquiring a vibration data set and a voiceprint data set of the bearing of the wind turbine to be diagnosed;
the first fusion processing module is used for carrying out fusion processing on the vibration data set and the voiceprint data set to obtain a first fusion data set;
the identification module is used for obtaining at least one fault defect grade relation based on the first fusion data set through a preset bearing fault identification model, and the fault defect grade relation is used for reflecting the corresponding relation between the fusion data in the first fusion data set and the fault defect grade;
and the determining module is used for determining the fault type of the wind turbine generator bearing to be diagnosed based on each fault defect grade relation.
7. The apparatus of claim 6, wherein the apparatus further comprises:
the second acquisition module is used for acquiring a preset fault database, a historical vibration data set and a historical voiceprint data set of the wind turbine generator bearing;
the second fusion processing module is used for carrying out fusion processing on the historical vibration data set and the historical voiceprint data set to obtain a second fusion data set;
and the training module is used for preprocessing the second fusion data set and the preset fault database and inputting the preprocessed second fusion data set and the preprocessed second fusion data set into a hidden Markov neural network for training until the preset bearing fault recognition model is obtained.
8. The apparatus of claim 7, wherein the training module comprises:
the calculation sub-module is used for obtaining a fusion average value data set through an average value calculation method based on the second fusion data set;
the matching sub-module is used for carrying out characteristic matching on the fusion average value data set and the preset fault database to obtain a characteristic fault parameter set;
and the training sub-module is used for obtaining the preset bearing fault recognition model through hidden Markov neural network training based on the second fusion data set and the characteristic fault parameter set.
9. A computer-readable storage medium storing computer instructions for causing the computer to perform the wind turbine bearing fault identification method according to any one of claims 1 to 4.
10. An electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the wind turbine bearing failure identification method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310406239.8A CN116625683A (en) | 2023-04-11 | 2023-04-11 | Wind turbine generator system bearing fault identification method, system and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310406239.8A CN116625683A (en) | 2023-04-11 | 2023-04-11 | Wind turbine generator system bearing fault identification method, system and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116625683A true CN116625683A (en) | 2023-08-22 |
Family
ID=87612405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310406239.8A Pending CN116625683A (en) | 2023-04-11 | 2023-04-11 | Wind turbine generator system bearing fault identification method, system and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116625683A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116910570A (en) * | 2023-09-13 | 2023-10-20 | 华能新能源股份有限公司山西分公司 | Wind turbine generator system fault monitoring and early warning method and system based on big data |
| CN117905656A (en) * | 2024-03-20 | 2024-04-19 | 南京土星视界科技有限公司 | On-line monitoring device for fan blade |
| CN118408743A (en) * | 2024-07-04 | 2024-07-30 | 山东轴研精密轴承有限公司 | Bearing fault detection system and method |
| CN118794690A (en) * | 2024-09-13 | 2024-10-18 | 华润电力技术研究院有限公司 | Bearing fault diagnosis method for multi-source wind turbine generator |
-
2023
- 2023-04-11 CN CN202310406239.8A patent/CN116625683A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116910570A (en) * | 2023-09-13 | 2023-10-20 | 华能新能源股份有限公司山西分公司 | Wind turbine generator system fault monitoring and early warning method and system based on big data |
| CN116910570B (en) * | 2023-09-13 | 2023-12-15 | 华能新能源股份有限公司山西分公司 | Wind turbine generator system fault monitoring and early warning method and system based on big data |
| CN117905656A (en) * | 2024-03-20 | 2024-04-19 | 南京土星视界科技有限公司 | On-line monitoring device for fan blade |
| CN118408743A (en) * | 2024-07-04 | 2024-07-30 | 山东轴研精密轴承有限公司 | Bearing fault detection system and method |
| CN118408743B (en) * | 2024-07-04 | 2024-10-01 | 山东轴研精密轴承有限公司 | Bearing fault detection system and method |
| CN118794690A (en) * | 2024-09-13 | 2024-10-18 | 华润电力技术研究院有限公司 | Bearing fault diagnosis method for multi-source wind turbine generator |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116625683A (en) | Wind turbine generator system bearing fault identification method, system and device and electronic equipment | |
| CN110044623B (en) | Intelligent rolling bearing fault identification method based on empirical mode decomposition residual signal characteristics | |
| CN112692646B (en) | Intelligent assessment method and device for tool wear state | |
| KR102321607B1 (en) | Rotating machine fault detecting apparatus and method | |
| CN110060368A (en) | Mechanical method for detecting abnormality based on potential feature coding | |
| CN115758200A (en) | Vibration signal fault identification method and system based on similarity measurement | |
| CN115437358A (en) | Intelligent state monitoring and fault diagnosis system and fault diagnosis method for industrial robot | |
| CN113339204A (en) | Wind driven generator fault identification method based on hybrid neural network | |
| CN111678699A (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| CN112711850B (en) | Unit on-line monitoring method based on big data | |
| CN112729825A (en) | Method for constructing bearing fault diagnosis model based on convolution cyclic neural network | |
| CN118051822A (en) | Equipment running state abnormality detection method based on voiceprint recognition technology | |
| CN114996258B (en) | Contact network fault diagnosis method based on data warehouse | |
| CN115793590A (en) | Data processing method and platform suitable for system safety operation and maintenance | |
| CN118114186B (en) | Equipment vibration fault diagnosis method based on artificial intelligence | |
| CN113237619B (en) | Fault early warning method, device, equipment and storage medium for variable-speed rotating machinery vibration | |
| KR102306244B1 (en) | Method and apparatus for generating fault detecting model for device | |
| CN117423345A (en) | Voiceprint recognition monitoring system for power equipment | |
| Wu et al. | Early anomaly detection in wind turbine bolts breaking problem—Methodology and application | |
| Sobha et al. | A comprehensive approach for gearbox fault detection and diagnosis using sequential neural networks | |
| CN114839960A (en) | Method and system for detecting vehicle fault based on artificial intelligence algorithm | |
| CN118609601B (en) | Voiceprint information-based equipment operation state identification method and system | |
| CN118706446B (en) | Noise detection method and system applied to speed reducer | |
| CN118260648B (en) | Pumped storage power station equipment supervision system for fault wave recording identification | |
| KR102321602B1 (en) | Rotating machine fault detecting apparatus and method |
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 |