CN116664096A - Wind power bolt data processing method and device based on federal learning - Google Patents
Wind power bolt data processing method and device based on federal learning Download PDFInfo
- Publication number
- CN116664096A CN116664096A CN202211014503.5A CN202211014503A CN116664096A CN 116664096 A CN116664096 A CN 116664096A CN 202211014503 A CN202211014503 A CN 202211014503A CN 116664096 A CN116664096 A CN 116664096A
- Authority
- CN
- China
- Prior art keywords
- bolt
- wind power
- data information
- fault
- characteristic
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 16
- 238000013210 evaluation model Methods 0.000 claims abstract description 77
- 238000012549 training Methods 0.000 claims abstract description 58
- 238000004458 analytical method Methods 0.000 claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 31
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 25
- 238000011156 evaluation Methods 0.000 claims abstract description 24
- 238000000586 desensitisation Methods 0.000 claims abstract description 15
- 238000012423 maintenance Methods 0.000 claims abstract description 11
- 230000002776 aggregation Effects 0.000 claims abstract description 6
- 238000004220 aggregation Methods 0.000 claims abstract description 6
- 239000000463 material Substances 0.000 claims description 22
- 238000012706 support-vector machine Methods 0.000 claims description 20
- 238000003066 decision tree Methods 0.000 claims description 19
- 238000005259 measurement Methods 0.000 claims description 19
- 238000010276 construction Methods 0.000 claims description 5
- 238000000691 measurement method Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 description 16
- 238000004590 computer program Methods 0.000 description 13
- 230000015654 memory Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 229910000831 Steel Inorganic materials 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 229910000851 Alloy steel Inorganic materials 0.000 description 1
- 229910001339 C alloy Inorganic materials 0.000 description 1
- 229910000975 Carbon steel Inorganic materials 0.000 description 1
- 229910000954 Medium-carbon steel Inorganic materials 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000010962 carbon steel Substances 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000002592 echocardiography Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000010791 quenching Methods 0.000 description 1
- 230000000171 quenching effect Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000005496 tempering Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Human Resources & Organizations (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Wind Motors (AREA)
Abstract
The disclosure provides a wind power bolt data processing method and device based on federal learning. The scheme is as follows: acquiring first wind power bolt data information of a first area; uploading the data information of the first wind power bolt after data desensitization to a bolt analysis module; analyzing the first wind power bolt data information to obtain a first characteristic; inputting the first characteristic into a convolutional neural network for training to construct a first evaluation model; obtaining a second characteristic of the second region, and inputting the second characteristic into a convolutional neural network for training to obtain a second evaluation model; performing aggregation training on model parameters of the first and second evaluation models to obtain a comprehensive evaluation model; and obtaining an evaluation result according to the comprehensive evaluation model, and carrying out maintenance management on the wind turbine generator based on the evaluation result. Therefore, accuracy and instantaneity of the bolt data processing result are improved, the supervision and management level of the wind turbine generator set is further improved, safe operation of the wind turbine generator set is guaranteed, and the method has good application prospects.
Description
Technical Field
The disclosure relates to the technical field of deep learning, in particular to a wind power bolt data processing method and device based on federal learning.
Background
The bolt connection is an important assembly mode in the assembly of the wind generating set, almost all parts of the wind generating set are involved, and the selection and strength check of the bolts and the assembly quality are important guarantees of the reliability of the wind generating set. With the rapid increase of the number of installed fans in China in recent years, a plurality of accidents of fan collapse occur, and many of the accidents are caused by failure of connecting bolts, and even the accidents of collapse of wind turbine tower cylinders occur seriously, so that serious economic loss and political influence are caused. Therefore, the reliability and the safety of the bolt data monitoring play a vital role in the normal operation of the whole wind turbine generator.
However, the prior art has the technical problems that the wind turbine generator system safe operation is affected due to the fact that the wind turbine bolt fault data are not timely and accurate.
Disclosure of Invention
The disclosure provides a wind power bolt data processing method and device based on federal learning.
According to a first aspect of the present disclosure, there is provided a wind power bolt data processing method based on federal learning, including:
Acquiring first wind power bolt data information of a first area;
uploading the data information of the first wind power bolt subjected to data desensitization to a wind power bolt analysis module;
performing fault identification analysis on the first wind power bolt data information based on the wind power bolt analysis module so as to obtain a first bolt fault characteristic;
inputting the first bolt fault characteristics into a deep convolutional neural network for training to construct a first wind power bolt evaluation model;
obtaining a second bolt fault characteristic of a second area, and inputting the second bolt fault characteristic into the deep convolutional neural network for distributed training to obtain a second wind power bolt evaluation model;
performing aggregation training on model parameters of the first wind power bolt evaluation model and the second wind power bolt evaluation model to obtain a wind power bolt comprehensive evaluation model;
and obtaining a wind power bolt evaluation result according to the wind power bolt comprehensive evaluation model, and carrying out maintenance management on the wind turbine generator based on the wind power bolt evaluation result.
According to a second aspect of the present disclosure, there is provided a federally learning-based wind power bolt data processing apparatus, comprising:
the first acquisition module is used for acquiring first wind power bolt data information of a first area;
The uploading module is used for uploading the data information of the first wind power bolt subjected to data desensitization to the wind power bolt analysis module;
the analysis module is used for carrying out fault identification analysis on the first wind power bolt data information based on the wind power bolt analysis module so as to obtain first bolt fault characteristics;
the construction module is used for inputting the first bolt fault characteristics into a deep convolutional neural network for training so as to construct a first wind power bolt evaluation model;
the second acquisition module is used for acquiring a second bolt fault characteristic of a second area, inputting the second bolt fault characteristic into the deep convolutional neural network for distributed training, and acquiring a second wind power bolt evaluation model;
the third acquisition module is used for performing aggregate training on model parameters of the first wind power bolt evaluation model and the second wind power bolt evaluation model to obtain a wind power bolt comprehensive evaluation model;
and the fourth acquisition module is used for acquiring a wind power bolt evaluation result according to the wind power bolt comprehensive evaluation model and carrying out maintenance management on the wind turbine generator based on the wind power bolt evaluation result.
In a third aspect, the present application provides an electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected by the bus, the computer program when executed by the processor implementing the steps of any of the methods described above.
In a fourth aspect, the application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of any of the methods described above.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
the method comprises the steps of carrying out data desensitization on wind power bolt data information acquired by an acquisition area, uploading the data desensitization information to a wind power bolt analysis module for fault identification analysis, inputting the identified bolt fault characteristics into a deep convolutional neural network for training, constructing a first wind power bolt evaluation model, similarly acquiring the bolt fault characteristics of other areas, inputting the acquired second bolt fault characteristics into the deep convolutional neural network for distributed training, constructing a second wind power bolt evaluation model, carrying out aggregation training on model parameters of the first wind power bolt evaluation model and the second wind power bolt evaluation model, constructing a wind power bolt comprehensive evaluation model, outputting wind power bolt evaluation results according to the wind power bolt comprehensive evaluation model, and carrying out maintenance management on a wind turbine generator based on the wind power bolt evaluation results. And then, the bolt data of a plurality of areas are integrated and analyzed, the data utilization rate is improved, a wind power bolt comprehensive evaluation model is constructed to timely process bolt faults, the accuracy and the instantaneity of bolt data processing results are improved, the supervision and management level of the wind turbine generator set is further improved, the occurrence of safety accidents is prevented through advanced diagnosis, technical basis is provided for overhauling, reconstruction and supervision of related parts of the bolts, and the technical effect of safe operation of the wind turbine generator set is ensured.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
FIG. 1 is a flowchart of a method for processing wind power bolt data based on federal learning according to an embodiment of the present disclosure;
FIG. 2 is a flowchart of a method for processing wind power bolt data based on federal learning according to an embodiment of the present disclosure;
FIG. 3 is a block diagram of a wind turbine bolt data processing apparatus based on federal learning according to an embodiment of the present disclosure;
FIG. 4 is a block diagram of an electronic device for implementing a federally learned wind turbine data processing method in accordance with an embodiment of the present disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The federally learned wind power bolt data processing method, apparatus, electronic device and storage medium according to embodiments of the present disclosure are described below with reference to the accompanying drawings.
The method can be executed by the wind power bolt data processing device based on federal learning, and the device can be realized in a software and/or hardware mode or can be executed by electronic equipment provided by the present disclosure. The wind power bolt data processing method based on federal learning provided by the present disclosure is performed with the wind power bolt data processing device based on federal learning provided by the present disclosure, and is not limited to the present disclosure, and is hereinafter simply referred to as a "device".
Fig. 1 is a flowchart of a method for processing wind power bolt data based on federal learning according to an embodiment of the present disclosure.
As shown in fig. 1, the application provides a wind power bolt data processing method based on federal learning, wherein the method comprises the following steps:
and step 101, acquiring first wind power bolt data information of a first area.
Specifically, the bolt connection is an important assembly mode in the assembly of the wind generating set, almost all parts of the wind generating set are involved, and the selection and strength check of the bolts and the assembly quality are important guarantees of the reliability of the wind generating set. With the rapid increase of the number of installed fans in China in recent years, a plurality of accidents of fan collapse occur, and many of the accidents are caused by failure of connecting bolts, and even the accidents of collapse of wind turbine tower cylinders occur seriously, so that serious economic loss and political influence are caused. Therefore, the reliability and the safety of the bolt data monitoring play a vital role in the normal operation of the whole wind turbine generator.
And acquiring wind power bolt data information, wherein the first area is a data acquisition area of a wind generating set and can be any area of wind power generation. The collected first wind power bolt data information of the area comprises bolt material components, mechanical properties, head shape, thread teeth, manufacturing precision, size structure, average service life, application scene, use effect, use failure rate and the like, and a data base is provided for accurate analysis of subsequent bolt failure data.
And step 102, uploading the data information of the first wind power bolt subjected to data desensitization to a wind power bolt analysis module.
Specifically, after data desensitization is carried out on the first wind power bolt data information, uploading is carried out, the data desensitization refers to real data deformation of certain wind power sensitive information through a desensitization rule, reliable protection of bolt sensitive privacy data is achieved, and data transmission safety is guaranteed. And transmitting the data to a wind power bolt analysis module for analysis, wherein the wind power bolt analysis module is a basic module for analyzing the acquired data so as to realize identification control of bolt fault information.
And step 103, performing fault identification analysis on the first wind power bolt data information based on the wind power bolt analysis module so as to obtain a first bolt fault characteristic.
Specifically, the device can carry out fault identification analysis on each bolt data in the first wind power bolt data information based on the wind power bolt analysis module. The method comprises the steps of firstly classifying first wind power bolt data information through a bolt characteristic decision tree, constructing the bolt characteristic decision tree through bolt characteristic information, and obtaining bolt classification characteristic information, wherein the bolt classification characteristic information is a bolt characteristic classification result and comprises bolt dimension specification characteristics, material characteristics, application scene characteristics and the like. The bolts with different characteristic categories have different fault recognition modes, so that the bolt calibration coefficients are determined according to the bolt classification characteristic information and are used for dividing the selection of the recognition model when the bolts are subjected to fault calibration.
Then, a first bolt fault identification support vector machine, which is a fault identification model applicable to the bolt, can be called from a bolt fault identification model library based on the bolt calibration coefficients. And inputting the first wind power bolt data information into the first bolt fault identification support vector machine, and obtaining a training output result of the model, namely the first bolt fault characteristics, wherein the first bolt fault characteristics comprise strength fault characteristics, connection fault characteristics, material fault characteristics and the like. By classifying and identifying the fault data, the bolt fault data can be accurately and effectively obtained, and the accuracy and the effectiveness of the bolt data processing result can be further improved.
And 104, inputting the first bolt fault characteristics into a deep convolutional neural network for training to construct a first wind power bolt evaluation model.
Specifically, the first bolt fault characteristics can be input into a deep convolutional neural network for training, and the deep convolutional neural network is a feedforward neural network which comprises convolutional calculation and has a deep structure, and has high characteristic recognition stability. And constructing a first wind power bolt evaluation model through training, wherein the first wind power bolt evaluation model is used for wind power bolt data processing in the area so as to timely identify bolt fault information and accurately analyze fault characteristics.
And 105, obtaining a second bolt fault feature of the second area, and inputting the second bolt fault feature into a deep convolutional neural network for distributed training to obtain a second wind power bolt evaluation model.
Specifically, in order to perform more accurate and comprehensive analysis on wind power bolt fault data, bolt data acquisition is performed on other areas in the same way, one or more second areas can be provided, second bolt fault characteristics are input into the deep convolutional neural network to perform multiparty distributed training, and a corresponding second wind power bolt evaluation model is obtained.
And 106, performing aggregate training on model parameters of the first wind power bolt evaluation model and the second wind power bolt evaluation model to obtain a wind power bolt comprehensive evaluation model.
And performing aggregate training on model parameters of the first wind power bolt evaluation model and the second wind power bolt evaluation model based on the training result of the wind power bolt evaluation model, such as bolt fault type parameters, fault influence range parameters, model corresponding weights and the like. And updating parameters of the evaluation model according to model parameters, constructing a comprehensive evaluation model of the wind power bolts after the aggregate training, so that the output result of the comprehensive evaluation model of the wind power bolts after the parameter federal learning is more reasonable and accurate, the application range is more comprehensive, and the utilization rate of the collected data of the bolts is improved.
And step 107, obtaining a wind power bolt evaluation result according to the wind power bolt comprehensive evaluation model, and carrying out maintenance management on the wind turbine generator based on the wind power bolt evaluation result.
Specifically, according to the constructed comprehensive wind power bolt evaluation model, fault analysis is performed on the wind power bolt to be evaluated to obtain corresponding wind power bolt evaluation results, such as whether the bolt works safely, fault types, fault severity, fault influence range and the like. And carrying out maintenance management, such as maintenance measures of overhaul, replacement, diagnosis, reconstruction and the like, on the wind turbine generator based on the wind power bolt evaluation result.
By integrating and analyzing bolt data of a plurality of areas, the data utilization rate is improved, a wind power bolt comprehensive evaluation model is constructed to timely process bolt faults, accuracy and instantaneity of bolt data processing results are improved, and further supervision and management level of a wind turbine generator set is improved, safety accidents are prevented through advanced diagnosis, technical basis is provided for overhauling, reconstruction and supervision of related parts of the bolts, and safe operation of the wind turbine generator set is guaranteed.
In summary, the wind power bolt data information acquired in the acquisition area is subjected to data desensitization and then uploaded to the wind power bolt analysis module for fault identification analysis, the identified bolt fault characteristics are input into the deep convolutional neural network for training, a first wind power bolt evaluation model is built, the bolt fault characteristics of other areas are acquired in a similar way, the acquired second bolt fault characteristics are input into the deep convolutional neural network for distributed training, a second wind power bolt evaluation model is built, model parameters of the first wind power bolt evaluation model and model parameters of the second wind power bolt evaluation model are subjected to aggregation training, a wind power bolt comprehensive evaluation model is built, wind power bolt evaluation results are output according to the wind power bolt comprehensive evaluation model, and the wind power generation set is maintained and managed based on the wind power bolt evaluation results. And then, the bolt data of a plurality of areas are integrated and analyzed, the data utilization rate is improved, a wind power bolt comprehensive evaluation model is constructed to timely process bolt faults, the accuracy and the instantaneity of bolt data processing results are improved, the supervision and management level of the wind turbine generator set is further improved, the occurrence of safety accidents is prevented through advanced diagnosis, technical basis is provided for overhauling, reconstruction and supervision of related parts of the bolts, and the technical effect of safe operation of the wind turbine generator set is ensured.
The method can be applied to data processing of wind power bolts, and by integrating and analyzing bolt data of a plurality of areas, the data utilization rate, the accuracy and the instantaneity of bolt data processing results are improved, so that the supervision and management level of the wind power generator set is improved, the safe operation of the wind power generator set is ensured, and the method has a good application prospect.
FIG. 2 is a flowchart of a method for processing wind power bolt data based on federal learning according to an embodiment of the present application.
As shown in fig. 2, the application provides a wind power bolt data processing method based on federal learning, wherein the method comprises the following steps:
step 201, acquiring first wind power bolt data information of a first area.
And 202, uploading the data information of the first wind power bolt subjected to data desensitization to a wind power bolt analysis module.
It should be noted that, the specific implementation manner of the steps 201 and 202 may refer to the above embodiments, and will not be described herein.
And 203, classifying the first wind power bolt data information based on a bolt characteristic decision tree to obtain bolt classification characteristic information.
Specifically, the device may first construct a bolt feature decision tree before classifying the first wind power bolt data information based on the bolt feature decision tree, specifically by:
Obtaining a bolt mechanical specification attribute, and taking the bolt mechanical specification attribute as a first classification characteristic;
obtaining a bolt material grade attribute, and taking the bolt material grade attribute as a second classification characteristic;
obtaining a bolt application attribute, and taking the bolt application attribute as a third classification characteristic;
and constructing the bolt characteristic decision tree according to the first classification characteristic, the second classification characteristic and the third classification characteristic.
Specifically, to build a bolt feature decision tree specifically, bolt classification features are first determined. And taking the bolt mechanical specification attribute as a first classification characteristic, wherein the bolt mechanical specification attribute is a bolt size specification, and comprises a bolt mechanical size, a head shape, a thread tooth and the like, and is used in an application scene according to the bolt mechanical specification.
The bolt material grade attribute is taken as a second classification characteristic, the bolt material grade attribute is the mechanical grade of a bolt material, including carbon steel, alloy steel, stainless steel, heat-resistant steel and the like, and the mechanical properties of the bolt material grade are correspondingly different, for example, the bolt material above 8.8 grades (including 8.8 grades) is low-carbon alloy steel or medium-carbon steel and is subjected to heat treatment (quenching and tempering), so that the bolt is commonly called a high-strength bolt, and the bolt below 8.8 grades (excluding 8.8 grades) is commonly called a common bolt.
And taking the bolt application attribute as a third classification characteristic, wherein the bolt application attribute is an application scene of the bolt in the wind turbine generator, such as a tower foundation bolt, a tower flange bolt, a bolt for a yaw system, a main shaft bolt, a blade bolt and the like, and the strength requirements are different according to different application attributes. The decision tree is a decision analysis method for solving the probability that the expected value of the net present value is larger than or equal to zero by forming the decision tree on the basis of knowing the occurrence probability of various conditions, and judging the feasibility of the net present value, and is a graphical method for intuitively applying probability analysis.
And taking the first classification feature, the second classification feature and the third classification feature as internal nodes of the bolt feature decision tree respectively, and carrying out information entropy calculation on the internal nodes to carry out priority classification on the feature with the minimum entropy value, so that the bolt feature decision tree is constructed recursively. And carrying out bolt data classification through the accuracy construction of the bolt characteristic decision tree so as to determine the personalized call of the subsequent bolt fault recognition model, thereby improving the accuracy and the specificity of the bolt data processing result.
And 204, determining a bolt calibration coefficient according to the bolt classification characteristic information.
It should be noted that, the bolts with different feature categories and the fault recognition modes are also different, so that the bolt calibration coefficient is determined according to the bolt classification feature information, and the bolt calibration coefficient is used for dividing the selection of the recognition model when the fault calibration is carried out on the bolts.
And 205, constructing a historical bolt data information base, wherein the historical bolt data information base comprises bolt data information of each calibration coefficient type.
Specifically, a historical bolt data information base is constructed, wherein the historical bolt data information base comprises bolt data information of various calibration coefficient categories, and the bolt data information comprises various fault bolt data information, such as bolt fault types, fault causes and the like. And carrying out cluster division on the data information in the historical bolt data information base, namely carrying out fault classification on the bolt data information, and obtaining a corresponding bolt cluster information result.
And 206, carrying out cluster division on the data information in the historical bolt data information base to obtain a bolt cluster information result.
Optionally, the device may obtain a bolt measurement signal wave by an ultrasonic measurement method, then denoise and filters the bolt measurement signal wave to obtain a standard bolt measurement signal wave, then performs feature analysis on the standard bolt measurement signal wave to obtain an ultrasonic transit time, and then performs cluster division on the data information in the historical bolt data information base based on the ultrasonic transit time.
Specifically, the device can monitor bolt stress through ultrasonic measurement method, and ultrasonic stress measurement technique utilizes the inside various information of ultrasonic wave sensitively reflection test piece, uses ultrasonic wave parameter to represent stress, has accurate, environmental protection, portable, penetrating power is strong, fast advantage. The principle of ultrasonic stress measurement is controlled by utilizing the propagation time of ultrasonic under different stress conditions, and the bolt stress can be measured by a bolt stress ultrasonic measuring instrument to obtain detected bolt measuring signal waves, namely ultrasonic wave measuring longitudinal wave information of the bolt to be measured. And then denoising and filtering the bolt measurement signal wave, removing noise from the wave form, and filtering out the frequency of a specific wave band in the signal so as to reduce the influence of noise interference and the like between equipment and the external environment and obtain the processed standard bolt measurement signal wave. And based on time difference characteristic analysis on the standard bolt measurement signal wave, obtaining ultrasonic transit time, wherein the ultrasonic transit time is the time difference between two adjacent reflected echoes of the ultrasonic longitudinal wave signal which is transmitted to the bolt by the ultrasonic probe and is transmitted back and forth along the axial direction of the bolt. The ultrasonic transit time reflects the stress applied to the axial direction of the bolt, and the stress state of the bolt is judged based on the ultrasonic transit time, so that the data information in the historical bolt data information base is clustered and divided. Bolt data of operation faults are determined through ultrasonic measurement, identification is more accurate and effective, technical basis is provided for overhauling, reconstruction and supervision of related parts of the bolts, and fine management of bolts of the wind turbine generator is achieved.
When the device performs clustering classification on the data information in the historical bolt data information base based on the ultrasonic transit time, the ultrasonic transit time can be input into an ultrasonic stress time difference formula at first, the axial stress of the bolt is obtained through calculation, then the working state of the bolt is determined based on the axial stress of the bolt, and then when the axial stress of the bolt reaches a preset yield value, the working state of the bolt is early warned to be a fault according to a first early warning instruction.
Further, the ultrasonic stress time difference formula specifically comprises:
wherein sigma is the axial stress of the bolt; Δt is the ultrasonic transit time; l (L) 0 The length of the bolt; k is the elastic constant of the bolt material; e is Young's modulus; c (C) 0 The speed of sound is measured for ultrasound.
Specifically, the ultrasonic transit time is input into an ultrasonic stress time difference formula, the axial stress of the bolt can be calculated and obtained, sigma is the calculated axial stress of the bolt, Δt is the ultrasonic transit time, and L 0 The length of the bolt is K, the elastic constant of the bolt material is K, E is Young's modulus, the Young's modulus is related to the bolt material, the rigidity of the material is marked, the larger the Young's modulus is, the less easy deformation is caused, C 0 For ultrasonic measurements of sound velocity, the sound velocity is related to the propagation medium.
The device can determine the working state of the bolt based on the axial stress of the bolt, judge whether the axial stress of the bolt is in the safe operation range of the bolt, and when the axial stress of the bolt reaches a preset yield value, namely the axial stress of the bolt is overlarge and exceeds the bearing limit of the bolt, the bolt can be deformed or broken and damaged. And detecting the stress state of the bolt by ultrasonic measurement according to the first early warning instruction, comprehensively and accurately controlling the defect damage condition of the bolt of the wind turbine generator in operation, improving the controllability of the defect of the bolt, and realizing standardized and refined management of the bolt of the wind turbine generator.
And 207, performing category marking on the bolt clustering information result to obtain a marked training bolt data set.
And carrying out category marking on the bolt clustering information result, for example, connection fracture faults and the like caused by material problems, and obtaining a corresponding marking training bolt data set.
And step 208, respectively taking the marked training bolt data set as input data according to the calibration coefficient categories to carry out support vector machine model training, and constructing the bolt fault identification model library.
It should be noted that, the labeled training bolt data set may be divided according to each calibration coefficient type, and the labeled training bolt data set may be used as input data to perform model training of a support vector machine, where the support vector machine is generally used to perform pattern recognition, classification and regression analysis, that is, to construct a bolt fault recognition model by performing supervised learning on the labeled training detection data set. And constructing a bolt fault recognition model library through bolt fault recognition models of various calibration coefficient types, and timely recognizing bolt fault data through constructing a vector machine model library, so that personalized calling of the bolt recognition models is ensured, and further, the accuracy and the efficiency of fault data recognition are improved.
And step 209, calling a first bolt fault identification support vector machine from a bolt fault identification model library based on the bolt calibration coefficient.
And 210, inputting the first wind power bolt data information into the first bolt fault identification support vector machine to obtain the first bolt fault characteristics.
The device can call a first bolt fault identification support vector machine from a bolt fault identification model library based on the bolt calibration coefficient, wherein the first bolt fault identification support vector machine is a fault identification model suitable for the bolt. And inputting the first wind power bolt data information into a first bolt fault identification support vector machine, and obtaining a training output result of the model, namely a first bolt fault characteristic, wherein the first bolt fault characteristic comprises an intensity fault characteristic, a connection fault characteristic, a material fault characteristic and the like. By classifying and identifying the fault data, the bolt fault data can be accurately and effectively obtained, and the accuracy and the effectiveness of the bolt data processing result can be further improved.
And step 211, inputting the first bolt fault characteristics into a deep convolutional neural network for training to construct a first wind power bolt evaluation model.
And 212, obtaining a second bolt fault feature of a second area, and inputting the second bolt fault feature into the deep convolutional neural network for distributed training to obtain a second wind power bolt evaluation model.
And 213, performing aggregate training on model parameters of the first wind power bolt evaluation model and the second wind power bolt evaluation model to obtain a wind power bolt comprehensive evaluation model.
And 214, obtaining a wind power bolt evaluation result according to the wind power bolt comprehensive evaluation model, and carrying out maintenance management on the wind turbine generator based on the wind power bolt evaluation result.
It should be noted that, the specific implementation manner of the steps 211 to 214 may refer to the above embodiment, and will not be described herein.
Therefore, the technical problems that the wind power bolt fault data acquisition and analysis are not timely and accurate enough in the prior art, so that the safety operation of the wind turbine generator is affected can be solved, the data utilization rate is improved by integrating and analyzing bolt data of a plurality of areas, the wind power bolt comprehensive evaluation model is constructed to timely process bolt faults, the accuracy and the instantaneity of bolt data processing results are improved, the supervision and management level of the wind turbine generator is further improved, the occurrence of safety accidents is diagnosed in advance, technical basis is provided for overhauling, reconstruction and supervision of related parts of bolts, and the safety operation technical effect of the wind turbine generator is guaranteed.
Fig. 3 is a schematic structural diagram of a federally learned wind power bolt data processing apparatus according to an embodiment of the present disclosure.
As shown in fig. 3, the federal learning-based wind power bolt data processing apparatus 300 includes:
a first obtaining module 310, configured to obtain first wind power bolt data information of a first area;
the uploading module 320 is configured to upload the data information of the first wind power bolt after the data desensitization to a wind power bolt analysis module;
the analysis module 330 is configured to perform fault identification analysis on the first wind power bolt data information based on the wind power bolt analysis module, so as to obtain a first bolt fault feature;
the construction module 340 is configured to input the first bolt fault feature into a deep convolutional neural network for training, so as to construct a first wind power bolt evaluation model;
the second obtaining module 350 is configured to obtain a second bolt fault feature of a second area, input the second bolt fault feature into the deep convolutional neural network, and perform distributed training to obtain a second wind power bolt evaluation model;
a third obtaining module 360, configured to perform aggregate training on model parameters of the first wind power bolt assessment model and the second wind power bolt assessment model, to obtain a wind power bolt comprehensive assessment model;
And the fourth obtaining module 370 is configured to obtain a wind power bolt evaluation result according to the wind power bolt comprehensive evaluation model, and perform maintenance management on the wind turbine generator based on the wind power bolt evaluation result.
Optionally, the analysis module includes:
the first acquisition unit is used for classifying the first wind power bolt data information based on a bolt characteristic decision tree to obtain bolt classification characteristic information;
the determining unit is used for determining a bolt calibration coefficient according to the bolt classification characteristic information;
the calling unit is used for calling a first bolt fault identification support vector machine from a bolt fault identification model library based on the bolt calibration coefficient;
the second acquisition unit is used for inputting the first wind power bolt data information into the first bolt fault identification support vector machine to obtain the first bolt fault characteristics.
Optionally, the calling unit is further configured to:
constructing a historical bolt data information base, wherein the historical bolt data information base comprises bolt data information of each calibration coefficient type;
clustering and dividing the data information in the historical bolt data information base to obtain a bolt clustering information result;
Carrying out category marking on the bolt clustering information result to obtain a marking training bolt data set;
and respectively taking the marking training bolt data set as input data according to the calibration coefficient categories to carry out support vector machine model training, and constructing the bolt fault identification model library.
Optionally, the first obtaining unit is further configured to:
obtaining a bolt mechanical specification attribute, and taking the bolt mechanical specification attribute as a first classification characteristic;
obtaining a bolt material grade attribute, and taking the bolt material grade attribute as a second classification characteristic;
obtaining a bolt application attribute, and taking the bolt application attribute as a third classification characteristic;
and constructing the bolt characteristic decision tree according to the first classification characteristic, the second classification characteristic and the third classification characteristic.
Optionally, the calling unit is further configured to:
obtaining a bolt measurement signal wave by an ultrasonic measurement method;
denoising and filtering the bolt measurement signal wave to obtain a standard bolt measurement signal wave;
performing characteristic analysis on the standard bolt measurement signal wave to obtain ultrasonic transit time;
and carrying out clustering division on the data information in the historical bolt data information base based on the ultrasonic transit time.
Optionally, the calling unit is further configured to:
inputting the ultrasonic transit time into an ultrasonic stress time difference formula, and calculating to obtain the axial stress of the bolt;
determining a bolt working state based on the bolt axial stress;
and when the axial stress of the bolt reaches a preset yield value, the working state of the bolt is warned to be a fault according to a first warning instruction.
In summary, the wind power bolt data information acquired in the acquisition area is subjected to data desensitization and then uploaded to the wind power bolt analysis module for fault identification analysis, the identified bolt fault characteristics are input into the deep convolutional neural network for training, a first wind power bolt evaluation model is built, the bolt fault characteristics of other areas are acquired in a similar way, the acquired second bolt fault characteristics are input into the deep convolutional neural network for distributed training, a second wind power bolt evaluation model is built, model parameters of the first wind power bolt evaluation model and model parameters of the second wind power bolt evaluation model are subjected to aggregation training, a wind power bolt comprehensive evaluation model is built, wind power bolt evaluation results are output according to the wind power bolt comprehensive evaluation model, and the wind power generation set is maintained and managed based on the wind power bolt evaluation results. And then, the bolt data of a plurality of areas are integrated and analyzed, the data utilization rate is improved, a wind power bolt comprehensive evaluation model is constructed to timely process bolt faults, the accuracy and the instantaneity of bolt data processing results are improved, the supervision and management level of the wind turbine generator set is further improved, the occurrence of safety accidents is prevented through advanced diagnosis, technical basis is provided for overhauling, reconstruction and supervision of related parts of the bolts, and the technical effect of safe operation of the wind turbine generator set is ensured.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
Fig. 4 illustrates a schematic block diagram of an example electronic device 400 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 4, the apparatus 400 includes a computing unit 401 that can perform various suitable actions and processes according to a computer program stored in a Read Only Memory (ROM) 402 or a computer program loaded from a storage unit 408 into a Random Access Memory (RAM) 403. In RAM 403, various programs and data required for the operation of device 400 may also be stored. The computing unit 401, ROM 402, and RAM 403 are connected to each other by a bus 404. An input/output (I/O) interface 405 is also connected to bus 404.
Various components in device 400 are connected to I/O interface 405, including: an input unit 406 such as a keyboard, a mouse, etc.; an output unit 407 such as various types of displays, speakers, and the like; a storage unit 408, such as a magnetic disk, optical disk, etc.; and a communication unit 409 such as a network card, modem, wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The computing unit 401 may be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 401 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 401 performs the various methods and processes described above, such as the federal learning-based wind turbine bolt data processing method. For example, in some embodiments, the federally learned wind turbine data processing method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 400 via the ROM 402 and/or the communication unit 409. When a computer program is loaded into RAM 403 and executed by computing unit 401, one or more of the steps of the federally learned wind turbine bolt data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the federally learned wind turbine data processing method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the description of the present application, those skilled in the art will appreciate that the present application may be embodied as methods, apparatus, electronic devices, and computer-readable storage media. Accordingly, the present application may be embodied in the following forms: complete hardware, complete software (including firmware, resident software, micro-code, etc.), a combination of hardware and software. Furthermore, in some embodiments, the application may also be embodied in the form of a computer program product in one or more computer-readable storage media, which contain computer program code.
Any combination of one or more computer-readable storage media may be employed by the computer-readable storage media described above. The computer-readable storage medium includes: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer readable storage medium include the following: portable computer magnetic disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disk read-only memories, optical storage devices, magnetic storage devices, or any combination thereof. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, device.
The technical scheme of the application obtains, stores, uses, processes and the like the data, which all meet the relevant regulations of national laws.
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-readable program instructions. These computer-readable 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, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service ("Virtual Private Server" or simply "VPS") are overcome. The server may also be a server of a distributed system or a server that incorporates a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (10)
1. A wind power bolt data processing method based on federal learning is characterized by comprising the following steps:
acquiring first wind power bolt data information of a first area;
uploading the data information of the first wind power bolt subjected to data desensitization to a wind power bolt analysis module;
performing fault identification analysis on the first wind power bolt data information based on the wind power bolt analysis module so as to obtain a first bolt fault characteristic;
Inputting the first bolt fault characteristics into a deep convolutional neural network for training to construct a first wind power bolt evaluation model;
obtaining a second bolt fault characteristic of a second area, and inputting the second bolt fault characteristic into the deep convolutional neural network for distributed training to obtain a second wind power bolt evaluation model;
performing aggregation training on model parameters of the first wind power bolt evaluation model and the second wind power bolt evaluation model to obtain a wind power bolt comprehensive evaluation model;
and obtaining a wind power bolt evaluation result according to the wind power bolt comprehensive evaluation model, and carrying out maintenance management on the wind turbine generator based on the wind power bolt evaluation result.
2. The method of claim 1, wherein performing a fault-recognition analysis on the first wind-powered bolt data information based on the wind-powered bolt analysis module to obtain a first bolt fault signature comprises:
classifying the first wind power bolt data information based on a bolt characteristic decision tree to obtain bolt classification characteristic information;
determining a bolt calibration coefficient according to the bolt classification characteristic information;
invoking a first bolt fault identification support vector machine from a bolt fault identification model library based on the bolt calibration coefficient;
And inputting the first wind power bolt data information into the first bolt fault identification support vector machine to obtain the first bolt fault characteristics.
3. The method of claim 2, further comprising, prior to said invoking the first bolt failure recognition support vector machine from the bolt failure recognition model library:
constructing a historical bolt data information base, wherein the historical bolt data information base comprises bolt data information of each calibration coefficient type;
clustering and dividing the data information in the historical bolt data information base to obtain a bolt clustering information result;
carrying out category marking on the bolt clustering information result to obtain a marking training bolt data set;
and respectively taking the marking training bolt data set as input data according to the calibration coefficient categories to carry out support vector machine model training, and constructing the bolt fault identification model library.
4. The method of claim 2, further comprising, prior to classifying the first wind power bolt data information based on the bolt feature decision tree to obtain bolt classification feature information:
obtaining a bolt mechanical specification attribute, and taking the bolt mechanical specification attribute as a first classification characteristic;
Obtaining a bolt material grade attribute, and taking the bolt material grade attribute as a second classification characteristic;
obtaining a bolt application attribute, and taking the bolt application attribute as a third classification characteristic;
and constructing the bolt characteristic decision tree according to the first classification characteristic, the second classification characteristic and the third classification characteristic.
5. The method of claim 3, wherein the clustering the data information in the historical bolt data information base to obtain a bolt cluster information result comprises:
obtaining a bolt measurement signal wave by an ultrasonic measurement method;
denoising and filtering the bolt measurement signal wave to obtain a standard bolt measurement signal wave;
performing characteristic analysis on the standard bolt measurement signal wave to obtain ultrasonic transit time;
and carrying out clustering division on the data information in the historical bolt data information base based on the ultrasonic transit time.
6. The method of claim 5, wherein the clustering the data information in the historical bolt data information base based on the ultrasonic transit time comprises:
inputting the ultrasonic transit time into an ultrasonic stress time difference formula, and calculating to obtain the axial stress of the bolt;
Determining a bolt working state based on the bolt axial stress;
and when the axial stress of the bolt reaches a preset yield value, the working state of the bolt is warned to be a fault according to a first warning instruction.
7. Wind power bolt data processing device based on federal study, characterized by comprising:
the first acquisition module is used for acquiring first wind power bolt data information of a first area;
the uploading module is used for uploading the data information of the first wind power bolt subjected to data desensitization to the wind power bolt analysis module;
the analysis module is used for carrying out fault identification analysis on the first wind power bolt data information based on the wind power bolt analysis module so as to obtain first bolt fault characteristics;
the construction module is used for inputting the first bolt fault characteristics into a deep convolutional neural network for training so as to construct a first wind power bolt evaluation model;
the second acquisition module is used for acquiring a second bolt fault characteristic of a second area, inputting the second bolt fault characteristic into the deep convolutional neural network for distributed training, and acquiring a second wind power bolt evaluation model;
the third acquisition module is used for performing aggregate training on model parameters of the first wind power bolt evaluation model and the second wind power bolt evaluation model to obtain a wind power bolt comprehensive evaluation model;
And the fourth acquisition module is used for acquiring a wind power bolt evaluation result according to the wind power bolt comprehensive evaluation model and carrying out maintenance management on the wind turbine generator based on the wind power bolt evaluation result.
8. The apparatus of claim 7, wherein the analysis module comprises:
the first acquisition unit is used for classifying the first wind power bolt data information based on a bolt characteristic decision tree to obtain bolt classification characteristic information;
the determining unit is used for determining a bolt calibration coefficient according to the bolt classification characteristic information;
the calling unit is used for calling a first bolt fault identification support vector machine from a bolt fault identification model library based on the bolt calibration coefficient;
the second acquisition unit is used for inputting the first wind power bolt data information into the first bolt fault identification support vector machine to obtain the first bolt fault characteristics.
9. The apparatus of claim 8, wherein the calling unit is further configured to:
constructing a historical bolt data information base, wherein the historical bolt data information base comprises bolt data information of each calibration coefficient type;
clustering and dividing the data information in the historical bolt data information base to obtain a bolt clustering information result;
Carrying out category marking on the bolt clustering information result to obtain a marking training bolt data set;
and respectively taking the marking training bolt data set as input data according to the calibration coefficient categories to carry out support vector machine model training, and constructing the bolt fault identification model library.
10. The apparatus of claim 8, wherein the first acquisition unit is further configured to:
obtaining a bolt mechanical specification attribute, and taking the bolt mechanical specification attribute as a first classification characteristic;
obtaining a bolt material grade attribute, and taking the bolt material grade attribute as a second classification characteristic;
obtaining a bolt application attribute, and taking the bolt application attribute as a third classification characteristic;
and constructing the bolt characteristic decision tree according to the first classification characteristic, the second classification characteristic and the third classification characteristic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211014503.5A CN116664096B (en) | 2022-08-23 | 2022-08-23 | Wind power bolt data processing method and device based on federal learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211014503.5A CN116664096B (en) | 2022-08-23 | 2022-08-23 | Wind power bolt data processing method and device based on federal learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116664096A true CN116664096A (en) | 2023-08-29 |
| CN116664096B CN116664096B (en) | 2024-02-13 |
Family
ID=87719423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211014503.5A Active CN116664096B (en) | 2022-08-23 | 2022-08-23 | Wind power bolt data processing method and device based on federal learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116664096B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069476A (en) * | 2015-08-10 | 2015-11-18 | 国网宁夏电力公司 | Method for identifying abnormal wind power data based on two-stage integration learning |
| CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
| CN108664010A (en) * | 2018-05-07 | 2018-10-16 | 广东省电信规划设计院有限公司 | Generating set fault data prediction technique, device and computer equipment |
| CN110378427A (en) * | 2019-07-23 | 2019-10-25 | 上海电气风电集团有限公司 | Fault detection method, system, equipment and the medium of the blade root bolt of wind electricity blade |
| US20200278240A1 (en) * | 2018-02-07 | 2020-09-03 | Dalian University Of Technology | Piezoelectric patch-based real-time and high-precision bolt preload detection method and system |
| CN114151293A (en) * | 2021-11-30 | 2022-03-08 | 甘肃中电瓜州风力发电有限公司 | Fault early warning method, system, equipment and storage medium of fan variable pitch system |
| CN114216640A (en) * | 2022-02-21 | 2022-03-22 | 蘑菇物联技术（深圳）有限公司 | Method, apparatus and medium for detecting fault status of industrial equipment |
| CN114331761A (en) * | 2022-03-15 | 2022-04-12 | 浙江万胜智能科技股份有限公司 | Equipment parameter analysis and adjustment method and system for special transformer acquisition terminal |
-
2022
- 2022-08-23 CN CN202211014503.5A patent/CN116664096B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069476A (en) * | 2015-08-10 | 2015-11-18 | 国网宁夏电力公司 | Method for identifying abnormal wind power data based on two-stage integration learning |
| CN107179503A (en) * | 2017-04-21 | 2017-09-19 | 美林数据技术股份有限公司 | The method of Wind turbines intelligent fault diagnosis early warning based on random forest |
| US20200278240A1 (en) * | 2018-02-07 | 2020-09-03 | Dalian University Of Technology | Piezoelectric patch-based real-time and high-precision bolt preload detection method and system |
| CN108664010A (en) * | 2018-05-07 | 2018-10-16 | 广东省电信规划设计院有限公司 | Generating set fault data prediction technique, device and computer equipment |
| CN110378427A (en) * | 2019-07-23 | 2019-10-25 | 上海电气风电集团有限公司 | Fault detection method, system, equipment and the medium of the blade root bolt of wind electricity blade |
| CN114151293A (en) * | 2021-11-30 | 2022-03-08 | 甘肃中电瓜州风力发电有限公司 | Fault early warning method, system, equipment and storage medium of fan variable pitch system |
| CN114216640A (en) * | 2022-02-21 | 2022-03-22 | 蘑菇物联技术（深圳）有限公司 | Method, apparatus and medium for detecting fault status of industrial equipment |
| CN114331761A (en) * | 2022-03-15 | 2022-04-12 | 浙江万胜智能科技股份有限公司 | Equipment parameter analysis and adjustment method and system for special transformer acquisition terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116664096B (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019080367A1 (en) | Method for evaluating health status of mechanical device | |
| CN109858104A (en) | A kind of rolling bearing health evaluating and method for diagnosing faults and monitoring system | |
| US10458416B2 (en) | Apparatus and method for monitoring a pump | |
| CN110688617B (en) | Fan vibration abnormity detection method and device | |
| CN110567388A (en) | Fault isolation and aircraft damage detection for automatic flight control surfaces by non-contact measurement | |
| JP2009288100A (en) | Soundness diagnosis method and program, and soundness diagnosis apparatus of windmill | |
| CN103939325B (en) | A kind of method for diagnosing faults of the fire pump under low-speed running | |
| CN111027594B (en) | Step-by-step anomaly detection method based on dictionary representation | |
| US12045047B2 (en) | Fault diagnostics systems and methods | |
| Song et al. | Data and decision level fusion-based crack detection for compressor blade using acoustic and vibration signal | |
| CN117980707A (en) | Autonomous discrimination of operational vibration signals | |
| Chen et al. | Acoustical damage detection of wind turbine yaw system using Bayesian network | |
| CN110990978A (en) | Bolt state monitoring method and device | |
| CN114002332A (en) | Structural damage monitoring and early warning method and structural integrity digital twinning system | |
| CN112712305A (en) | Aircraft system and health assessment method and device thereof | |
| You et al. | Signal anomaly identification strategy based on Bayesian inference for nuclear power machinery | |
| Ogaili et al. | Statistically optimal vibration feature selection for fault diagnosis in wind turbine blade | |
| CN116664096B (en) | Wind power bolt data processing method and device based on federal learning | |
| Zhou et al. | Modeling of wind turbine power curve based on Gaussian process | |
| CN114577470A (en) | Fault diagnosis method and system for fan main bearing | |
| Chen et al. | Early fault detection of rolling elememt bearings based on visibility graph modeling of vibration signals | |
| King et al. | Probabilistic approach to the condition monitoring of aerospace engines | |
| CN113504302B (en) | Method and system for monitoring fan blade state, electronic equipment and storage medium | |
| KR102212022B1 (en) | Method of automatically determining condition of hydro turbine in hydroelectric power plant and system for the same | |
| CN114993373A (en) | Aviation glass state monitoring method and device, computer equipment and medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |