CN117591962A - Defect detection model training, GIS equipment defect detection method and related device - Google Patents
Defect detection model training, GIS equipment defect detection method and related device Download PDFInfo
- Publication number
- CN117591962A CN117591962A CN202311559157.3A CN202311559157A CN117591962A CN 117591962 A CN117591962 A CN 117591962A CN 202311559157 A CN202311559157 A CN 202311559157A CN 117591962 A CN117591962 A CN 117591962A
- Authority
- CN
- China
- Prior art keywords
- defect detection
- mechanical vibration
- gis equipment
- detection model
- training
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 106
- 238000001514 detection method Methods 0.000 title claims abstract description 96
- 230000006870 function Effects 0.000 claims abstract description 67
- 239000011159 matrix material Substances 0.000 claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 26
- 230000005284 excitation Effects 0.000 claims abstract description 20
- 230000003044 adaptive effect Effects 0.000 claims abstract description 10
- 230000009467 reduction Effects 0.000 claims description 24
- 238000007637 random forest analysis Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 8
- 230000004044 response Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000005484 gravity Effects 0.000 claims description 7
- 241000254158 Lampyridae Species 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 abstract description 5
- 238000012544 monitoring process Methods 0.000 abstract 1
- 238000012216 screening Methods 0.000 abstract 1
- 238000000605 extraction Methods 0.000 description 7
- 230000009471 action Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000009466 transformation Effects 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a defect monitoring model training, GIS equipment defect detection method and a related device, which are applied to the field of GIS equipment mechanical defect detection, wherein the method adopts improved adaptive noise complete set empirical mode decomposition to conduct characteristic decomposition on GIS equipment mechanical vibration signals under variable frequency current excitation, and utilizes normalized mutual information calculation to conduct validity screening on eigenmode functions and achieve GIS equipment mechanical vibration signal reconstruction; and further extracting a characteristic matrix of the mechanical vibration signal of the reconstructed GIS equipment, and performing model training to obtain a defect detection model. According to the invention, the feature decomposition and the signal reconstruction of the GIS equipment mechanical vibration signal under the excitation of the variable-frequency current are realized through the modal decomposition and the normalized mutual information calculation, and the defect detection model is trained by extracting the features of the reconstructed GIS equipment mechanical vibration signal.
Description
Technical Field
The present invention relates to the field of mechanical defect detection of GIS devices, and in particular, to a defect detection model training method, a GIS device defect detection apparatus, an electronic device, and a computer readable storage medium.
Background
The gas-insulated metal-enclosed switchgear (Gas Insulated Switchgear, GIS) has the unique advantages of supporting high-voltage and large-capacity transmission of electric energy, being compact in structure, convenient to install and maintain and the like, and has become an important component of an electric power system. The mechanical defect is one of important factors causing the GIS equipment to fail, and the mechanical failure rate reaches 39.3% in the GIS equipment with the voltage level of more than 126 kV. GIS equipment has various mechanical faults, complex conditions and serious harm. The frequency conversion excitation vibration analysis method can excavate the inherent attribute of the mechanical structure and enhance the structural characteristic characterization and mechanical defect detection effect of the GIS equipment, but the existing study on the mechanical defect detection method of the GIS equipment is mostly based on power frequency current, the structural frequency response characteristic of the GIS equipment cannot be represented, and the mechanical defect detection accuracy rate of the GIS equipment under single frequency current is lower.
Disclosure of Invention
The invention aims to provide a defect detection model training method, a GIS equipment defect detection method and a related device, which are applied to the field of GIS equipment mechanical defect detection.
In order to solve the technical problems, the invention provides a defect detection model training method, which comprises the following steps:
acquiring a GIS equipment mechanical vibration signal under the excitation of variable frequency current;
performing modal decomposition on the GIS equipment mechanical vibration signal through an improved adaptive noise complete set empirical mode decomposition algorithm to obtain a plurality of intrinsic mode functions;
calculating normalized mutual information of the GIS equipment mechanical vibration signals and a plurality of eigenvalue functions;
removing false eigenmode functions in the eigenmode functions based on the normalized mutual information to obtain target eigenmode functions;
linearly superposing a plurality of target eigen mode functions to obtain a mechanical vibration signal of the reconstructed GIS equipment;
extracting the characteristics of the mechanical vibration signals of the reconstructed GIS equipment and a plurality of eigenvalue functions, and constructing a characteristic matrix based on the characteristics;
and training based on the feature matrix to obtain a defect detection model.
Optionally, the extracting the characteristics of the mechanical vibration signal of the reconstructed GIS device and the plurality of eigenmode functions includes:
extracting the amplitude, fundamental frequency amplitude, skewness index, kurtosis index, parity response ratio and vibration entropy of the mechanical vibration signal of the reconstructed GIS equipment;
and extracting the modal energy ratio and the modal gravity center ratio of a plurality of the eigenmode functions.
Optionally, the training based on the feature matrix to obtain a defect detection model includes:
training a random forest model based on the data set by taking the feature matrix as the data set;
and determining the trained random forest model as the defect detection model.
Optionally, the training random forest model based on the data set includes:
training the random forest model based on the data set, and searching optimized model parameters through a firefly algorithm in the training process.
Optionally, the training based on the feature matrix to obtain a defect detection model includes:
performing data dimension reduction on the feature matrix to obtain a dimension reduction feature matrix;
and training based on the dimension reduction feature matrix to obtain the defect detection model.
Optionally, the step of performing data dimension reduction on the feature matrix to obtain a dimension-reduced feature matrix includes:
and performing PCA dimension reduction on the feature matrix to obtain the dimension reduction feature matrix.
In order to solve the technical problems, the invention provides a GIS equipment defect detection method, which comprises the following steps:
acquiring a mechanical vibration signal of GIS equipment to be detected;
performing defect detection on the GIS equipment based on the defect detection model and the mechanical vibration signal of the GIS equipment to be detected;
the defect detection model is a model which is trained according to any defect detection model training method.
In order to solve the above technical problems, the present invention provides a device for training a defect detection model, comprising:
the first module is used for acquiring a GIS equipment mechanical vibration signal under the excitation of variable frequency current;
the second module is used for carrying out modal decomposition on the GIS equipment mechanical vibration signal through an improved adaptive noise complete set empirical mode decomposition algorithm to obtain a plurality of eigenmode functions;
the third module is used for calculating normalized mutual information of the GIS equipment mechanical vibration signals and the plurality of eigenvalue functions;
a fourth module, configured to remove a false eigenmode function in the eigenmode functions based on the normalized mutual information, so as to obtain a plurality of target eigenmode functions;
a fifth module, configured to linearly superimpose the multiple target eigen mode functions to obtain a mechanical vibration signal of the reconstructed GIS device;
a sixth module, configured to extract characteristics of the mechanical vibration signal of the reconstructed GIS device and a plurality of eigen mode functions, and construct a feature matrix based on the characteristics;
and a seventh module, configured to train to obtain a defect detection model based on the feature matrix.
In order to solve the above technical problems, the present invention provides an electronic device, including:
a memory for storing a computer program;
the processor is used for realizing the defect detection model training method according to any one of the above methods and/or the GIS equipment defect detection method when executing the computer program.
To solve the above technical problem, the present invention provides a computer readable storage medium, in which computer executable instructions are stored, which when executed by a processor, implement any one of the defect detection model training methods and/or the GIS device defect detection method.
Therefore, the method of the invention obtains the GIS equipment mechanical vibration signal under the excitation of variable frequency current; performing modal decomposition on the GIS equipment mechanical vibration signal through an improved adaptive noise complete set empirical mode decomposition algorithm to obtain a plurality of eigenmode functions; calculating normalized mutual information of the GIS equipment mechanical vibration signals and a plurality of eigenvalue functions; removing false eigenmode functions in the eigenmode functions based on the normalized mutual information to obtain target eigenmode functions; linearly superposing a plurality of target eigenmode functions to obtain a mechanical vibration signal of the reconstructed GIS equipment; extracting the characteristics of the mechanical vibration signals and the plurality of eigenmode functions of the reconstructed GIS equipment, and constructing a characteristic matrix based on the characteristics; and training based on the feature matrix to obtain a defect detection model, and performing defect detection on the GIS equipment based on the defect detection model and mechanical vibration signals of the GIS equipment to be detected. Compared with the prior art, the GIS mechanical defect detection method based on single power frequency current improves detection accuracy.
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 required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for training a defect detection model according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for detecting defects of GIS equipment according to an embodiment of the present invention;
fig. 3 is a block diagram of a training device for a defect detection model according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
Referring to fig. 1, fig. 1 is a flowchart of a defect detection model training method according to an embodiment of the present invention, where the method may include:
s101: and acquiring a GIS equipment mechanical vibration signal under the excitation of variable frequency current.
The frequency conversion excitation vibration analysis method is used as an advanced structural characteristic detection method, and can mine the inherent attribute of the mechanical structure, and enhance the structural characteristic characterization and the mechanical defect detection effect. The embodiment can acquire the mechanical vibration signal of the GIS equipment under the excitation of variable-frequency current, and the embodiment does not limit the frequency range of the current and the magnitude of the current. The embodiment can generally collect mechanical vibration signals of GIS equipment with voltage of 550kV, current frequency of 20Hz, 40Hz, 50Hz, 60Hz, 80Hz and 100Hz and excitation current of various defect states of 0-5000A, the embodiment is not limited to specific types of defect states, and four types of defects are generally represented most typically: the GIS equipment mechanical vibration signals under the four defect states can be collected by the aid of the method, namely, the normal bus base is loosened, the isolating switch spring piece is invalid, and the supporting frame bolt is loosened.
S102: and carrying out modal decomposition on the GIS equipment mechanical vibration signal through an improved adaptive noise complete set empirical mode decomposition algorithm to obtain a plurality of eigenmode functions.
According to the embodiment, the GIS equipment mechanical vibration signals can be subjected to modal decomposition (Improved Complete Ensemble EMD with Adaptive Noise, ICEEMDAN) through an improved adaptive noise complete set empirical mode decomposition algorithm to obtain a plurality of eigen mode functions (Intrinsic Mode Function, IMF), so that the GIS equipment mechanical vibration signals are decomposed.
S103: and calculating normalized mutual information of the GIS equipment mechanical vibration signals and the plurality of eigenmode functions.
S104: and removing false eigenmode functions in the eigenmode functions based on the normalized mutual information to obtain a plurality of target eigenmode functions.
S105: and linearly superposing the plurality of target eigenmode functions to obtain a mechanical vibration signal of the reconstructed GIS equipment.
According to the embodiment, normalized mutual information (Normalized Mutual Information, NMI) of the GIS equipment mechanical vibration signals and the plurality of eigenvalue functions can be calculated, the normalized mutual information is used for representing the similarity degree of 2 clustering results, and the validity evaluation can be carried out on the IMF obtained through decomposition through the normalized mutual information to eliminate false modes. The embodiment is not limited to a specific rejection mode, a threshold may be generally set, the eigenmode functions with normalized mutual information smaller than the threshold may be removed, the normalized mutual information obtained by calculation may be sorted, the eigenmode functions are removed according to a preset percentage, and the remaining eigenmode functions are target eigenmode functions.
In the embodiment, a plurality of target eigen mode functions can be linearly overlapped to obtain a reconstructed GIS equipment mechanical vibration signal, the reconstructed GIS equipment mechanical vibration signal eliminates false modes, and mode reconstruction and feature reinforcement of the GIS equipment mechanical vibration signal are realized.
S106: and extracting the characteristics of the mechanical vibration signals and the plurality of eigenmode functions of the reconstructed GIS equipment, and constructing a characteristic matrix based on the characteristics.
In this embodiment, characteristics of a mechanical vibration signal and a plurality of eigen mode functions of the reconstructed GIS device may be extracted, in this embodiment, the characteristic types of the signal may include a vibration amplitude indicator, a time domain statistics indicator, a frequency domain indicator and a mode domain indicator, the vibration amplitude indicator may include an amplitude characteristic and a fundamental frequency amplitude characteristic, the time domain statistics indicator may include a skewness indicator characteristic and a kurtosis indicator characteristic, the frequency domain indicator may include a parity response ratio characteristic and a vibration entropy characteristic, and the mode domain indicator may include a mode energy ratio characteristic and a mode gravity ratio characteristic.
The present embodiment is not limited to the extraction method of each feature, and the method of extracting the amplitude may be as follows:
y max ＝max(y(n))；
wherein y is max Y (n) is the time sequence of the mechanical vibration signal of the reconstructed GIS equipment, and n is the serial number of the sampling point.
The extraction method of the fundamental frequency amplitude can be as follows:
wherein A is base The fundamental frequency amplitude of the mechanical vibration signal of the reconstructed GIS equipment, p (f) is a frequency domain sequence obtained by Fourier transformation of the reconstructed vibration signal, f represents frequency, and f e Is the frequency of the excitation current.
The extraction mode of the skewness index can be as follows:
wherein S is the deviation index of the mechanical vibration signal of the reconstructed GIS equipment, N is the number of sampling points,for sigma y And reconstructing the average value of the time sequence of the mechanical vibration signals of the GIS equipment.
The kurtosis index can be extracted as follows:
wherein K is a kurtosis index of a mechanical vibration signal of the reconstructed GIS equipment.
The extraction method of the even response ratio can be shown as follows:
wherein R is the even response ratio of mechanical vibration signals of the reconstructed GIS equipment, f max Is the highest frequency of the frequency spectrum of the mechanical vibration signal of the GIS equipment.
The extraction mode of the vibration entropy can be as follows:
in the formula, H is the vibration entropy of the mechanical vibration signal of the reconstructed GIS equipment.
In this embodiment, the mode energy ratio may be extracted from a plurality of eigenmode functions, where the extraction manner may be as follows:
wherein E is harm For the mode energy ratio, p IMFk (f) For the frequency domain sequence of the k-th order mode IMFk in the plurality of eigenmode functions, k is preferably 2.
The mode of extraction of the modal gravity center ratio is as follows:
wherein G is harm Is the modal gravity center ratio.
According to the embodiment, the characteristic matrix can be constructed according to the characteristics of the mechanical vibration signals and the plurality of eigen mode functions of the reconstructed GIS equipment under the excitation of different variable-frequency currents, the specific form of the characteristic matrix is not limited, columns of the matrix can be current frequencies, and rows of the matrix can be characteristic types.
S107: and training based on the feature matrix to obtain a defect detection model.
In this embodiment, the feature matrix may be first subjected to data dimension reduction processing, so as to reduce the dimension of the data and improve the accuracy of the defect model obtained by training. The embodiment is not limited to a specific mode of performing data dimension reduction, and a feature matrix can be generally subjected to dimension reduction by adopting principal component analysis (Principal Component Analysis, PCA) to obtain a PCA dimension reduction matrix, and a high-dimension variable with correlation is projected into a low-dimension space through positive-negative conversion, so that a group of new linear independent feature variables is established, and a dimension reduction optimization feature matrix with better representativeness and smaller information overlap between dimensions is obtained while information loss is reduced as much as possible.
The embodiment does not limit the type of the defect detection model, and can be a random forest model generally, the embodiment can train the random forest model by taking the feature matrix in each defect state as a data set, and the trained random forest model is determined to be the defect detection model.
According to the embodiment of the invention, the feature decomposition and the signal reconstruction of the GIS equipment mechanical vibration signal under the excitation of the variable-frequency current are realized through the modal decomposition and the normalized mutual information calculation, and the defect detection model is trained through extracting the features of the reconstructed GIS equipment mechanical vibration signal.
Referring to fig. 2, fig. 2 is a flowchart of a method for detecting defects of GIS devices according to an embodiment of the present invention, where the method may include:
s201: acquiring a mechanical vibration signal of GIS equipment to be detected;
s202: performing defect detection on the GIS equipment based on the defect detection model and mechanical vibration signals of the GIS equipment to be detected;
the defect detection model is a model which is trained according to any defect detection model training method.
According to the embodiment, the mechanical vibration signals of the GIS equipment to be detected can be obtained, the defect detection of the GIS equipment can be carried out based on the defect detection model and the mechanical vibration signals of the GIS equipment to be detected, the feature matrix to be detected in the mechanical vibration signals of the GIS equipment to be detected can be extracted according to the mode of extracting the feature matrix from the mechanical vibration signals of the GIS equipment under the excitation of variable frequency current in the process of training the defect detection model, the feature matrix to be detected is input into the defect detection model trained according to any defect detection model training method, and the defect detection is carried out, so that a defect detection result is obtained.
The following is a specific embodiment provided by the embodiment of the present invention, where the GIS device is a 550kV real GIS device, and the specific embodiment may include:
setting the frequency of excitation current to be 20Hz, 40Hz, 50Hz, 60Hz, 80Hz and 100Hz, wherein the excitation current is 0-5000A;
taking a GIS equipment mechanical vibration signal of the same current with 6 frequency currents as 1 sample, and finally obtaining a source domain sample set containing 400 samples;
4 defect states are selected: normal, bus bar base loosening, isolation switch spring piece failure, support frame bolt loosening, each defect state containing 100 samples; wherein 20 samples are taken at 1000A, 2000A, 3000A, 4000A and 5000A currents, respectively;
carrying out ICEEMDAN decomposition on each sample to obtain a plurality of IMFs, removing false modes in the IMFs based on a normalized mutual information method, and carrying out linear superposition on the residual target IMFs to obtain reconstructed samples;
extracting amplitude, fundamental frequency amplitude, skewness index, kurtosis index, parity response ratio and vibration entropy in each reconstruction sample, extracting modal energy ratios and modal gravity center ratios of a plurality of IMFs, and constructing a feature matrix according to the extracted features;
performing PCA dimension reduction on the feature matrix to obtain a dimension reduction feature matrix, taking the dimension reduction feature matrix as a data set to train a random forest model, and performing parameter optimization by using a firefly algorithm in the training process;
and determining the trained random forest model as a defect detection model, acquiring a mechanical vibration signal of the GIS equipment to be detected, and performing defect detection of the GIS equipment based on the defect detection model and the mechanical vibration signal of the GIS equipment to be detected.
Referring to fig. 3, fig. 3 is a block diagram of a defect detection model training device according to an embodiment of the present invention, where the device may include:
a first module 100, configured to acquire a mechanical vibration signal of the GIS device under excitation of a variable frequency current;
the second module 200 is configured to perform modal decomposition on the GIS device mechanical vibration signal by using an improved adaptive noise complete set empirical mode decomposition algorithm, so as to obtain a plurality of eigen mode functions;
a third module 300, configured to calculate normalized mutual information of the mechanical vibration signal of the GIS device and a plurality of eigen mode functions;
a fourth module 400, configured to remove a false eigenmode function in the eigenmode functions based on the normalized mutual information, so as to obtain a plurality of target eigenmode functions;
a fifth module 500, configured to linearly superimpose a plurality of the target eigen-mode functions to obtain a mechanical vibration signal of the reconstructed GIS device;
a sixth module 600, configured to extract characteristics of the mechanical vibration signal of the reconstructed GIS device and a plurality of eigen-mode functions, and construct a feature matrix based on the characteristics;
and a seventh module 700, configured to train to obtain a defect detection model based on the feature matrix.
Based on the embodiment, the method realizes the characteristic decomposition and signal reconstruction of the GIS equipment mechanical vibration signal under the excitation of the variable frequency current through the modal decomposition and the normalized mutual information calculation, and improves the detection precision compared with the detection of the GIS mechanical defect based on single power frequency current in the prior art through extracting the characteristic training defect detection model of the reconstructed GIS equipment mechanical vibration signal.
Based on the above embodiment, the sixth module 600 may include:
the first unit is used for extracting the amplitude, the fundamental frequency amplitude, the skewness index, the kurtosis index, the parity response ratio and the vibration entropy of the mechanical vibration signal of the reconstructed GIS equipment;
and the second unit is used for extracting the modal energy ratio and the modal gravity center ratio of the plurality of the eigenmode functions.
Based on the above embodiments, the seventh module 700 may include:
a third unit for training a random forest model based on the data set by taking the feature matrix as the data set;
and a fourth unit, configured to determine the trained random forest model as the defect detection model.
Based on the above embodiments, the third unit may include:
the first subunit trains the random forest model based on the data set in language, and searches optimized model parameters through a firefly algorithm in the training process.
Based on the above embodiments, the seventh module 700 may include:
a fifth unit, configured to perform data dimension reduction on the feature matrix to obtain a dimension-reduced feature matrix;
and a sixth unit, configured to train to obtain the defect detection model based on the dimension reduction feature matrix.
Based on the above embodiments, the fifth unit includes:
and the second subunit is used for performing PCA dimension reduction on the feature matrix to obtain the dimension reduction feature matrix.
The following is a defect detection device for a GIS device provided by the embodiment of the present invention, where the device may include:
an eighth module, configured to obtain a mechanical vibration signal of the GIS device to be detected;
a ninth module, configured to perform defect detection on the GIS device based on the defect detection model and the mechanical vibration signal of the GIS device to be detected;
the defect detection model is a model which is trained according to any defect detection model training device.
Based on the above embodiment, the present invention further provides an electronic device, where the device may include a memory and a processor, where the memory stores a computer program, and the processor may implement the steps provided in the above embodiment when calling the computer program in the memory. Of course, the device may also include various necessary network interfaces, power supplies, and other components, etc.
The invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by an execution terminal or a processor can implement the method provided by the embodiment of the invention; the storage medium may include: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing has described in detail a defect detection model training, a method for detecting defects of a GIS device and related devices, and specific examples are applied to illustrate the principles and embodiments of the present invention, and the above description of the examples is only for helping to understand the method and core ideas of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. A method for training a defect detection model, comprising:
acquiring a GIS equipment mechanical vibration signal under the excitation of variable frequency current;
performing modal decomposition on the GIS equipment mechanical vibration signal through an improved adaptive noise complete set empirical mode decomposition algorithm to obtain a plurality of intrinsic mode functions;
calculating normalized mutual information of the GIS equipment mechanical vibration signals and a plurality of eigenvalue functions;
removing false eigenmode functions in the eigenmode functions based on the normalized mutual information to obtain target eigenmode functions;
linearly superposing a plurality of target eigen mode functions to obtain a mechanical vibration signal of the reconstructed GIS equipment;
extracting the characteristics of the mechanical vibration signals of the reconstructed GIS equipment and a plurality of eigenvalue functions, and constructing a characteristic matrix based on the characteristics;
and training based on the feature matrix to obtain a defect detection model.
2. The method of claim 1, wherein extracting the characteristics of the reconstructed GIS device mechanical vibration signal and the plurality of eigenmode functions comprises:
extracting the amplitude, fundamental frequency amplitude, skewness index, kurtosis index, parity response ratio and vibration entropy of the mechanical vibration signal of the reconstructed GIS equipment;
and extracting the modal energy ratio and the modal gravity center ratio of a plurality of the eigenmode functions.
3. The method for training a defect detection model according to claim 1, wherein the training based on the feature matrix to obtain the defect detection model comprises:
training a random forest model based on the data set by taking the feature matrix as the data set;
and determining the trained random forest model as the defect detection model.
4. A method of training a defect detection model as claimed in claim 3, wherein said training a random forest model based on said data set comprises:
training the random forest model based on the data set, and searching optimized model parameters through a firefly algorithm in the training process.
5. The method for training a defect detection model according to claim 1, wherein the training based on the feature matrix to obtain the defect detection model comprises:
performing data dimension reduction on the feature matrix to obtain a dimension reduction feature matrix;
and training based on the dimension reduction feature matrix to obtain the defect detection model.
6. The method for training a defect detection model according to claim 5, wherein the step of performing data dimension reduction on the feature matrix to obtain a dimension-reduced feature matrix comprises:
and performing PCA dimension reduction on the feature matrix to obtain the dimension reduction feature matrix.
7. The GIS equipment defect detection method is characterized by comprising the following steps of:
acquiring a mechanical vibration signal of GIS equipment to be detected;
performing defect detection on the GIS equipment based on the defect detection model and the mechanical vibration signal of the GIS equipment to be detected;
wherein the defect detection model is a model trained according to the defect detection model training method of any one of claims 1 to 6.
8. A defect detection model training device, comprising:
the first module is used for acquiring a GIS equipment mechanical vibration signal under the excitation of variable frequency current;
the second module is used for carrying out modal decomposition on the GIS equipment mechanical vibration signal through an improved adaptive noise complete set empirical mode decomposition algorithm to obtain a plurality of eigenmode functions;
the third module is used for calculating normalized mutual information of the GIS equipment mechanical vibration signals and the plurality of eigenvalue functions;
a fourth module, configured to remove a false eigenmode function in the eigenmode functions based on the normalized mutual information, so as to obtain a plurality of target eigenmode functions;
a fifth module, configured to linearly superimpose the multiple target eigen mode functions to obtain a mechanical vibration signal of the reconstructed GIS device;
a sixth module, configured to extract characteristics of the mechanical vibration signal of the reconstructed GIS device and a plurality of eigen mode functions, and construct a feature matrix based on the characteristics;
and a seventh module, configured to train to obtain a defect detection model based on the feature matrix.
9. An electronic device, comprising:
a memory for storing a computer program;
processor for implementing the defect detection model training method according to any one of claims 1 to 6 and/or the GIS device defect detection method according to claim 7 when executing the computer program.
10. A computer readable storage medium, wherein computer executable instructions are stored in the computer readable storage medium, and when executed by a processor, the computer executable instructions implement the defect detection model training method according to any one of claims 1 to 6, and/or the GIS device defect detection method according to claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311559157.3A CN117591962A (en) | 2023-11-21 | 2023-11-21 | Defect detection model training, GIS equipment defect detection method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311559157.3A CN117591962A (en) | 2023-11-21 | 2023-11-21 | Defect detection model training, GIS equipment defect detection method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117591962A true CN117591962A (en) | 2024-02-23 |
Family
ID=89909452
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311559157.3A Pending CN117591962A (en) | 2023-11-21 | 2023-11-21 | Defect detection model training, GIS equipment defect detection method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117591962A (en) |
-
2023
- 2023-11-21 CN CN202311559157.3A patent/CN117591962A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lee et al. | New fault diagnosis of circuit breakers | |
| Yu et al. | A novel sensor fault diagnosis method based on modified ensemble empirical mode decomposition and probabilistic neural network | |
| CN110926778B (en) | Mechanical fault diagnosis method for gas insulated switchgear assembly based on abnormal vibration | |
| CN108761287B (en) | Transformer partial discharge type identification method | |
| CN109633368A (en) | The method of duration power quality disturbances containing distributed power distribution network based on VMD and DFA | |
| CN111239263B (en) | Method and system for detecting foreign matter defects in GIS equipment | |
| CN101614786A (en) | Power electronic circuit on-line intelligence method for diagnosing faults based on FRFT and IFSVC | |
| CN110068759A (en) | A kind of fault type preparation method and device | |
| Zhao et al. | Fault diagnosis of circuit breaker energy storage mechanism based on current-vibration entropy weight characteristic and grey wolf optimization–support vector machine | |
| CN109470985A (en) | A kind of voltage sag source identification methods based on more resolution singular value decompositions | |
| CN112816838B (en) | GIS equipment defect diagnosis device and method based on FFT, VMD and LS-SVM | |
| Koley et al. | Wavelet-aided SVM tool for impulse fault identification in transformers | |
| CN112147444A (en) | Power transformer working state monitoring method and system | |
| Jena et al. | Variational mode decomposition‐based power system disturbance assessment to enhance WA situational awareness and post‐mortem analysis | |
| CN113391244A (en) | VMD-based transformer switching-on vibration signal characteristic frequency calculation method | |
| CN113379252A (en) | Bayesian network high-voltage switch cabinet health system evaluation method based on multi-scale arrangement entropy | |
| CN111079647A (en) | Circuit breaker defect identification method | |
| CN113671037A (en) | Post insulator vibration acoustic signal processing method | |
| Ray et al. | Frequency mode identification using modified masking signal‐based empirical mode decomposition | |
| CN117591962A (en) | Defect detection model training, GIS equipment defect detection method and related device | |
| CN110703080B (en) | GIS spike discharge diagnosis method, discharge degree identification method and device | |
| CN114417929A (en) | GIS equipment nonlinear vibration behavior analysis method and system | |
| Otudi et al. | Training Machine Learning Models with Simulated Data for Improved Line Fault Events Classification From 3-Phase PMU Field Recordings | |
| Liu et al. | Underdetermined blind source separation algorithm of 220kV substation noise based on SCA | |
| Shang et al. | Mechanical fault diagnosis system based on acoustic feature analysis in gas insulated switchgear |
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 |