CN114238368A - Transformer fault diagnosis method and device, computer equipment and readable storage medium - Google Patents
Transformer fault diagnosis method and device, computer equipment and readable storage medium Download PDFInfo
- Publication number
- CN114238368A CN114238368A CN202111485317.5A CN202111485317A CN114238368A CN 114238368 A CN114238368 A CN 114238368A CN 202111485317 A CN202111485317 A CN 202111485317A CN 114238368 A CN114238368 A CN 114238368A
- Authority
- CN
- China
- Prior art keywords
- transformer
- actual
- operation data
- fault
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000003745 diagnosis Methods 0.000 title claims abstract description 36
- 238000003860 storage Methods 0.000 title claims description 11
- 238000004519 manufacturing process Methods 0.000 claims abstract description 44
- 238000001514 detection method Methods 0.000 claims abstract description 14
- 239000011159 matrix material Substances 0.000 claims description 68
- 238000012545 processing Methods 0.000 claims description 63
- 238000009826 distribution Methods 0.000 claims description 40
- 238000001228 spectrum Methods 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 22
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000009877 rendering Methods 0.000 claims description 8
- 230000003595 spectral effect Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 description 7
- 230000011218 segmentation Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/242—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Mathematical Physics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application relates to a transformer fault diagnosis method and a device, wherein the method comprises the following steps: obtaining target operation data of each fault-free transformer; target operation data is built in a fault-free model database; acquiring actual operation data of a transformer to be detected; the actual operation data comprises actual load frequency, actual sound production points and actual sound intensity characteristics; searching a fault-free model database based on the actual load frequency to obtain target operation data corresponding to the actual load frequency; the fault information of the transformer to be detected is output according to the target operation data, the actual sound production point and the actual sound intensity characteristic corresponding to the actual load frequency, a large amount of time and energy are not consumed, whether the transformer has a fault or not can be diagnosed only through the noise emitted by the transformer, the detection efficiency is high, the detection result is accurate, and the method has important significance for guaranteeing the safety, the reliability and the economy of the operation of the power system.
Description
Technical Field
The present application relates to the field of fault diagnosis technologies, and in particular, to a transformer fault diagnosis method and apparatus, a computer device, and a readable storage medium.
Background
With the development of power systems, the safety of power systems is receiving more and more attention. The power transformer is one of the main devices of the power system, and directly affects the production safety and economic benefit of the power system. Therefore, the power transformer fault is timely detected and effective maintenance measures are taken, and the method has important significance for guaranteeing the safety, reliability and economy of the operation of a power system.
However, the conventional processing method requires manual work to go to the place to be excluded, and relies on manual experience to diagnose whether the transformer is faulty or not according to the noise emitted from the transformer. The method not only needs to consume a great deal of time and energy, but also is interfered by human factors, and fault diagnosis is possible to be wrong.
Disclosure of Invention
In view of the above, it is necessary to provide a transformer fault diagnosis method, apparatus, computer device and readable storage medium for solving the above technical problems.
A transformer fault diagnosis method comprises the following steps:
acquiring target operation data of each fault-free transformer;
target operation data is built in a fault-free model database;
acquiring actual operation data of a transformer to be detected; the actual operation data comprises actual load frequency, actual sound production points and actual sound intensity characteristics;
searching a fault-free model database based on the actual load frequency to obtain target operation data corresponding to the actual load frequency;
and outputting fault information of the transformer to be detected according to the target operation data corresponding to the actual load frequency, the actual sound production point and the actual sound intensity characteristic.
In one embodiment, the step of acquiring actual operation data of the transformer to be detected comprises:
scaling the transformer to be detected into a virtual model in an equal proportion;
carrying out lightweight processing on the virtual model to obtain a lightweight model;
rendering the lightweight model to obtain a digital twin model of the transformer to be detected;
and monitoring the digital twin model to obtain actual operation data.
In one embodiment, the step of obtaining target operation data of each fault-free transformer includes:
acquiring target load frequency and audio data of each fault-free transformer;
establishing distribution characteristic data of the fault-free transformer noise under each target load frequency according to the audio data;
and processing the distribution characteristic data to obtain target operation data.
In one embodiment, the step of establishing distribution characteristic data of the fault-free transformer noise at each target load frequency according to the audio data comprises:
segmenting the audio data under each target load frequency to obtain segmented data;
carrying out Fourier transform on each segmentation data to obtain frequency domain data;
processing the frequency domain data to obtain a cross-spectrum density matrix;
processing the cross-spectrum density matrix to obtain a signal subspace matrix and a noise subspace matrix;
obtaining an MUSIC spatial spectrum according to the signal subspace matrix and the noise subspace matrix;
carrying out spectrum peak search on the MUSIC space spectrum to obtain the direction of arrival angle of the signal;
and performing beam forming processing on the direction of arrival angle to obtain distribution characteristic data.
In one embodiment, the step of processing the distribution characteristic data to obtain the target operation data includes:
carrying out dimensionless processing on the distribution characteristic data to obtain dimensionless data;
carrying out standardization processing on the dimensionless data to obtain a standardized matrix;
obtaining a correlation coefficient matrix according to the standardized matrix;
processing the correlation coefficient matrix to obtain a main characteristic value;
and determining the product of the main eigenvalue and the eigenvector corresponding to the main eigenvalue as target operation data.
In one embodiment, the target operation data comprises a target load frequency, a target sound emitting point and a target sound intensity characteristic; the method comprises the following steps of outputting fault information of the transformer to be detected according to target operation data corresponding to the actual load frequency, an actual sound production point and actual sound intensity characteristics, wherein the steps comprise:
calculating a first proportional value of the number of the actual sound production points and the number of the target sound production points;
calculating a second proportional value of the actual sound intensity characteristic and the target sound intensity characteristic;
and outputting fault information under the condition that the first proportion value is larger than a first preset proportion value and/or the second proportion value is larger than the first preset proportion value.
In one embodiment, the step of outputting the fault information of the transformer to be detected according to the target operation data corresponding to the actual load frequency, the actual sound-emitting point and the actual sound intensity characteristic further includes:
under the condition that the first proportion value is larger than a first preset proportion value and/or the second proportion value is larger than a second preset proportion value, alarm information is output; wherein, the second preset proportion value is smaller than the first preset proportion value.
A transformer fault diagnosis apparatus comprising:
the target operation data acquisition module is used for acquiring target operation data of each fault-free transformer;
the database establishing module is used for internally arranging the target operation data in the fault-free model database;
the actual operation data acquisition module is used for acquiring actual operation data of the transformer to be detected; the actual operation data comprises actual load frequency, actual sound production points and actual sound intensity characteristics;
the target operation data searching module is used for searching the fault-free model database based on the actual load frequency to obtain target operation data corresponding to the actual load frequency;
and the fault detection module is used for outputting fault information of the transformer to be detected according to the target operation data, the actual sound production point and the actual sound intensity characteristic corresponding to the actual load frequency.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method when the processor executes the computer program.
A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method.
According to the transformer fault diagnosis method, target operation data of each fault-free transformer are obtained; target operation data is built in a fault-free model database; acquiring actual operation data of a transformer to be detected; the actual operation data comprises actual load frequency, actual sound production points and actual sound intensity characteristics; searching a fault-free model database based on the actual load frequency to obtain target operation data corresponding to the actual load frequency; and outputting fault information of the transformer to be detected according to the target operation data corresponding to the actual load frequency, the actual sound production point and the actual sound intensity characteristic. The method can monitor the actual sound production point and the actual sound intensity characteristic of the transformer to be detected in real time, obtains the detection result by comparing the actual sound production point and the actual sound intensity characteristic with the target operation data, does not need to consume a large amount of time and energy, can diagnose whether the transformer has a fault only through the noise emitted by the transformer, has high detection efficiency and accurate detection result, and has important significance for guaranteeing the safety, the reliability and the economy of the operation of the power system.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments or the conventional technologies of the present application, the drawings used in the descriptions of the embodiments or the conventional technologies will be briefly introduced below, it is obvious that the drawings in the following descriptions are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a transformer fault diagnosis method according to an embodiment;
FIG. 2 is a flowchart illustrating steps of obtaining actual operational data of a transformer to be tested according to one embodiment;
FIG. 3 is a flowchart illustrating steps for obtaining target operational data for each fault-free transformer in one embodiment;
FIG. 4 is a flowchart illustrating the steps for establishing distribution characterization data of fault-free transformer noise at various target load frequencies based on audio data according to one embodiment;
FIG. 5 is a flowchart illustrating the steps of processing distributed signature data to obtain target operational data according to one embodiment;
fig. 6 is a flowchart illustrating steps of outputting fault information of the transformer to be detected according to target operation data, an actual sound emission point, and an actual sound intensity characteristic corresponding to an actual load frequency in one embodiment.
Detailed Description
To facilitate an understanding of the present application, the present application will now be described more fully with reference to the accompanying drawings. Embodiments of the present application are set forth in the accompanying drawings. This application may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
It is to be understood that, as used herein, the terms "a", "an" and "the" can also include the plural form unless the context clearly dictates otherwise. It will be further understood that the terms "comprises/comprising," "includes" or "including," etc., specify the presence of stated features, integers, steps, operations, components, parts, or combinations thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, components, parts, or combinations thereof. Also, as used in this specification, the term "and/or" includes any and all combinations of the associated listed items.
In recent years, with the development of electric power utilities, people are receiving more attention to the damage caused by vibration noise. When the transformer fails, vibration is generated, noise is generated due to the vibration, and important information of the working state is contained in the noise. By collecting the noise signals and carrying out a series of fault diagnosis methods such as time domain and frequency domain processing on the noise signals, the faults of the transformer can be well reflected and the health condition of the transformer can be well predicted. At the present stage, the research on transformer fault diagnosis in China is still in a starting stage, and because noise signals show different characteristics in different running states, the distribution rule of noise is difficult to accurately analyze through theoretical calculation.
The early noise imaging technology mostly adopts a single-channel data acquisition method according to the vibration test idea and applies a vibration test analysis means and idea to process noise signals. These methods can have some effect on analyzing and processing simple faults, but in practice, a plurality of noise sources interfere with each other, and in this case, a good effect is difficult to produce.
In view of this, the invention provides a transformer fault diagnosis method, a diagnosis device, a computer device and a readable storage medium, which can visually display the distribution of fault points, are simple and practical, and can be used for live detection to well find potential defects and faults of a transformer and avoid equipment accidents.
In one embodiment, as shown in fig. 1, there is provided a transformer fault diagnosis method, including the steps of:
s110, acquiring target operation data of each fault-free transformer;
specifically, the fault-free transformer is a transformer which normally operates, and the parameters of the transformer are in a reasonable range; the target operation data is operation data of the fault-free transformer, such as load frequency, sound emission point and sound intensity characteristic of the fault-free transformer.
Specifically, first, load frequency and noise audio data of a fault-free transformer are obtained, and since the load frequency of the fault-free transformer is different and the noise audio data thereof is also different, target operation data of a plurality of fault-free transformers needs to be obtained, that is, the target operation data is operation data of all fault-free transformers, and the target operation data may be obtained by any method in the art, which is not limited herein. Secondly, the noise audio data is processed to obtain target operation data, and preferably, the noise audio data can be processed by adopting methods such as mean, variance and the like to obtain the target operation data.
S120, embedding the target operation data in a fault-free model database;
specifically, in the fault-free model database, the target operation data of each fault-free transformer is stored in a one-to-one correspondence manner, for example, the load frequency of the transformer 1 is stored in correspondence with the noise data of the transformer 1, and the load frequency of the transformer 2 is stored in correspondence with the noise data of the transformer 2; the database of the fault-free model is a relational database management system (Microsoft Office Access, referred to as Access database for short), so that a graphical user interface of a database engine and a software development tool are combined together, and the user can conveniently check the database. Specifically, the extracted target operation data is stored in the host, and the target operation data is built in the fault-free model database by utilizing the SQL language, so that the method is simple and convenient, and the efficiency of transformer fault diagnosis is improved.
The fault-free model database can also be an SQLite database, in practical application, power equipment monitoring systems in different regions are different, and the SQLite database can support mainstream operating systems such as Windows/Linux/Unix and the like and is suitable for different field environments. Specifically, target operation data can be stored in the SQLite database by using programming languages such as C #, PHP and Java, and the diagnosis efficiency of the transformer is improved by using the high processing speed of the SQLite database.
S130, acquiring actual operation data of the transformer to be detected; the actual operation data comprises actual load frequency, actual sound production points and actual sound intensity characteristics;
specifically, the actual operation data is data of the transformer to be detected when the transformer works normally; specifically, the actual operation data of the transformer to be detected can be obtained by adopting an audio sensor, or the actual operation data of the transformer to be detected can be obtained by adopting a digital twin method, as long as the operation data of the transformer to be detected can be obtained.
S140, searching a fault-free model database based on the actual load frequency to obtain target operation data corresponding to the actual load frequency;
specifically, the actual load rate of the transformer to be detected is obtained, and since the target load frequency and other target operation data of each transformer without fault are stored in the fault model database in a one-to-one correspondence manner, the target operation data with the target load frequency and the actual load frequency of the transformer without fault being equal is found, that is, the target operation data corresponding to the actual load frequency of the transformer to be detected is obtained.
Specifically, according to the difference of the fault-free model database, the fault-free model database is searched by adopting a corresponding programming language. For example, when the non-fault model database is the Access database, the non-fault model database is searched by using the SQL programming language to obtain the target operation data corresponding to the actual load frequency.
And S150, outputting fault information of the transformer to be detected according to the target operation data, the actual sound production point and the actual sound intensity characteristic corresponding to the actual load frequency.
Specifically, after the fault-free model database is searched based on the actual load frequency, and the target operation data corresponding to the actual load frequency is obtained, the target operation data is compared with the actual sound production point and the actual sound intensity characteristic of the transformer to be detected, so that a comparison result is obtained, fault information can be output according to the comparison result of the actual sound production point and the target operation data, fault information can also be output according to the comparison result of the actual sound intensity characteristic and the target operation data, and alarm information can also be output according to the comparison result to remind a worker of the transformer to be detected of faults.
According to the transformer fault diagnosis method, target operation data of each fault-free transformer are obtained; target operation data is built in a fault-free model database; acquiring actual operation data of a transformer to be detected; the actual operation data comprises actual load frequency, actual sound production points and actual sound intensity characteristics; searching a fault-free model database based on the actual load frequency to obtain target operation data corresponding to the actual load frequency; and outputting fault information of the transformer to be detected according to the target operation data corresponding to the actual load frequency, the actual sound production point and the actual sound intensity characteristic. The method can monitor the actual sound production point and the actual sound intensity characteristic of the transformer to be detected in real time, obtains the detection result through comparison with the target operation data, does not need to consume a large amount of time and energy, can diagnose whether the transformer has faults or not only through the noise emitted by the transformer, and is high in detection efficiency and accurate in detection result.
In one embodiment, as shown in fig. 2, the step of acquiring actual operation data of the transformer to be detected includes:
s160, scaling the transformer to be detected into a virtual model in an equal proportion;
s170, carrying out lightweight processing on the virtual model to obtain a lightweight model;
s180, rendering the lightweight model to obtain a digital twin model of the transformer to be detected;
and S190, monitoring the digital twin model to obtain actual operation data.
In particular, the virtual model is a three-dimensional model. There is provided a method of monitoring operational data of a transformer to be detected using a digital twin approach. Specifically, SolidWorks software is used for scaling the transformer to be detected into a virtual model in an equal proportion mode and carrying out lightweight processing on the virtual model to obtain a lightweight model, then 3DMax software is used for carrying out rendering processing on the lightweight model to obtain a digital twin model of the transformer to be detected, the digital twin model is monitored, and actual operation data are obtained. The method can construct a virtual entity representing the real-time running state of the entity transformer in a virtual space, has all-round functions of integrating geometric modeling, simulation and data analysis, and can feed back the running state of the physical world transformer through real-time connection, mapping, analysis and feedback. Digital twins rely on digital threads in the process of integrating converged industrial data. The digital thread is a channel connecting the physical world and the digital twin, and is also a channel connecting various types of digital twins, and has a function of pushing correct information to a correct place in a correct manner at a correct time. In summary, the digital twinning method can accurately connect and map the physical-level transformers to the digital level, thereby facilitating the diagnosis and analysis of transformer faults.
In one embodiment, as shown in fig. 3, the step of obtaining target operation data of each fault-free transformer includes:
s200, acquiring target load frequency and audio data of each fault-free transformer;
specifically, the transformer may generate vibration during operation, the vibration may generate noise, the noise contains important information of the operating state, and the audio data is noise data generated by the vibration of the fault-free transformer during operation. The target load rate is the load frequency of the fault-free transformer in the normal working process.
S210, establishing distribution characteristic data of the fault-free transformer noise under each target load frequency according to the audio data;
specifically, since the audio data of the transformers with different load frequencies are different, the audio data needs to be processed under different load frequencies to establish the distribution characteristic data of the noise of each fault-free transformer. The distribution characteristic data is data including a sound emission point and a sound intensity characteristic.
Specifically, the audio data is usually interfered by other noise in the environment during the acquisition process, and other noise interference signals are mixed. The acoustic signal generated by the transformer is generally a one-dimensional signal and usually represents a relatively stable low-frequency signal, while the noise interference in the environment is mainly a pulse-like high-frequency unstable signal. Therefore, it is necessary to select a proper method to perform noise reduction processing on the audio data, so as to eliminate the influence of noise interference in the environment on the audio data and make the fault diagnosis result more accurate.
And S220, processing the distribution characteristic data to obtain target operation data.
Specifically, the target operation data comprises sound production points and sound intensity characteristics, and specifically, the target operation data in the distributed characteristic data can be extracted by a characteristic decomposition method.
In one embodiment, as shown in fig. 4, the step of establishing the distribution characteristic data of the fault-free transformer noise at each target load frequency according to the audio data includes:
s230, segmenting the audio data under each target load frequency to obtain segmented data;
s240, carrying out Fourier transform on each piece of divided data to obtain frequency domain data;
s250, processing the frequency domain data to obtain a cross-spectral density matrix;
s260, processing the cross-spectrum density matrix to obtain a signal subspace matrix and a noise subspace matrix;
s270, obtaining an MUSIC spatial spectrum according to the signal subspace matrix and the noise subspace matrix;
s280, performing spectral peak search on the MUSIC spatial spectrum to obtain the direction of arrival angle of the signal;
specifically, the audio data is denoised by using a MUSIC (multiple Signal classification) algorithm, which is a spatial spectrum estimation algorithm, and is a method for performing feature decomposition on a covariance matrix of received data, separating a Signal subspace and a noise subspace, forming a MUSIC spatial spectrum by utilizing orthogonality of a Signal direction vector and the noise subspace, and further performing spectral peak search on the MUSIC spatial spectrum to estimate a direction of arrival angle of the Signal. The MUSIC algorithm has high direction finding resolution, can carry out asymptotic unbiased estimation on the direction of arrival of the sound signal, and ensures the accuracy of the transformer fault diagnosis result.
And S290, performing beam forming processing on the direction of arrival angle to obtain distribution characteristic data.
Specifically, the Linear Constrained Minimum Variance (LCMV) criterion is used here to advance the direction of arrivalOptimizing the line beam forming, specifically, calculating the weight w in the search range of the direction of arrival angle by using a linear constraint minimum variance criterion, and then drawing a spectrum function N (w) ═ wHAnd Rw and R are covariance matrixes, and then the covariance matrixes are subjected to spectral peak search to obtain distribution characteristic data.
In one embodiment, as shown in fig. 5, the step of processing the distribution characteristic data to obtain the target operation data includes:
s300, carrying out dimensionless processing on the distribution characteristic data to obtain dimensionless data;
specifically, the distribution characteristic data is processed by an extremum method to obtain dimensionless data. For example, dimensionless data is obtained based on the following formula:
dimensionless evaluation indicators can also be obtained based on the following formula:
in the formula, YkFor distributing the feature data, k denotes the k-th item of data, YkmaxAnd YkminRespectively the maximum and minimum values of the data,
i.e. dimensionless data.
S310, normalizing the dimensionless data to obtain a normalized matrix B ═ (B)ij)n×p；
S320, obtaining a correlation coefficient matrix according to the standardized matrix;
specifically, the correlation coefficient matrix is formed by the correlation coefficients after matrix normalization, and the correlation coefficient matrix R is:
wherein r isijCov is the covariance, as the correlation coefficient.
S330, processing the correlation coefficient matrix to obtain a main characteristic value;
and S340, determining the product of the main eigenvalue and the eigenvector corresponding to the main eigenvalue as target operation data.
Specifically, the correlation coefficient matrix R is solved by an eigen equation, and p corresponding eigenvalues and eigenvectors corresponding to the eigenvalues can be obtained. And calculating the accumulated contribution rate of the characteristic values, and determining the characteristic value with the contribution rate of more than 85% as a main characteristic value. And further, determining the product of the main eigenvalue and the eigenvector corresponding to the main eigenvalue as target operation data.
The transformer fault diagnosis method adopts a principal component analysis method to process the distribution characteristic data to obtain target operation data. For example, when the target data includes a sound emission point and a sound intensity feature, the method can eliminate the correlation influence between the sound emission point and the sound intensity feature, and improve the accuracy of the result of the fault diagnosis.
In one embodiment, as shown in FIG. 6, the target operational data includes a target load frequency, a target sound emission point, and a target sound intensity characteristic; the method comprises the following steps of outputting fault information of the transformer to be detected according to target operation data corresponding to the actual load frequency, an actual sound production point and actual sound intensity characteristics, wherein the steps comprise:
s350, calculating a first proportional value of the number of the actual sound production points and the number of the target sound production points;
s360, calculating a second proportional value of the actual sound intensity characteristic and the target sound intensity characteristic;
and S370, outputting fault information under the condition that the first proportion value is larger than the first preset proportion value and/or the second proportion value is larger than the first preset proportion value.
Specifically, the actual sound producing point is the sound producing point of the transformer to be tested; the actual sound intensity characteristic is the sound intensity characteristic of the transformer to be tested; optionally, both the first proportional value and the second proportional value are set to 1.2, specifically, when the number of the actual sounding points of the transformer to be tested exceeds 20% of the number of the target sounding points, a fault of the transformer to be tested is indicated, and at this time, fault information is output; and when the actual sound intensity characteristic of the transformer to be tested exceeds the target sound intensity characteristic by 20%, indicating that the transformer to be tested has a fault, and outputting fault information at the moment.
In one embodiment, the step of outputting the fault information of the transformer to be detected according to the target operation data corresponding to the actual load frequency, the actual sound emission point and the actual sound intensity characteristic further includes:
under the condition that the first proportion value is larger than a first preset proportion value and/or the second proportion value is larger than a second preset proportion value, alarm information is output; wherein, the second preset proportion value is smaller than the first preset proportion value.
Specifically, the second preset proportion value is set according to the precision requirement of the actual environment on the transformer, for example, in the environment with high precision requirement, the second preset proportion value is relatively small; in an environment with a low precision requirement, the second preset proportion value is relatively large, and it should be noted that the second preset proportion value is always smaller than the first preset proportion value. Optionally, the second preset proportion value is 1.1, specifically, when the number of the actual sounding points of the transformer to be tested exceeds 10% of the number of the target sounding points, alarm information is output to remind a worker to pay attention to the transformer; when the actual sound intensity characteristic of the transformer to be tested exceeds the target sound intensity characteristic by 10%, alarm information is output to remind a worker to pay attention to the transformer.
It should be understood that although the various steps in the flowcharts of fig. 1-6 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-6 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.
In one embodiment, there is provided a transformer fault diagnosis apparatus including:
the target operation data acquisition module is used for acquiring target operation data of each fault-free transformer;
the database establishing module is used for internally arranging the target operation data in the fault-free model database;
the actual operation data acquisition module is used for acquiring actual operation data of the transformer to be detected; the actual operation data comprises actual load frequency, actual sound production points and actual sound intensity characteristics;
the target operation data searching module is used for searching the fault-free model database based on the actual load frequency to obtain target operation data corresponding to the actual load frequency;
and the fault detection module is used for outputting fault information of the transformer to be detected according to the target operation data, the actual sound production point and the actual sound intensity characteristic corresponding to the actual load frequency.
In one embodiment, the actual operation data acquisition module includes:
the scaling module is used for scaling the transformer to be detected into a virtual model in an equal proportion;
the light weight module is used for carrying out light weight processing on the virtual model to obtain a light weight model;
the rendering module is used for rendering the lightweight model to obtain a digital twin model of the transformer to be detected;
and the monitoring module is used for monitoring the digital twin model to obtain actual operation data.
In one embodiment, the target operational data acquisition module includes:
the audio data acquisition module is used for acquiring the target load frequency and the audio data of each fault-free transformer;
the distribution characteristic data acquisition module is used for establishing distribution characteristic data of the fault-free transformer noise under each target load frequency according to the audio data;
and the distribution characteristic data processing module is used for processing the distribution characteristic data to obtain target operation data.
In one embodiment, the distributed feature data acquisition module includes:
the segmentation module is used for segmenting the audio data under each target load frequency to obtain segmented data;
the transformation module is used for carrying out Fourier transformation on each segmentation data to obtain frequency domain data;
the frequency domain data processing module is used for processing the frequency domain data to obtain a cross-spectrum density matrix;
the cross spectrum density matrix processing module is used for processing the cross spectrum density matrix to obtain a signal subspace matrix and a noise subspace matrix;
the MUSIC spatial spectrum acquisition module is used for obtaining an MUSIC spatial spectrum according to the signal subspace matrix and the noise subspace matrix;
the arrival acquisition module is used for carrying out spectrum peak search on the MUSIC spatial spectrum to obtain the arrival direction angle of the signal;
and the arrival processing module is used for carrying out beam forming processing on the arrival direction angle to obtain distribution characteristic data.
In one embodiment, the distributed feature data processing module comprises:
the dimensionless data acquisition module is used for carrying out dimensionless processing on the distribution characteristic data to obtain dimensionless data;
the standardization module is used for carrying out standardization processing on the dimensionless data to obtain a standardization matrix;
the correlation coefficient matrix acquisition module is used for acquiring a correlation coefficient matrix according to the standardized matrix;
the correlation coefficient matrix processing module is used for processing the correlation coefficient matrix to obtain a main eigenvalue;
and the product module is used for determining the product of the main eigenvalue and the eigenvector corresponding to the main eigenvalue as target operation data.
In one embodiment, the target operating data includes a target load frequency, a target sound emission point, and a target sound intensity characteristic; the fault detection module includes:
the first proportional value calculating module is used for calculating a first proportional value of the number of the actual sound production points and the number of the target sound production points;
the second proportional value calculating module is used for calculating a second proportional value of the actual sound intensity characteristic and the target sound intensity characteristic;
and the fault information output module is used for outputting fault information under the condition that the first proportion value is larger than a first preset proportion value and/or the second proportion value is larger than the first preset proportion value.
In one embodiment, the fault detection module further comprises:
the alarm information output module is used for outputting alarm information under the condition that the first proportion value is larger than a first preset proportion value and/or the second proportion value is larger than a second preset proportion value; wherein, the second preset proportion value is smaller than the first preset proportion value.
For specific limitations of the transformer fault diagnosis device, reference may be made to the above limitations of the transformer fault diagnosis method, and details are not described herein again. The modules in the transformer fault diagnosis device can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules. It should be noted that, in the embodiment of the present application, the division of the module is schematic, and is only one logic function division, and there may be another division manner in actual implementation.
In one embodiment, there is provided a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring target operation data of each fault-free transformer;
target operation data is built in a fault-free model database;
acquiring actual operation data of a transformer to be detected; the actual operation data comprises actual load frequency, actual sound production points and actual sound intensity characteristics;
searching a fault-free model database based on the actual load frequency to obtain target operation data corresponding to the actual load frequency;
and outputting fault information of the transformer to be detected according to the target operation data corresponding to the actual load frequency, the actual sound production point and the actual sound intensity characteristic.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
scaling the transformer to be detected into a virtual model in an equal proportion;
carrying out lightweight processing on the virtual model to obtain a lightweight model;
rendering the lightweight model to obtain a digital twin model of the transformer to be detected;
and monitoring the digital twin model to obtain actual operation data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring target load frequency and audio data of each fault-free transformer;
establishing distribution characteristic data of the fault-free transformer noise under each target load frequency according to the audio data; and processing the distribution characteristic data to obtain target operation data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
segmenting the audio data under each target load frequency to obtain segmented data;
carrying out Fourier transform on each segmentation data to obtain frequency domain data;
processing the frequency domain data to obtain a cross-spectrum density matrix;
processing the cross-spectrum density matrix to obtain a signal subspace matrix and a noise subspace matrix;
obtaining an MUSIC spatial spectrum according to the signal subspace matrix and the noise subspace matrix;
carrying out spectrum peak search on the MUSIC space spectrum to obtain the direction of arrival angle of the signal;
and performing beam forming processing on the direction of arrival angle to obtain distribution characteristic data.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
carrying out dimensionless processing on the distribution characteristic data to obtain dimensionless data;
carrying out standardization processing on the dimensionless data to obtain a standardized matrix;
obtaining a correlation coefficient matrix according to the standardized matrix;
processing the correlation coefficient matrix to obtain a main characteristic value;
and determining the product of the main eigenvalue and the eigenvector corresponding to the main eigenvalue as target operation data. In one embodiment, the target operating data includes a target load frequency, a target sound emission point, and a target sound intensity characteristic; the processor, when executing the computer program, further performs the steps of:
calculating a first proportional value of the number of the actual sound production points and the number of the target sound production points;
calculating a second proportional value of the actual sound intensity characteristic and the target sound intensity characteristic;
and outputting fault information under the condition that the first proportion value is larger than a first preset proportion value and/or the second proportion value is larger than the first preset proportion value.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
under the condition that the first proportion value is larger than a first preset proportion value and/or the second proportion value is larger than a second preset proportion value, alarm information is output; wherein, the second preset proportion value is smaller than the first preset proportion value.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring target operation data of each fault-free transformer;
target operation data is built in a fault-free model database;
acquiring actual operation data of a transformer to be detected; the actual operation data comprises actual load frequency, actual sound production points and actual sound intensity characteristics;
searching a fault-free model database based on the actual load frequency to obtain target operation data corresponding to the actual load frequency;
and outputting fault information of the transformer to be detected according to the target operation data corresponding to the actual load frequency, the actual sound production point and the actual sound intensity characteristic.
In one embodiment, the computer program when executed by the processor further performs the steps of:
scaling the transformer to be detected into a virtual model in an equal proportion;
carrying out lightweight processing on the virtual model to obtain a lightweight model;
rendering the lightweight model to obtain a digital twin model of the transformer to be detected;
and monitoring the digital twin model to obtain actual operation data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
acquiring target load frequency and audio data of each fault-free transformer;
establishing distribution characteristic data of the fault-free transformer noise under each target load frequency according to the audio data;
and processing the distribution characteristic data to obtain target operation data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
segmenting the audio data under each target load frequency to obtain segmented data;
carrying out Fourier transform on each segmentation data to obtain frequency domain data;
processing the frequency domain data to obtain a cross-spectrum density matrix;
processing the cross-spectrum density matrix to obtain a signal subspace matrix and a noise subspace matrix;
obtaining an MUSIC spatial spectrum according to the signal subspace matrix and the noise subspace matrix;
carrying out spectrum peak search on the MUSIC space spectrum to obtain the direction of arrival angle of the signal;
and performing beam forming processing on the direction of arrival angle to obtain distribution characteristic data.
In one embodiment, the computer program when executed by the processor further performs the steps of:
carrying out dimensionless processing on the distribution characteristic data to obtain dimensionless data;
carrying out standardization processing on the dimensionless data to obtain a standardized matrix;
obtaining a correlation coefficient matrix according to the standardized matrix;
processing the correlation coefficient matrix to obtain a main characteristic value;
and determining the product of the main eigenvalue and the eigenvector corresponding to the main eigenvalue as target operation data.
In one embodiment, the target operating data includes a target load frequency, a target sound emission point, and a target sound intensity characteristic; the computer program when executed by the processor further realizes the steps of:
calculating a first proportional value of the number of the actual sound production points and the number of the target sound production points;
calculating a second proportional value of the actual sound intensity characteristic and the target sound intensity characteristic;
and outputting fault information under the condition that the first proportion value is larger than a first preset proportion value and/or the second proportion value is larger than the first preset proportion value.
In one embodiment, the computer program when executed by the processor further performs the steps of:
under the condition that the first proportion value is larger than a first preset proportion value and/or the second proportion value is larger than a second preset proportion value, alarm information is output; wherein, the second preset proportion value is smaller than the first preset proportion value.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
In the description herein, references to the description of "some embodiments," "other embodiments," "desired embodiments," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, a schematic description of the above terminology may not necessarily refer to the same embodiment or example.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A transformer fault diagnosis method is characterized by comprising the following steps:
acquiring target operation data of each fault-free transformer;
the target operation data is built in a fault-free model database;
acquiring actual operation data of a transformer to be detected; the actual operation data comprises actual load frequency, actual sound production points and actual sound intensity characteristics;
searching the fault-free model database based on the actual load frequency to obtain target operation data corresponding to the actual load frequency;
and outputting the fault information of the transformer to be detected according to the target operation data corresponding to the actual load frequency, the actual sound production point and the actual sound intensity characteristic.
2. The transformer fault diagnosis method according to claim 1, wherein the step of acquiring actual operation data of the transformer to be detected comprises:
scaling the transformer to be detected into a virtual model in an equal proportion;
carrying out lightweight processing on the virtual model to obtain a lightweight model;
rendering the lightweight model to obtain a digital twin model of the transformer to be detected;
and monitoring the digital twin model to obtain the actual operation data.
3. The transformer fault diagnosis method according to claim 1, wherein the step of obtaining target operation data of each fault-free transformer comprises:
acquiring target load frequency and audio data of each fault-free transformer;
establishing distribution characteristic data of the fault-free transformer noise under each target load frequency according to the audio data;
and processing the distribution characteristic data to obtain the target operation data.
4. The transformer fault diagnosis method according to claim 3, wherein the step of establishing distribution characteristic data of the fault-free transformer noise at each of the target load frequencies based on the audio data comprises:
segmenting the audio data under each target load frequency to obtain segmented data;
performing Fourier transform on each piece of the segmented data to obtain frequency domain data;
processing the frequency domain data to obtain a cross-spectrum density matrix;
processing the cross-spectrum density matrix to obtain a signal subspace matrix and a noise subspace matrix;
obtaining an MUSIC spatial spectrum according to the signal subspace matrix and the noise subspace matrix;
performing spectral peak search on the MUSIC spatial spectrum to obtain the direction of arrival angle of the signal;
and carrying out beam forming processing on the direction of arrival angle to obtain the distribution characteristic data.
5. The transformer fault diagnosis method according to claim 3, wherein the step of processing the distribution characteristic data to obtain the target operation data comprises:
carrying out dimensionless processing on the distribution characteristic data to obtain dimensionless data;
carrying out standardization processing on the dimensionless data to obtain a standardized matrix;
obtaining a correlation coefficient matrix according to the standardized matrix;
processing the correlation coefficient matrix to obtain a main characteristic value;
and determining the product of the main eigenvalue and the eigenvector corresponding to the main eigenvalue as the target operation data.
6. The transformer fault diagnosis method according to claim 1, wherein the target operation data includes a target load frequency, a target sound emission point, and a target sound intensity characteristic; the step of outputting the fault information of the transformer to be detected according to the target operation data corresponding to the actual load frequency, the actual sound production point and the actual sound intensity characteristic comprises the following steps:
calculating a first proportional value of the number of the actual sound production points and the number of the target sound production points;
calculating a second proportion value of the actual sound intensity characteristic and the target sound intensity characteristic;
and outputting the fault information under the condition that the first proportion value is larger than a first preset proportion value and/or the second proportion value is larger than the first preset proportion value.
7. The transformer fault diagnosis method according to claim 6, wherein the step of outputting the fault information of the transformer to be detected according to the target operation data corresponding to the actual load frequency, the actual sound emission point and the actual sound intensity characteristic further comprises:
under the condition that the first proportion value is larger than a first preset proportion value and/or the second proportion value is larger than a second preset proportion value, alarm information is output; and the second preset proportion value is smaller than the first preset proportion value.
8. A transformer fault diagnosis apparatus, characterized by comprising:
the target operation data acquisition module is used for acquiring target operation data of each fault-free transformer;
the database establishing module is used for internally arranging the target operation data in a fault-free model database;
the actual operation data acquisition module is used for acquiring actual operation data of the transformer to be detected; the actual operation data comprises actual load frequency, actual sound production points and actual sound intensity characteristics;
the target operation data searching module is used for searching the fault-free model database based on the actual load frequency to obtain target operation data corresponding to the actual load frequency;
and the fault detection module is used for outputting the fault information of the transformer to be detected according to the target operation data corresponding to the actual load frequency, the actual sound production point and the actual sound intensity characteristic.
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111485317.5A CN114238368A (en) | 2021-12-07 | 2021-12-07 | Transformer fault diagnosis method and device, computer equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111485317.5A CN114238368A (en) | 2021-12-07 | 2021-12-07 | Transformer fault diagnosis method and device, computer equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114238368A true CN114238368A (en) | 2022-03-25 |
Family
ID=80753670
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111485317.5A Pending CN114238368A (en) | 2021-12-07 | 2021-12-07 | Transformer fault diagnosis method and device, computer equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114238368A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117194900A (en) * | 2023-09-25 | 2023-12-08 | 中国铁路成都局集团有限公司成都供电段 | Equipment operation lightweight monitoring method and system based on self-adaptive sensing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110412368A (en) * | 2019-06-27 | 2019-11-05 | 安徽继远软件有限公司 | Electrical equipment online supervision method and system based on Application on Voiceprint Recognition |
| CN111175698A (en) * | 2020-01-18 | 2020-05-19 | 国网山东省电力公司菏泽供电公司 | Transformer noise source positioning method, system and device based on sound and vibration combination |
| CN112395959A (en) * | 2020-10-30 | 2021-02-23 | 天合云能源互联网技术(杭州)有限公司 | Power transformer fault prediction and diagnosis method and system based on audio features |
| CN112684379A (en) * | 2020-11-25 | 2021-04-20 | 江苏科技大学 | Transformer fault diagnosis system and method based on digital twinning |
-
2021
- 2021-12-07 CN CN202111485317.5A patent/CN114238368A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110412368A (en) * | 2019-06-27 | 2019-11-05 | 安徽继远软件有限公司 | Electrical equipment online supervision method and system based on Application on Voiceprint Recognition |
| CN111175698A (en) * | 2020-01-18 | 2020-05-19 | 国网山东省电力公司菏泽供电公司 | Transformer noise source positioning method, system and device based on sound and vibration combination |
| CN112395959A (en) * | 2020-10-30 | 2021-02-23 | 天合云能源互联网技术(杭州)有限公司 | Power transformer fault prediction and diagnosis method and system based on audio features |
| CN112684379A (en) * | 2020-11-25 | 2021-04-20 | 江苏科技大学 | Transformer fault diagnosis system and method based on digital twinning |
Non-Patent Citations (1)
| Title |
|---|
| 郑倩: "《人脑磁共振图像的数据智能分析方法研究》", vol. 978, 30 November 2020, 中国铁道出版社有限公司, pages: 82 - 84 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117194900A (en) * | 2023-09-25 | 2023-12-08 | 中国铁路成都局集团有限公司成都供电段 | Equipment operation lightweight monitoring method and system based on self-adaptive sensing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220146462A1 (en) | Method for predicting remaining life of numerical control machine tool | |
| US9909863B2 (en) | Determination of a room dimension estimate | |
| CN117196353B (en) | Environmental pollution assessment and monitoring method and system based on big data | |
| JP2020071624A (en) | Abnormality diagnosing apparatus, abnormality diagnosing method and program | |
| CN117116290B (en) | Method and related equipment for positioning defects of numerical control machine tool parts based on multidimensional characteristics | |
| CN116861544B (en) | Building abnormal vibration source positioning method based on edge cloud cooperation and related equipment | |
| CN114238368A (en) | Transformer fault diagnosis method and device, computer equipment and readable storage medium | |
| CN115128345B (en) | Power grid safety early warning method and system based on harmonic monitoring | |
| CN114184367A (en) | Fault diagnosis method, device and equipment for rotary mechanical equipment and readable storage medium | |
| CN117473338B (en) | Nuclear power pump operation monitoring method and system | |
| CN115222727A (en) | Method for identifying target for preventing external damage of power transmission line | |
| de Siqueira Nascimento et al. | Data-driven soft sensor for the estimation of sound power levels of refrigeration compressors through vibration measurements | |
| KR101803119B1 (en) | Data perturbation for wafer inspection or metrology setup | |
| CN116907586B (en) | Ultrasonic equipment running state management system and method based on cloud computing | |
| CN113553319A (en) | LOF outlier detection cleaning method, device and equipment based on information entropy weighting and storage medium | |
| CN112801135A (en) | Fault line selection method and device for power plant service power system based on characteristic quantity correlation | |
| CN116484184A (en) | Method and device for enhancing partial discharge defect sample of power equipment | |
| CN113704942B (en) | Method, device and computer system for estimating pressure of unknown node of water supply pipe network | |
| JP7347303B2 (en) | Monitoring equipment, monitoring system, monitoring method and monitoring program | |
| Agrawal et al. | Induction motor bearing fault classification using WPT, PCA and DSVM | |
| CN116664950B (en) | Aurora image automatic classification method, aurora image automatic classification device, computer equipment and storage medium | |
| CN117314914B (en) | Defect identification method for engineering nondestructive testing image and related equipment | |
| CN117216489B (en) | Waterproof coating quality inspection analysis method and system based on Internet | |
| CN117574113B (en) | Bearing fault monitoring method and system based on spherical coordinate underdetermined blind source separation | |
| CN113806495B (en) | Outlier machine detection method and device |
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 |