CN117470867B - Method and device for distinguishing contamination of insulator of power transformation equipment and electronic equipment - Google Patents
Method and device for distinguishing contamination of insulator of power transformation equipment and electronic equipment Download PDFInfo
- Publication number
- CN117470867B CN117470867B CN202311811269.3A CN202311811269A CN117470867B CN 117470867 B CN117470867 B CN 117470867B CN 202311811269 A CN202311811269 A CN 202311811269A CN 117470867 B CN117470867 B CN 117470867B
- Authority
- CN
- China
- Prior art keywords
- pollution
- spectral line
- spectral
- data
- preset
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 83
- 230000009466 transformation Effects 0.000 title claims abstract description 66
- 239000012212 insulator Substances 0.000 title claims abstract description 37
- 238000011109 contamination Methods 0.000 title claims description 15
- 230000003595 spectral effect Effects 0.000 claims abstract description 237
- 238000012544 monitoring process Methods 0.000 claims abstract description 54
- 238000012545 processing Methods 0.000 claims abstract description 51
- 238000012937 correction Methods 0.000 claims abstract description 49
- 238000004458 analytical method Methods 0.000 claims abstract description 35
- 150000003839 salts Chemical class 0.000 claims abstract description 35
- 239000003344 environmental pollutant Substances 0.000 claims abstract description 6
- 231100000719 pollutant Toxicity 0.000 claims abstract description 6
- 238000001228 spectrum Methods 0.000 claims description 53
- 238000003384 imaging method Methods 0.000 claims description 24
- 238000010438 heat treatment Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 14
- 230000005855 radiation Effects 0.000 claims description 12
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 claims description 10
- -1 compound salt Chemical class 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 229910018072 Al 2 O 3 Inorganic materials 0.000 claims description 5
- 239000005995 Aluminium silicate Substances 0.000 claims description 5
- 229910004298 SiO 2 Inorganic materials 0.000 claims description 5
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 claims description 5
- 235000012211 aluminium silicate Nutrition 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 5
- NLYAJNPCOHFWQQ-UHFFFAOYSA-N kaolin Chemical compound O.O.O=[Al]O[Si](=O)O[Si](=O)O[Al]=O NLYAJNPCOHFWQQ-UHFFFAOYSA-N 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 5
- 239000011780 sodium chloride Substances 0.000 claims description 5
- 230000004069 differentiation Effects 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- 238000009413 insulation Methods 0.000 abstract description 14
- 238000001514 detection method Methods 0.000 abstract description 4
- 239000010410 layer Substances 0.000 description 17
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 238000013136 deep learning model Methods 0.000 description 7
- 239000010935 stainless steel Substances 0.000 description 6
- 229910001220 stainless steel Inorganic materials 0.000 description 6
- 238000009825 accumulation Methods 0.000 description 5
- 229910000838 Al alloy Inorganic materials 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000000701 chemical imaging Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000012774 insulation material Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000002844 melting Methods 0.000 description 2
- 230000008018 melting Effects 0.000 description 2
- 238000004321 preservation Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 239000000443 aerosol Substances 0.000 description 1
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/93—Detection standards; Calibrating baseline adjustment, drift correction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8883—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges involving the calculation of gauges, generating models
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/12—Circuits of general importance; Signal processing
- G01N2201/127—Calibration; base line adjustment; drift compensation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The application provides a method and a device for distinguishing pollution of an insulator of an electric transformation device and electronic equipment, and relates to the technical field of insulation detection, wherein the method comprises the following steps: collecting pollution monitoring data of the surface of the target power transformation equipment, wherein pollutants are deposited on the surface of the target power transformation equipment; carrying out data correction processing and spectral line identification processing on the pollution monitoring data in sequence to obtain a spectral line identification result of an effective spectral line; inputting the spectral line recognition result into a trained pollution distinguishing model for classifying the pollution types to obtain a pollution analysis result, wherein the pollution analysis result at least comprises salt density and gray density. According to the method and the device, the type of the pollution of the power transformation equipment can be automatically evaluated under the condition that the on-site pollution is not damaged, and the accuracy of the pollution of the insulator is distinguished.
Description
Technical Field
The application relates to the technical field of insulation detection, in particular to a method and a device for distinguishing pollution of insulators of electric transformation equipment and electronic equipment.
Background
When operating on line in the atmosphere environment, the transformer equipment is affected by environmental factors such as industrial emissions, natural dust and the like, and a layer of dirt is easy to deposit on the surface of the transformer equipment. Under the condition of dry weather, the power transformation equipment with the filth on the surfaces can still keep a higher insulation level, and the discharge voltage is similar to that in a clean and dry state. However, when wet weather such as fog, capillary rain, ice melting, snow melting and the like is met, a water film is formed on the surface of the power transformation equipment, soluble salts in the dirt layer are dissolved in water, so that a conductive water film is formed, leakage current flows along the surface of the power transformation equipment, and a certain potential safety hazard exists.
With the continuous accumulation of experience and the continuous progress of testing means, a great deal of research is carried out, and various characterization methods for quantitatively dividing the pollution level are provided: salt deposit method, surface dirty layer conductivity method, leakage current method, dirty lightning position gradient method, power transformation equipment dirty discharge detection method based on acoustic emission technology, local conductivity method, etc. From the results of the existing researches, no unified method for accurately evaluating the pollution type of the power transformation equipment exists, manual sampling is needed in the method, the condition of site pollution accumulation can be destroyed, and the accurate distinction of the insulator pollution cannot be realized.
Disclosure of Invention
In view of the above, the application provides a method and a device for distinguishing the pollution of an insulator of a power transformation device and an electronic device, which can automatically evaluate the pollution type of the power transformation device under the condition of not damaging the field pollution accumulation, thereby realizing the accuracy distinction of the pollution of the insulator.
To achieve the above object, a first aspect of the present application provides a method for distinguishing contamination of an insulator of an electrical transformer, including:
collecting pollution monitoring data of the surface of the target power transformation equipment, wherein pollutants are deposited on the surface of the target power transformation equipment;
Carrying out data correction processing and spectral line identification processing on the pollution monitoring data in sequence to obtain a spectral line identification result of an effective spectral line;
inputting the spectral line recognition result into a trained pollution distinguishing model for classifying the pollution types to obtain a pollution analysis result, wherein the pollution analysis result at least comprises salt density and gray density.
A second aspect of the present application provides a device for distinguishing a contamination of an insulator of an electrical transformer apparatus, comprising:
the acquisition module is used for acquiring pollution monitoring data of the surface of the target power transformation equipment, and pollutants are deposited on the surface of the target power transformation equipment;
the processing module is used for sequentially carrying out data correction processing and spectral line identification processing on the pollution monitoring data to obtain a spectral line identification result of an effective spectral line;
the input module is used for inputting the spectral line recognition result into the trained pollution distinguishing model to carry out pollution type classification and division, and a pollution analysis result is obtained and at least comprises salt density and gray density.
In a third aspect, there is provided an electronic device comprising a processor, a memory for storing instructions, a user interface and a network interface, both for communicating to other devices, the processor for executing the instructions stored in the memory to cause the electronic device to perform a method as in the first aspect.
In a fourth aspect, there is provided a computer-readable storage medium storing a computer program for causing a computer to perform the method as in the first aspect.
According to the technical scheme provided by the application, after the pollution monitoring data on the surface of the target power transformation equipment are collected, data correction processing and spectral line identification processing can be performed on the pollution monitoring data, so that a spectral line identification result of an effective spectral line is obtained; and inputting the spectral line recognition result into a trained pollution distinguishing model to classify the pollution types, so as to obtain a pollution analysis result comprising salt density and gray density. In the embodiment of the disclosure, the type of the pollution of the power transformation equipment can be automatically evaluated by using the deep learning model under the condition of not damaging the site pollution, and the accurate values of the salt density and the ash density are obtained by calculation, so that the accuracy distinction of the pollution of the insulator is realized.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application. Additional features and advantages of the present application will be set forth in the detailed description which follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is an application scenario diagram provided in an embodiment of the present application;
fig. 2 is a schematic flow chart of a method for distinguishing contamination of an insulator of an electrical transformer according to an embodiment of the present application;
fig. 3 is a schematic flow chart of a method for distinguishing contamination of an insulator of an electrical transformer according to another embodiment of the present disclosure;
fig. 4 is a block diagram of a combined heat-preserving main control box according to an embodiment of the present application;
fig. 5 is a block diagram of a middle heat insulation layer in a combined heat insulation main control box according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a device for distinguishing contamination of an insulator of an electrical transformer according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a device for distinguishing contamination of an insulator of an electrical transformer according to an embodiment of the present application;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
In the figure:
4-combined heat-insulating main control box, 41-infrared radiation film heating device, 411-aluminum alloy frame, 412-heat insulation material, 42-middle heat insulation layer, 421-stainless steel inner shell and 422-stainless steel outer shell;
5-power supply.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present application based on the embodiments herein.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
With the continuous accumulation of experience and the continuous progress of testing means, a great deal of research is carried out, and various characterization methods for quantitatively dividing the pollution level are provided: salt deposit method, surface dirty layer conductivity method, leakage current method, dirty lightning position gradient method, power transformation equipment dirty discharge detection method based on acoustic emission technology, local conductivity method, etc. From the results of the existing researches, no unified method for accurately evaluating the pollution type of the power transformation equipment exists, manual sampling is needed in the method, the condition of site pollution accumulation can be destroyed, and the accurate distinction of the insulator pollution cannot be realized.
It should be understood that the technical solution of the present application may be applied to the following scenarios, but is not limited to:
in some implementations, fig. 1 is an application scenario diagram provided in an embodiment of the present application, where, as shown in fig. 1, an electronic device 110 and a network device 120 may be included in the application scenario. The electronic device 110 may establish a connection with the network device 120 through a wired network or a wireless network.
By way of example, the electronic device 110 may be, but is not limited to, a desktop computer, a notebook computer, a tablet computer, and the like. The network device 120 may be a terminal device or a server, but is not limited thereto. In one embodiment of the present application, the electronic device 110 may send a request message to the network device 120, where the request message may be used to request to obtain a pollution analysis result of the surface of the target power transformation device, and further, the electronic device 110 may receive a response message sent by the network device 120, where the response message includes the pollution analysis result of the surface of the target power transformation device.
In addition, fig. 1 illustrates one electronic device 110 and one network device 120, and may actually include other numbers of electronic devices and network devices, which is not limited in this application.
In other realizations, the technical solutions of the present application may also be executed by the electronic device 110, or the technical solutions of the present application may also be executed by the network device 120, which is not limited in this application.
After the application scenario of the embodiment of the present application is introduced, the following details of the technical solution of the present application will be described:
step 210, collecting pollution monitoring data of the surface of the target power transformation equipment, wherein pollutants are deposited on the surface of the target power transformation equipment.
The target power transformation equipment is power transformation equipment with deposited filth on the surface, and the power transformation equipment to be identified by filth distinguishing can comprise a power distribution panel, a transformer substation or a switching device for power supply or distribution, and the like, and is not particularly limited; the pollution monitoring data are spectrum data which can be identified by a computer after hyperspectral image data of the surface of the target substation equipment are acquired by using a customized prism-grating-prism imaging spectrometer and hyperspectral imaging technology.
And 220, sequentially carrying out data correction processing and spectral line identification processing on the pollution monitoring data to obtain a spectral line identification result of an effective spectral line.
For the embodiment of the disclosure, in order to improve the accuracy of spectral line data reflected by the pollution monitoring data, data correction processing may be performed on the pollution monitoring data, where the data correction processing may include mirror image transformation, black-and-white frame calibration, multiple scattering correction, atmospheric correction, and the like, and specific correction processes may refer to the existing published patent, and specific details are not described herein. In the following example steps in the present disclosure, the technical solution in the present disclosure will be described by taking the example that the data correction processing includes multiple scattering correction and atmospheric correction as an example, but the present disclosure is not limited to the specific example. After carrying out data correction processing on the pollution monitoring data, further carrying out spectral line identification processing, completing comparison of different material spectral information, classification identification of unknown materials and the like, and obtaining spectral line identification results of effective spectral lines. The purpose of spectral line identification is to extract effective spectral lines from a plurality of spectral lines, so that interference of interference spectral lines in pollution monitoring data to a pollution distinguishing process is reduced, the task amount of a pollution distinguishing model is reduced, and the efficiency of pollution distinguishing is improved.
And 230, inputting the spectral line recognition result into a trained pollution distinguishing model to classify the pollution types, so as to obtain a pollution analysis result, wherein the pollution analysis result at least comprises salt density and gray density.
The pollution distinguishing model is a deep learning model trained by a pollution distinguishing task, and can classify and divide the pollution types according to input spectral line recognition results, namely by characteristic analysis of each effective spectral line in the spectral line recognition results. The deep learning model may include, but is not limited to, a deep belief network (Deep Belief Network, DBN) based on a limited boltzmann machine (Restricted Boltzmann Machine, RBM), a Stacked automatic encoder (packed AutoEncoders, SAE) based on an Automatic Encoder (AE), a convolutional neural network (Convolutional Neural Networks, CNN), and a recurrent neural network (Recurrent Neural Networks, RNN), among others.
In summary, according to the method for distinguishing the pollution of the insulator of the power transformation equipment provided by the application, after the pollution monitoring data of the surface of the target power transformation equipment is collected, the pollution monitoring data can be subjected to data correction processing and spectral line identification processing, so that the spectral line identification result of an effective spectral line is obtained; and inputting the spectral line recognition result into a trained pollution distinguishing model to classify the pollution types, so as to obtain a pollution analysis result comprising salt density and gray density. In the embodiment of the disclosure, the type of the pollution of the power transformation equipment can be automatically evaluated by using the deep learning model under the condition of not damaging the site pollution, and the accurate values of the salt density and the ash density are obtained by calculation, so that the accuracy distinction of the pollution of the insulator is realized.
Based on the embodiment shown in fig. 2, as a refinement and extension of the above embodiment, in order to fully describe the specific implementation procedure of the method of this embodiment, this embodiment provides a specific method as shown in fig. 3. As shown in fig. 3, the method comprises the steps of:
step 310, detecting two-dimensional geometric space and one-dimensional spectrum information of the surface of the target transformer equipment by using an imaging spectrometer, and obtaining continuous and narrow-band hyperspectral image data with hyperspectral resolution, wherein the hyperspectral image data at least comprises image information, spectrum information and image information of any spectrum.
The customized imaging spectrometer mainly applies hyperspectral imaging technology, and is characterized in that the imaging technology is combined with the spectroscopic technology based on image data technology with a large number of narrow wave bands, and two-dimensional geometric space and one-dimensional spectroscopic information of a target are detected to obtain continuous and narrow wave band image data with high spectral resolution. Hyperspectral images refer to a careful segmentation in the spectral dimension, not just the traditional distinction of black and white or R, G, B, but also N channels in the spectral dimension. Therefore, the three-dimensional data cube is obtained through the hyperspectral equipment, comprises image information and spectrum information, and can obtain image information of any spectrum after being unfolded in the spectrum dimension. The hyperspectral image data acquisition is completed by using a customized prism-grating-prism imaging spectrometer and applying a hyperspectral imaging technology, and the method specifically comprises the following steps: and (3) monitoring the pollution components of the insulator for a plurality of times by using a spectrum imager with the reflection characteristic of light, and obtaining hyperspectral image data of the pollution components of the insulator by taking the data average value of a plurality of experiments.
When the hyperspectral image data are acquired by using an imaging spectrometer, the method specifically comprises the following steps: performing two-dimensional space scanning in a direction perpendicular to the movement direction of the target substation equipment; and in the direction parallel to the movement of the target substation equipment, light is split through the grating and the prism, so that the spectrum dimension scanning is completed. The imaging spectrometer sequentially collects images of pixels on a certain line, spectrum information is split by the transmission grating to obtain a complete spectrum, so that the imaging spectrometer can synthesize a spectrum information file of an object to be detected through the internal movement of the motion platform to obtain hyperspectral image data. Meanwhile, the spectrum data acquisition principle also enables the three-dimensional characteristic of the hyperspectral image data to become more visual, and the hyperspectral image data can be a two-dimensional plane view under a specific wavelength or a spectrum characteristic curve of a certain pixel point or a certain pixel area.
In a specific application scene, the imaging spectrometer is influenced by high voltage, electromagnetism and other factors because of long-term operation in an outdoor cold environment, so that the fault probability of the system is increased. In order to improve the normal running performance of the system, the imaging spectrometer can be provided with a heat preservation measure to ensure the working performance of the imaging spectrometer. As shown in fig. 4 and 5, the proposed thermal insulation measure adopts a combined thermal insulation main control box 4 with excellent performance and a low-power consumption infrared radiation film heating device 41, so that the spectrum imager is in a proper working environment. It should be noted that, the combined heat-preserving main control box 4 does not play a role of heating, only plays a role of heat insulation, can delay the reduction process of the temperature in the box under the extremely low temperature environment, and can not play a role of protecting the optical imager under the long-term low temperature environment in winter only by virtue of the combined heat-preserving main control box. Therefore, the infrared radiation film heating apparatus 41 can also be designed to heat-treat the optical imager. The infrared radiation film heating device 41 is made of an aluminum alloy frame 411, a heat insulation material 412 is coated outside the aluminum alloy frame 411, a power interface is arranged on the aluminum alloy frame 411 and can be used for externally connecting a power supply 5, the middle heat insulation layer 41 is used for heating the infrared radiation film heating device 41 when the temperature of the spectrum imager is lower than a set temperature, and the heating is stopped when the temperature rises to the set temperature. An infrared radiation film heating device 41 is arranged in the combined heat-preserving main control box 4; the imaging spectrometer is arranged on the middle heat insulation layer 42 of the combined heat insulation main control box 4, and the middle heat insulation layer 42 is used for isolating the working environment of the imaging spectrometer and the external low-temperature environment; when the operating temperature in the operating environment is lower than the preset temperature threshold, the heating process is performed by the infrared radiation film heating device 41 so that the operating temperature reaches the preset temperature threshold. Wherein, the middle insulating layer 42 of the combined heat preservation master control box 4 is made of siliceous nano-pore heat insulation materials, the middle insulating layer 42 comprises a stainless steel inner shell 421 and a stainless steel outer shell 422, an infrared radiation film heating device 41 is laid at the bottom of the stainless steel inner shell 421, and heat insulation rubber is adopted at the junction of the stainless steel outer shell 422 and the opening to seal the junction. Can ensure that the interior of the box is fully isolated from the external severe environment in extremely cold weather.
Accordingly, the embodiment steps may further include: collecting the working temperature of the imaging spectrometer under the corresponding working environment; when the working temperature is judged to be lower than the preset temperature threshold, the infrared radiation film heating device 41 in the combined heat-preserving main control box 4 is utilized for heating treatment, so that the working temperature reaches the preset temperature threshold, wherein the imaging spectrometer is placed on the middle heat-insulating layer 42 of the combined heat-preserving main control box 4, and the middle heat-insulating layer 42 is used for isolating the working environment of the imaging spectrometer and the external low-temperature environment. The preset temperature threshold may be defined individually according to an actual application scenario, and is not specifically limited herein.
Step 320, converting the hyperspectral image data into pollution monitoring data in the form of digital signals.
For the disclosed embodiments, a photosensor may be utilized to convert spectral signals in the hyperspectral image data to voltage analog signals; and carrying out digital signal conversion on the voltage analog signal by using an AD analog-to-digital conversion circuit to obtain pollution monitoring data.
And 330, sequentially performing data correction processing and spectral line identification processing on the pollution monitoring data to obtain a spectral line identification result of the effective spectral line.
For the embodiment of the disclosure, the effective spectral lines can be extracted from the multiple spectral lines by sequentially carrying out data correction processing and spectral line identification processing on the pollution monitoring data, so that interference of interference spectral lines in the pollution monitoring data to a pollution distinguishing process is reduced, workload of a pollution distinguishing model is reduced, and efficiency of pollution distinguishing is improved. Accordingly, the embodiment steps may include: carrying out spectral feature recognition based on pollution monitoring data, and extracting target spectral lines with spectral overlap rate larger than a first preset threshold value and spectral data corresponding to the target spectral lines; performing data correction processing on the spectrum data to obtain corrected target spectrum data, wherein the data correction processing at least comprises multi-element scattering correction and atmospheric correction processing; and carrying out spectral line identification based on the target spectral data to obtain a spectral line identification result of the effective spectral line. The first preset threshold is a value between 0 and 1, and a specific value can be set according to an actual application scenario, which is not specifically limited herein. The closer the set value of the first preset threshold value is to 1, the higher the spectrum overlapping rate of the screened target spectrum line is, and the more likely the effective spectrum line of the pollution type can be obtained through analysis.
In the embodiment of the present disclosure, the technical solution in the present disclosure is described by taking the example that the data correction process includes the multiple scattering correction and the atmospheric correction process. Multivariate scatter correction (Multiplicative Scatter Correction, MSC) is a common algorithm for preprocessing hyperspectral data, and MSC can eliminate spectral differences due to different scatter levels, thereby enhancing correlation between spectra and data. The method corrects the baseline shift and offset phenomenon of the spectrum data through the ideal spectrum, and can specifically assume that the average value of all the pollution monitoring data is taken as the ideal spectrum.
The MSC specifically realizes the following steps:
1) The average value of all the pollution monitoring data is obtained as an ideal spectrum:
in the method, in the process of the invention,is an ideal spectrum; />The method comprises the steps of monitoring pollution components of an insulator for multiple times by utilizing a spectrum imager to obtain multiple pollution monitoring data;nthe data volume of the data is monitored for a plurality of contaminants.
2) Carrying out unitary linear regression on each pollution monitoring data and an ideal spectrum, solving a least square problem, and obtaining a baseline translation amount and an offset of each pollution monitoring data:
in the method, in the process of the invention,is an ideal spectrum; />The method comprises the steps of monitoring pollution components of an insulator for multiple times by utilizing a spectrum imager to obtain multiple pollution monitoring data; / >For the offset +.>Is the baseline shift amount.
3) Correction is performed on each of the pollution monitoring data: subtracting the obtained baseline translation amount and dividing the baseline translation amount by the offset amount to obtain spectrum data after multi-element scattering correction:
in the method, in the process of the invention,spectral data after multi-element scattering correction; />The method comprises the steps of monitoring pollution components of an insulator for multiple times by utilizing a spectrum imager to obtain multiple pollution monitoring data; />For the offset +.>Is the baseline shift amount.
In a specific application scenario, solar radiation is incident on the surface of the target transformer device in a certain way through the atmosphere and then reflected back to the sensor, and the original image contains the integration of information such as the surface of an object, the atmosphere, and information of the sun due to the images such as the atmosphere aerosol, the terrain, the adjacent ground objects and the like. If one wants to know the spectral properties of the surface of an object, one must separate its reflection information from the information of the atmosphere and sun, which requires an atmosphere correction process. For the embodiment of the disclosure, after the multi-element scattering correction is performed on the pollution monitoring data, the atmospheric correction treatment can be further performed so as to eliminate the spectral influence of factors such as atmosphere, illumination and the like on the surface reflection of the target power transformation equipment.
Accordingly, when performing line identification based on the target spectrum data to obtain a line identification result of the effective line, the steps of the embodiment may include: extracting spectral line characteristics of each target spectral line in target spectrum data, wherein the spectral line characteristics at least comprise spectral line wavelength and spectral line intensity; calculating the feature similarity between the spectral line features and preset spectral line features of a plurality of preset spectral lines; and determining a target spectral line with the corresponding feature similarity larger than a second preset threshold value as an effective spectral line, and determining the spectral line type of the preset spectral line successfully matched with the corresponding feature of the effective spectral line in the plurality of preset spectral lines as a spectral line identification result of the effective spectral line.
When the information feature similarity is calculated, feature distances between spectral line features and preset spectral line features of a plurality of preset spectral lines can be calculated based on a preset distance calculation formula, and the larger the feature distance is, the smaller the information feature similarity is indicated; the smaller the feature distance, the greater the similarity of the information features. The preset distance calculation formula may include, but is not limited to, euclidean distance calculation formula, minth distance calculation formula, mahalanobis distance calculation formula, etc.; in addition, the feature similarity between the spectral line feature and the preset spectral line feature of the plurality of preset spectral lines can be calculated based on a preset similarity calculation formula, and the preset similarity calculation formula can include, but is not limited to, a cosine similarity calculation formula, a correlation coefficient calculation formula and the like.
For example, a plurality of preset spectral lines may be preset: A. b, C, D, E, corresponding preset spectral line characteristics are respectively determined for a plurality of preset spectral lines: a. b, c, d, e and a corresponding second preset threshold value is set to 75%. For the target spectral line F, G, after extracting the corresponding spectral line features f and g, the spectral line features f and g and each preset spectral line feature can be calculated respectively: a. b, c, d, e, if the feature similarity between the spectral line feature f and each preset spectral line feature is calculated, the feature similarity is respectively as follows: 80%, 1%, 5%, 10%, 4%; the feature similarity between the spectral line feature g and each preset spectral line feature is calculated as follows: 50%, 20%, 5%, 10%, 15%. In view of the fact that the feature similarity of the spectral line feature F and the preset spectral line feature a is larger than a second preset threshold, a target spectral line F corresponding to the spectral line feature F can be determined to be an effective spectral line, and the spectral line type of the preset spectral line feature a corresponding to the preset spectral line A can be determined to be a spectral line identification result of the target spectral line F; in view of the fact that the feature similarity of the spectral line feature G and each preset spectral line feature is smaller than a second preset threshold, the target spectral line G corresponding to the spectral line feature G can be used as an interference spectral line for filtering, namely the target spectral line G is not determined to be an effective spectral line.
And 340, inputting the spectral line recognition result into the trained pollution distinguishing model to classify the pollution types, and obtaining a pollution analysis result.
The pollution distinguishing model comprises a self-encoder (AE), a multi-convolution self-encoder (Multiple Convolutional Auto-Encode, MCAE), a hybrid convolution self-encoder (Fix Convolutional Auto-Encode, FCAE) and a convolutional neural network. The self-encoder AE is a neural network of hidden layers, the input and output are x, and the input dimension must be larger than the output dimension, belonging to unsupervised learning, which compresses the input into a potential spatial representation, and then reconstructs the output from this representation. In the disclosed embodiments, the self-encoder AE may be used to extract combined structural features between different spectral line elements; the multi-convolution self-encoder MCAE can be used for extracting the spatial distribution characteristics of a plurality of spectral line elements in the spectral line identification result; the hybrid convolutional self-encoder FCAE may be used to extract hybrid features corresponding to the combined structural features and the spatially distributed features.
For embodiments of the present disclosure, the embodiment steps may include: inputting spectral line identification results into an encoder AE, a multi-convolution self-encoder MCAE and a mixed convolution self-encoder FCAE respectively to obtain combined structural features among different spectral line elements extracted from the encoder AE, spatial distribution features of a plurality of spectral line elements extracted from the multi-convolution self-encoder MCAE and mixed features corresponding to the combined structural features and the spatial distribution features extracted from the mixed convolution self-encoder FCAE; and carrying out classification and division on the pollution types based on the combined structural features, the spatial distribution features and the mixed features by using a convolutional neural network to obtain a pollution analysis result.
Since the fouling of the insulator surface typically comprises both soluble and insoluble components, the salt density (the amount of salt density typically used) refers to the ratio of soluble components to surface area in the fouling of the insulator surface layer, as distinguished from the ash density. According to the new standard of the power grid pollution division, the relation between the salt density and the ash density in the pollution degree is dispersed 5-10 times, and insulators with the same salt density and different ash densities can be in different pollution grades, so that the confirmation of the pollution grade can be determined by the combination of the salt density and the ash density. For the embodiment of the disclosure, after the classification and division of the pollution types are performed based on the pollution distinguishing model to obtain the salt density and the ash density, the pollution grade can be further determined based on the salt density and the ash density.
The pollution distinguishing model is a deep learning model trained by a pollution distinguishing task. When the pollution distinguishing model is trained, different kinds of compound salts can be used as pollution samples, the pollution accumulated on the surface of the power transformation equipment in the actual running environment is simulated, and any insulator sample only covers one pollution, and the method specifically comprises the following steps of: simulation of a pollution type compound salt of power transformation equipment: by NaCl, caSO 4 、CaCO 3 、SiO 2 、Al 2 O 3 、Fe 2 O 3 Six compound salts are used as pollution salt density in pollution samples, and the main components of the six compound salts are kaolin and diatomite which are mixtures of insoluble salts, so as to simulate the pollution ash density accumulated on the surfaces of power transformation equipment in an actual running environment.
The embodiment steps may include: generating a pollution sample provided with a preset characteristic label, wherein the pollution sample is used for simulating pollution accumulated on the surface of power transformation equipment in an actual operation environment, and NaCl and CaSO are utilized in the pollution sample 4 、CaCO 3 、SiO 2 、Al 2 O 3 、Fe 2 O 3 Six compound salts simulate the dirty salt density of the surface of the power transformation equipment and the mixture of insoluble salts, namely kaolin and diatomite are utilized to simulateThe method comprises the steps that dirt dust accumulated on the surface of power transformation equipment in an actual running environment is dense, and a preset characteristic label is a dirt analysis result corresponding to a dirt sample; acquiring sample spectral line identification data of a pollution sample; inputting sample spectral line identification data and a preset characteristic label into a pollution distinguishing model, and performing task training of pollution distinguishing on the pollution distinguishing model, wherein in the task training of pollution distinguishing, the sample spectral line identification data is used as an input characteristic, the preset characteristic label is used as a training label, model parameters in the pollution distinguishing model are iteratively updated until the accuracy of the pollution distinguishing model on the pollution distinguishing is greater than a preset accuracy threshold, and the completion of the training of the pollution distinguishing model is judged.
For the embodiment of the disclosure, after the pollution analysis result of the surface of the target power transformation equipment is obtained, the pollution analysis result can be transmitted to a background monitoring center for storage and display by using a wireless sensing network. When the pollution analysis result is transmitted to the background monitoring center for storage and then displayed by utilizing the wireless sensing network, the pollution analysis result can be transmitted to the background monitoring center through the LoRa-WAN wireless communication protocol, namely, a data transmission layer, so that the real-time monitoring of the pollution stability in the power transformation equipment is realized, and the real-time monitoring of operation personnel is facilitated. The LoRa-WAN wireless sensor network has the advantages that the LoRa-WAN wireless sensor network is not affected by local GPRS signals, and after large-area networking, the LoRa-WAN wireless sensor network can use frequency bands for free and does not increase the later maintenance cost. After each LoRa wireless node is networked, the wireless gateway is utilized to transmit the data set to the background terminal through GPRS signals.
In summary, according to the technical scheme provided by the application, after the pollution monitoring data on the surface of the target power transformation equipment are collected, data correction processing and spectral line identification processing can be performed on the pollution monitoring data, so that a spectral line identification result of an effective spectral line is obtained; and inputting the spectral line recognition result into a trained pollution distinguishing model to classify the pollution types, so as to obtain a pollution analysis result comprising salt density and gray density. In the embodiment of the disclosure, the type of the pollution of the power transformation equipment can be automatically evaluated by using the deep learning model under the condition of not damaging the site pollution, and the accurate values of the salt density and the ash density are obtained by calculation, so that the accuracy distinction of the pollution of the insulator is realized.
Based on the specific description of the method for distinguishing the contamination of the insulator of the electrical equipment provided in fig. 2 and 3, as shown in fig. 6, fig. 6 is a block diagram of a device for distinguishing the contamination of the insulator of the electrical equipment according to an exemplary embodiment. As shown in fig. 6, the apparatus includes:
the collecting module 51 can be used for collecting pollution monitoring data of the surface of the target power transformation equipment, and pollutants are deposited on the surface of the target power transformation equipment;
the processing module 52 is configured to perform data correction processing and spectral line identification processing on the pollution monitoring data in sequence, so as to obtain a spectral line identification result of an effective spectral line;
The input module 53 may be configured to input the spectral line recognition result into the trained pollution differentiation model to perform classification of the pollution types, so as to obtain a pollution analysis result, where the pollution analysis result at least includes salt density and gray density.
In some embodiments of the present application, the acquisition module 51 may be configured to detect two-dimensional geometric space and one-dimensional spectrum information of a surface of a target transformer device by using an imaging spectrometer, and obtain continuous, narrow-band hyperspectral image data with hyperspectral resolution, where the hyperspectral image data at least includes image information, spectrum information, and image information of any spectrum; and converting the hyperspectral image data into pollution monitoring data in a digital signal form.
In some embodiments of the present application, the processing module 52 may be configured to perform spectral feature recognition based on the pollution monitoring data, and extract a target spectral line with a spectral overlap rate greater than a first preset threshold, and spectral data corresponding to the target spectral line; performing data correction processing on the spectrum data to obtain corrected target spectrum data, wherein the data correction processing at least comprises multi-element scattering correction and atmospheric correction processing; and carrying out spectral line identification based on the target spectral data to obtain a spectral line identification result of the effective spectral line.
In some embodiments of the present application, the processing module 52 may be configured to extract spectral line features of each target spectral line in the target spectral data, where the spectral line features include at least a spectral line wavelength and a spectral line intensity; calculating the feature similarity between the spectral line features and preset spectral line features of a plurality of preset spectral lines; and determining a target spectral line with the corresponding feature similarity larger than a second preset threshold value as an effective spectral line, and determining a preset spectral line which is successfully matched with the corresponding feature of the effective spectral line in a plurality of preset spectral lines as a spectral line identification result of the effective spectral line.
In some embodiments of the present application, the acquisition module 51 may be further configured to acquire an operating temperature of the imaging spectrometer in a corresponding operating environment; the processing module 52 is further configured to perform heating processing by using the infrared radiation film heating device 41 in the combined heat-preserving main control box 4 when the working temperature is determined to be lower than the preset temperature threshold, so that the working temperature reaches the preset temperature threshold, wherein the imaging spectrometer is disposed on the middle heat-insulating layer 42 of the combined heat-preserving main control box 4, and the middle heat-insulating layer 42 is used for isolating the working environment of the imaging spectrometer from the external low-temperature environment.
In some embodiments of the present application, the pollution differentiation model includes a self-encoder AE, a multi-convolution self-encoder MCAE, a hybrid convolution self-encoder FCAE, and a convolutional neural network, and the input module 53 is configured to input spectral line recognition results into the self-encoder AE, the multi-convolution self-encoder MCAE, and the hybrid convolution self-encoder FCAE, respectively, to obtain a combined structural feature between different spectral line elements extracted from the encoder AE, a spatial distribution feature of a plurality of spectral line elements extracted from the multi-convolution self-encoder MCAE, and a hybrid feature corresponding to the combined structural feature and the spatial distribution feature extracted from the hybrid convolution self-encoder FCAE; and carrying out classification and division on the pollution types based on the combined structural features, the spatial distribution features and the mixed features by using a convolutional neural network to obtain a pollution analysis result.
In some embodiments of the present application, as shown in fig. 7, the apparatus further includes: a training module 54;
the training module 54 may be configured to generate a pollution sample configured with a preset feature tag, where the pollution sample is used to simulate a pollution accumulated on a surface of the power transformation device in an actual operating environment, and the pollution sample uses NaCl and CaSO 4 、CaCO 3 、SiO 2 、Al 2 O 3 、Fe 2 O 3 Six compound salt formsSimulating the pollution salt density of the surface of the power transformation equipment, and simulating the pollution ash density accumulated on the surface of the power transformation equipment in an actual running environment by utilizing the mixture kaolin and diatomite of insoluble salt, wherein a preset characteristic label is a pollution analysis result corresponding to a pollution sample; acquiring sample spectral line identification data of a pollution sample; inputting sample spectral line identification data and a preset characteristic label into a pollution distinguishing model, and performing task training of pollution distinguishing on the pollution distinguishing model, wherein in the task training of pollution distinguishing, the sample spectral line identification data is used as an input characteristic, the preset characteristic label is used as a training label, model parameters in the pollution distinguishing model are iteratively updated until the accuracy of the pollution distinguishing model on the pollution distinguishing is greater than a preset accuracy threshold, and the completion of the training of the pollution distinguishing model is judged.
The specific manner in which the various modules perform the operations in the apparatus of the above embodiments have been described in detail in connection with the embodiments of the method, and will not be described in detail herein.
According to the embodiment of the application, after the pollution monitoring data on the surface of the target power transformation equipment are collected, the pollution monitoring data can be subjected to data correction processing and spectral line identification processing, and a spectral line identification result of an effective spectral line is obtained; and inputting the spectral line recognition result into a trained pollution distinguishing model to classify the pollution types, so as to obtain a pollution analysis result comprising salt density and gray density. In the embodiment of the disclosure, the type of the pollution of the power transformation equipment can be automatically evaluated by using the deep learning model under the condition of not damaging the site pollution, and the accurate values of the salt density and the ash density are obtained by calculation, so that the accuracy distinction of the pollution of the insulator is realized.
The insulator contamination distinguishing device for the electric transformation equipment according to the embodiment of the invention is described above from the perspective of the functional module with reference to the accompanying drawings. It should be understood that the functional module may be implemented in hardware, or may be implemented by instructions in software, or may be implemented by a combination of hardware and software modules. Specifically, each step of the embodiment of the method for distinguishing the contamination of the insulator of the electric equipment in the embodiment of the invention can be completed through an integrated logic circuit of hardware in a processor and/or instructions in a software form, and the steps of the embodiment of the invention-applied method for distinguishing the contamination of the insulator of the electric equipment can be directly embodied as the execution of a hardware decoding processor or the execution of the combination of hardware and software modules in the decoding processor. Alternatively, the software modules may be located in a well-established storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, and the like. The storage medium is positioned in the memory, the processor reads the information in the memory, and the steps in the embodiment of the insulator pollution distinguishing method of the power transformation equipment are completed by combining the hardware of the processor.
Fig. 8 is a schematic block diagram of an electronic device 700 in accordance with one embodiment of the present invention.
As shown in fig. 8, the electronic device 700 may include:
a memory 710 and a processor 720, the memory 710 being configured to store a computer program and to transfer the program code to the processor 720. In other words, the processor 720 may call and run a computer program from the memory 710 to implement the method in the embodiment of the present invention.
For example, the processor 720 may be configured to perform the above-described method embodiments according to instructions in the computer program.
In some embodiments of the invention, the processor 720 may include, but is not limited to:
a general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like.
In some embodiments of the invention, the memory 710 includes, but is not limited to:
volatile memory and/or nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (Double Data Rate SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and Direct memory bus RAM (DR RAM).
In some embodiments of the invention, the computer program may be partitioned into one or more modules that are stored in the memory 710 and executed by the processor 720 to perform the methods provided by the invention. The one or more modules may be a series of computer program instruction segments capable of performing the specified functions, the instruction segments describing the execution of the computer program in the controller.
As shown in fig. 8, the electronic device 700 may further include:
a transceiver 730, the transceiver 730 being connectable to the processor 720 or the memory 710.
The processor 720 may control the transceiver 730 to communicate with other devices, and in particular, may transmit data or data to other devices or receive data or data transmitted by other devices. Transceiver 730 may include a transmitter and a receiver. Transceiver 730 may further include antennas, the number of which may be one or more.
It will be appreciated that the various components in the electronic device are connected by a bus system that includes, in addition to a data bus, a power bus, a control bus, and a status signal bus.
The present invention also provides a computer storage medium having stored thereon a computer program which, when executed by a computer, enables the computer to perform the method of the above-described method embodiments. Alternatively, an embodiment of the present invention also provides a computer program product containing instructions which, when executed by a computer, cause the computer to perform the method of the method embodiment described above.
When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy Disk, a hard Disk, a magnetic tape), an optical medium (e.g., a digital video disc (Digital Video Disc, DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.
Those of ordinary skill in the art will appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.
The modules illustrated as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. For example, functional modules in the embodiments of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that changes and substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (7)
1. A method for distinguishing a contamination of an insulator of a power transformation device, comprising:
collecting pollution monitoring data of the surface of target power transformation equipment, wherein pollution is deposited on the surface of the target power transformation equipment;
Sequentially performing data correction processing and spectral line identification processing based on spectral line characteristics on the pollution monitoring data to obtain a spectral line identification result of an effective spectral line, wherein the method comprises the following steps of: performing spectral feature recognition based on the pollution monitoring data, and extracting target spectral lines with spectral overlap ratios larger than a first preset threshold value and spectral data corresponding to the target spectral lines; performing data correction processing on the spectrum data to obtain corrected target spectrum data, wherein the data correction processing at least comprises multi-element scattering correction and atmospheric correction processing; performing spectral line identification based on the target spectrum data to obtain a spectral line identification result of an effective spectral line;
the method for identifying the spectral line based on the target spectrum data to obtain a spectral line identification result of an effective spectral line comprises the following steps: extracting spectral line characteristics of each target spectral line in the target spectrum data, wherein the spectral line characteristics at least comprise spectral line wavelength and spectral line intensity; calculating the feature similarity between the spectral line features and preset spectral line features of a plurality of preset spectral lines; determining a target spectral line with the feature similarity larger than a second preset threshold value as an effective spectral line, and determining the spectral line type of a preset spectral line successfully matched with the corresponding feature of the effective spectral line in the preset spectral lines as a spectral line identification result of the effective spectral line;
Inputting the spectral line recognition result into a trained pollution distinguishing model for classifying and dividing the pollution types to obtain a pollution analysis result, wherein the pollution analysis result at least comprises salt density and ash density, the pollution distinguishing model is obtained by training a pollution sample configured with a preset characteristic label, the pollution sample is used for simulating the pollution accumulated on the surface of the power transformation equipment in an actual running environment, and NaCl and CaSO are used in the pollution sample 4 、CaCO 3 、SiO 2 、Al 2 O 3 、Fe 2 O 3 Six compound salt simulation calculation of pollution salt density on the surface of the power transformation equipment, and simulation calculation of pollution ash density accumulated on the surface of the power transformation equipment in an actual running environment by utilizing the mixture of insoluble salt, namely kaolin and diatomite, wherein the preset characteristic label is the pollution sampleThe corresponding pollution analysis result;
the pollution distinguishing model comprises a self-encoder AE, a multi-convolution self-encoder MCAE, a mixed convolution self-encoder FCAE and a convolution neural network, wherein the spectral line identification result is input into the trained pollution distinguishing model to carry out pollution type classification and division, and a pollution analysis result is obtained, and the method comprises the following steps:
inputting the spectral line recognition result into the self-encoder AE, the multi-convolution self-encoder MCAE and the mixed convolution self-encoder FCAE respectively to obtain a combined structural feature among different spectral line elements extracted by the self-encoder AE, a spatial distribution feature of a plurality of spectral line elements extracted by the multi-convolution self-encoder MCAE and a mixed feature corresponding to the combined structural feature and the spatial distribution feature extracted by the mixed convolution self-encoder FCAE; and carrying out classification and division on the pollution types by utilizing the convolutional neural network based on the combined structural features, the spatial distribution features and the mixed features to obtain a pollution analysis result.
2. The method of claim 1, wherein the collecting the pollution monitoring data of the surface of the target power transformation device comprises:
detecting two-dimensional geometric space and one-dimensional spectrum information of the surface of the target transformer equipment by using an imaging spectrometer, and acquiring continuous and narrow-band hyperspectral image data with hyperspectral resolution, wherein the hyperspectral image data at least comprises image information, spectrum information and image information of any spectrum;
and converting the hyperspectral image data into pollution monitoring data in a digital signal form.
3. The method according to claim 2, wherein the method further comprises:
collecting the working temperature of the imaging spectrometer under the corresponding working environment;
when the working temperature is judged to be lower than a preset temperature threshold, an infrared radiation film heating device in the combined heat-preserving main control box is utilized for heating treatment, so that the working temperature reaches the preset temperature threshold, wherein the imaging spectrometer is arranged on an intermediate heat-insulating layer of the combined heat-preserving main control box, and the intermediate heat-insulating layer is used for isolating the working environment of the imaging spectrometer and the external low-temperature environment.
4. A method according to any one of claims 1 to 3, further comprising a training method of the fouling differentiation model, comprising:
Generating a pollution sample configured with a preset characteristic label;
acquiring sample spectral line identification data of the pollution sample;
inputting the sample spectral line identification data and the preset feature label into a pollution distinguishing model, and performing task training of pollution distinguishing on the pollution distinguishing model, wherein in the task training of pollution distinguishing, the sample spectral line identification data is used as an input feature, the preset feature label is used as a training label, model parameters in the pollution distinguishing model are iteratively updated until the accuracy of the pollution distinguishing model on pollution distinguishing is greater than a preset accuracy threshold, and the completion of the training of the pollution distinguishing model is judged.
5. A device for distinguishing a contamination of an insulator of a power transformation apparatus, comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring pollution monitoring data of the surface of target power transformation equipment, and pollutants are deposited on the surface of the target power transformation equipment;
the processing module is used for sequentially carrying out data correction processing and spectral line identification processing based on spectral line characteristics on the pollution monitoring data to obtain a spectral line identification result of an effective spectral line, and comprises the following steps: performing spectral feature recognition based on the pollution monitoring data, and extracting target spectral lines with spectral overlap ratios larger than a first preset threshold value and spectral data corresponding to the target spectral lines; performing data correction processing on the spectrum data to obtain corrected target spectrum data, wherein the data correction processing at least comprises multi-element scattering correction and atmospheric correction processing; performing spectral line identification based on the target spectrum data to obtain a spectral line identification result of an effective spectral line;
The method for identifying the spectral line based on the target spectrum data to obtain a spectral line identification result of an effective spectral line comprises the following steps: extracting spectral line characteristics of each target spectral line in the target spectrum data, wherein the spectral line characteristics at least comprise spectral line wavelength and spectral line intensity; calculating the feature similarity between the spectral line features and preset spectral line features of a plurality of preset spectral lines; determining a target spectral line with the feature similarity larger than a second preset threshold value as an effective spectral line, and determining the spectral line type of a preset spectral line successfully matched with the corresponding feature of the effective spectral line in the preset spectral lines as a spectral line identification result of the effective spectral line;
the input module is used for inputting the spectral line recognition result into a trained pollution distinguishing model to conduct pollution type classification and division to obtain a pollution analysis result, the pollution analysis result at least comprises salt density and ash density, the pollution distinguishing model is obtained by training a pollution sample provided with a preset characteristic label, the pollution sample is used for simulating pollution accumulated on the surface of power transformation equipment in an actual operation environment, and NaCl and CaSO are used in the pollution sample 4 、CaCO 3 、SiO 2 、Al 2 O 3 、Fe 2 O 3 The method comprises the steps of simulating and calculating pollution salt density on the surface of the power transformation equipment by using six compound salts, and simulating and calculating pollution ash density accumulated on the surface of the power transformation equipment in an actual running environment by using the mixture kaolin and diatomite of insoluble salts, wherein the preset characteristic label is a pollution analysis result corresponding to the pollution sample;
The pollution distinguishing model comprises a self-encoder AE, a multi-convolution self-encoder MCAE, a mixed convolution self-encoder FCAE and a convolution neural network, and the input module is used for:
inputting the spectral line recognition result into the self-encoder AE, the multi-convolution self-encoder MCAE and the mixed convolution self-encoder FCAE respectively to obtain a combined structural feature among different spectral line elements extracted by the self-encoder AE, a spatial distribution feature of a plurality of spectral line elements extracted by the multi-convolution self-encoder MCAE and a mixed feature corresponding to the combined structural feature and the spatial distribution feature extracted by the mixed convolution self-encoder FCAE; and carrying out classification and division on the pollution types by utilizing the convolutional neural network based on the combined structural features, the spatial distribution features and the mixed features to obtain a pollution analysis result.
6. An electronic device, comprising:
a processor and a memory for storing a computer program, the processor being for invoking and running the computer program stored in the memory to perform the method of any of claims 1-4.
7. A computer readable storage medium storing a computer program for causing a computer to perform the method of any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311811269.3A CN117470867B (en) | 2023-12-27 | 2023-12-27 | Method and device for distinguishing contamination of insulator of power transformation equipment and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311811269.3A CN117470867B (en) | 2023-12-27 | 2023-12-27 | Method and device for distinguishing contamination of insulator of power transformation equipment and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117470867A CN117470867A (en) | 2024-01-30 |
| CN117470867B true CN117470867B (en) | 2024-03-26 |
Family
ID=89633280
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311811269.3A Active CN117470867B (en) | 2023-12-27 | 2023-12-27 | Method and device for distinguishing contamination of insulator of power transformation equipment and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117470867B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117517335B (en) * | 2023-12-27 | 2024-03-29 | 国网辽宁省电力有限公司电力科学研究院 | System and method for monitoring pollution of insulator of power transformation equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108124142A (en) * | 2018-01-31 | 2018-06-05 | 西北工业大学 | Images steganalysis system and method based on RGB depth of field camera and EO-1 hyperion camera |
| CN109674481A (en) * | 2017-10-19 | 2019-04-26 | 三星电子株式会社 | It obtains the device and method of individuation unit spectrum and estimates the device and method of biotic component |
| CN110261405A (en) * | 2019-07-31 | 2019-09-20 | 西南交通大学 | Insulator contamination ingredient recognition methods based on micro- hyperspectral technique |
| CN110376214A (en) * | 2019-08-13 | 2019-10-25 | 西南交通大学 | Insulator dirty degree non-contact detection method based on hyperspectral technique |
| CN110427057A (en) * | 2019-07-03 | 2019-11-08 | 北京雪迪龙科技股份有限公司 | Temperature control method, temperature control device and the gas analyzer of spectrometer |
| CN113011499A (en) * | 2021-03-22 | 2021-06-22 | 安徽大学 | Hyperspectral remote sensing image classification method based on double-attention machine system |
| CN115376005A (en) * | 2022-08-01 | 2022-11-22 | 广东电网有限责任公司广州供电局 | Insulator pollution component identification method and system based on spectrum resolving network |
| CN116958036A (en) * | 2023-03-28 | 2023-10-27 | 南昌航空大学 | Method for inspecting pollution state of insulator by unmanned aerial vehicle based on hyperspectral technology |
| CN116952862A (en) * | 2022-03-31 | 2023-10-27 | 上海禾赛科技有限公司 | Detection method of laser gas telemetry instrument and laser gas telemetry instrument |
| CN117051556A (en) * | 2022-05-05 | 2023-11-14 | 青岛海尔智能技术研发有限公司 | Method, device, equipment and storage medium for identifying clothing material |
-
2023
- 2023-12-27 CN CN202311811269.3A patent/CN117470867B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109674481A (en) * | 2017-10-19 | 2019-04-26 | 三星电子株式会社 | It obtains the device and method of individuation unit spectrum and estimates the device and method of biotic component |
| CN108124142A (en) * | 2018-01-31 | 2018-06-05 | 西北工业大学 | Images steganalysis system and method based on RGB depth of field camera and EO-1 hyperion camera |
| CN110427057A (en) * | 2019-07-03 | 2019-11-08 | 北京雪迪龙科技股份有限公司 | Temperature control method, temperature control device and the gas analyzer of spectrometer |
| CN110261405A (en) * | 2019-07-31 | 2019-09-20 | 西南交通大学 | Insulator contamination ingredient recognition methods based on micro- hyperspectral technique |
| CN110376214A (en) * | 2019-08-13 | 2019-10-25 | 西南交通大学 | Insulator dirty degree non-contact detection method based on hyperspectral technique |
| CN113011499A (en) * | 2021-03-22 | 2021-06-22 | 安徽大学 | Hyperspectral remote sensing image classification method based on double-attention machine system |
| CN116952862A (en) * | 2022-03-31 | 2023-10-27 | 上海禾赛科技有限公司 | Detection method of laser gas telemetry instrument and laser gas telemetry instrument |
| CN117051556A (en) * | 2022-05-05 | 2023-11-14 | 青岛海尔智能技术研发有限公司 | Method, device, equipment and storage medium for identifying clothing material |
| CN115376005A (en) * | 2022-08-01 | 2022-11-22 | 广东电网有限责任公司广州供电局 | Insulator pollution component identification method and system based on spectrum resolving network |
| CN116958036A (en) * | 2023-03-28 | 2023-10-27 | 南昌航空大学 | Method for inspecting pollution state of insulator by unmanned aerial vehicle based on hyperspectral technology |
Non-Patent Citations (3)
| Title |
|---|
| "Method for detecting the pollution degree of naturally contaminated insulator based on hyperspectral characteristics";Yin Chengfeng等;《High Voltage》;20210303;第6卷(第6期);第1031-1039页 * |
| "Contaminati Level Monitoring Techniques for High-Voltage Insulators： A Review";Luqman Maraaba等;《energies》;20221017;第15卷;第1-32页 * |
| "基于SAM-ED光谱匹配的绝缘子污秽类型检测方法研究";刘益岑等;《光散射学报》;20230930;第35卷(第3期);第296-302页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117470867A (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109581372B (en) | Ecological environment remote sensing monitoring method | |
| CN117470867B (en) | Method and device for distinguishing contamination of insulator of power transformation equipment and electronic equipment | |
| Hilburn et al. | Development and interpretation of a neural-network-based synthetic radar reflectivity estimator using GOES-R satellite observations | |
| US11719853B2 (en) | Underground infrastructure sensing using unmanned aerial vehicle (UAV) | |
| Mushore et al. | Remote sensing applications in monitoring urban growth impacts on in-and-out door thermal conditions: A review | |
| CN111094956A (en) | Processing the thermographic image with a neural network to identify Corrosion Under Insulation (CUI) | |
| CN109799442B (en) | Insulator pollution flashover prediction method and system based on airborne hyperspectrum | |
| CA3093959C (en) | Image processing techniques for multi-sensor inspection of pipe interiors | |
| CN109946235B (en) | Multilayer cloud inversion method of wind cloud 4A meteorological satellite multichannel scanning imaging radiometer | |
| Friman et al. | Methods for large-scale monitoring of district heating systems using airborne thermography | |
| CN111191673B (en) | Ground surface temperature downscaling method and system | |
| CN108152235B (en) | Heavy metal content inversion method combining soil indoor and outdoor spectra | |
| Bley et al. | A threshold-based cloud mask for the high-resolution visible channel of Meteosat Second Generation SEVIRI | |
| Ji et al. | Solar photovoltaic module detection using laboratory and airborne imaging spectroscopy data | |
| Huertas-Tato et al. | Using a multi-view convolutional neural network to monitor solar irradiance | |
| Du et al. | Detection of crack growth in asphalt pavement through use of infrared imaging | |
| Ardiansyah et al. | Percent of building density (PBD) of urban environment: a multi-index approach based study in DKI Jakarta Province | |
| Garkusha et al. | Using Sentinel-1 data for monitoring of soil moisture | |
| Cao et al. | MODIS observations reveal decrease in lake suspended particulate matter across China over the past two decades | |
| CN110321528B (en) | Hyperspectral image soil heavy metal concentration assessment method based on semi-supervised geospatial regression analysis | |
| CN116227142A (en) | Daily earth surface temperature reconstruction method and device based on MODIS remote sensing data | |
| Fawzi et al. | Heat island detection in coal mining areas using multitemporal remote sensing | |
| CN117517335B (en) | System and method for monitoring pollution of insulator of power transformation equipment | |
| Flusche et al. | Defining a process to fuse polarimetric and spectral data for target detection and explore the trade space via simulation | |
| Nielsen et al. | The distribution in time and space of savanna fires in Burkina Faso as determined from NOAA AVHRR data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |