CN106596579A - Insulator contamination condition detection method based on multispectral image information fusion - Google Patents
Insulator contamination condition detection method based on multispectral image information fusion Download PDFInfo
- Publication number
- CN106596579A CN106596579A CN201611004199.0A CN201611004199A CN106596579A CN 106596579 A CN106596579 A CN 106596579A CN 201611004199 A CN201611004199 A CN 201611004199A CN 106596579 A CN106596579 A CN 106596579A
- Authority
- CN
- China
- Prior art keywords
- image
- insulator
- information fusion
- insulator contamination
- detection method
- 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
Classifications
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention relates to an insulator contamination condition detection method based on multispectral image information fusion. The method comprises the following steps that the insulator contamination condition is detected through three spectral images of the visible image, the infrared image and the ultraviolet image simultaneously; the insulator contamination condition is comprehensively evaluated through information fusion according to the obtained spectral images. Compared with the prior art, the insulator contamination condition detection method has the advantages that the three image detection methods do not interfere with one another, the detection accuracy rate is high, non-contact is achieved, live detection is achieved, the detection speed is high, and the reliability of the detection result is high.
Description
Technical field
The present invention relates to high voltage electric equipment fault detection and diagnosis, more particularly, to a kind of multispectral image information is based on
The insulator contamination condition detection method of fusion.
Background technology
Insulator receives much concern as the most widely used insulator arrangement of transmission line of electricity, its safety and stability.With
The aggravation of atmospheric pollution, insulator surface contamination is even more serious, and the rising of electric pressure also increases insulator and dirt occurs
The risk of dirty flashover.Therefore, detect insulator contamination state, insulator contamination prevented, to safeguarding that transmission line safety is stably transported
Row tool is of great significance.
At present, detect that the method for insulator contamination state can be divided into contact and contactless two big class.Contact method
Mainly include leakage current method, equivalent salt deposit density method, electrical conductivity method etc., such method is by measurement insulator surface leakage electricity
The direct parameters such as stream, equivalent salt deposit density, electrical conductivity judge insulator contamination state, and accuracy rate is high, but metering system is complicated, work
Work amount is big, and Part Methods need to have a power failure and carry out；Contactless method by detection contaminated insulator it is powered when produced sound, light,
The indirect signals such as heat, reductive analysis these signal characteristics judge the gradation for surface pollution of insulator.Contactless method mainly includes light arteries and veins
Rush detection method, acoustic wave detection, visual light imaging method, infrared thermal imagery method, ultraviolet image method etc..Light pulse detection method and sound wave are examined
Survey method is easily disturbed by environmental background noise, and the sensitivity of signals collecting is not high；Visual light imaging method, infrared thermal imagery method and purple
Outer imaging method is special by obtaining the signals such as insulator surface color, insulator card temperature rise, insulator surface shelf depreciation respectively
Levy, insulator contamination state is estimated, the features such as with simple to operate, live detection, fault location, can in a large number save inspection
The workload of personnel is repaiied, but because its accuracy is difficult to meet the requirement applied in engineering, needs to make improvements.
The content of the invention
The purpose of the present invention is exactly the defect in order to overcome above-mentioned prior art to exist and provides a kind of based on multispectral figure
As the insulator contamination condition detection method of information fusion.The present invention is by with reference to visual light imaging, infrared thermal imagery, ultraviolet imagery
Three kinds of detection methods are estimated to insulator contamination state, improve Detection accuracy, and make it preferably be applied to power transmission line
The insulator contamination state-detection on road.The present invention have detection speed is fast, accuracy is high, contactless, live detection, by environment
The advantages of factor affects little.The present invention relates to the pollution severity of insulators state diagram for field of power transformation such as transformer station, transmission line of electricity
As recognition detection method.
The purpose of the present invention can be achieved through the following technical solutions：
A kind of insulator contamination condition detection method based on multispectral image information fusion, the method includes following step
Suddenly：
S1, while being entered to insulator contamination state by visible images, infrared image, three kinds of spectrum pictures of ultraviolet image
Row detection；
S2, three kinds of spectrum pictures according to obtained by S1 are by information fusion, overall merit insulator contamination state.
Three kinds of spectrum pictures obtain insulator surface equivalent salt deposit density, by exhausted after information fusion in step S2
Edge sublist face equivalent salt deposit density evaluates insulator contamination state.
Visible images are respectively obtained by visible images, infrared image, three kinds of spectrum pictures of ultraviolet image in step S1
Eigenvalue, Infrared Image Features value and ultraviolet image eigenvalue, it will be seen that light image eigenvalue, Infrared Image Features value and ultraviolet
Image feature value is by information fusion, overall merit insulator contamination state.
Described visible images are obtained insulator disk after Visual image processing, feature extraction and feature selection
Face V component average is used as visible images eigenvalue.
Described infrared image is obtained insulator card most after infrared image processing, feature extraction and feature selection
Big temperature rise is used as Infrared Image Features value.
Described ultraviolet image is obtained insulator surface most after ultraviolet image process, feature extraction and feature selection
Big electric discharge facula area is used as ultraviolet image eigenvalue.
Multispectral image BP neural network, described god are built to described visible images, infrared image, ultraviolet image
The |input paramete of Jing networks is visible images eigenvalue, Infrared Image Features value, ultraviolet image eigenvalue, is output as insulator
Surface equivalent salt deposit density.
The BP neural network needs sample to be trained it, accordingly by neural network information fusion method to insulator
Filthy state is estimated.
The training step of BP neural network is as follows：
S1, netinit, according to the practical situation of object of study input layer, hidden layer and the output layer god of network are determined
Jing units number；
S2, carry out fl transmission signal of change using training sample；
S3, the adjustment that output layer and hidden layer connection weight are carried out using error backpropagation algorithm；
The given iterationses of S4, basis and error requirements judge whether network training terminates, if reaching given iteration
Number of times meets error requirements, then stop iteration, and training terminates, and otherwise continues step S3, until reaching given iterationses
Or till network error function E meets required precision.
When arbitrary detection method cannot be carried out in visible images detection, infrared image detection, ultraviolet image detection, other
Detection method still can be normally carried out.
Compared with prior art, the present invention has advantages below：
(1) present invention incorporates visual light imaging, infrared thermal imagery, three kinds of detection methods of ultraviolet imagery are to insulator contamination shape
State is estimated, and from the filthy state of three angle detection insulators, three kinds of image detecting methods do not interfere with each other, Detection accuracy
Height, the reliability of testing result is high.
(2) three kinds of image detecting methods that the present invention is combined are respectively provided with simple to operate, contactless, live detection, inspection
The features such as degree of testing the speed is fast, can on the spot provide insulator contamination state-detection result during detection, facilitate guide field staff and
Shi Qingxi pollution severity of insulators.
(3) applied range of the present invention, for the insulator of different type difference electric pressure, is obtaining a certain amount of sample
After this is trained to the BP neural network in the present invention, you can carry out filthy state-detection to such insulator.
(4) still can normally detect when present invention image a kind of wherein cannot be obtained, be limited little by environmental factorss, three kinds of figures
As being shot in the daytime.Infrared image shoots and ultraviolet image shoots and also can carry out at night, is applicable to contact net
The night vehicle-mounted line walking of external insulation equipment.
Description of the drawings
Fig. 1 is the flow chart of the inventive method；
Fig. 2 is the visible images master drawing that the present invention shoots；
Fig. 3 is Visual image processing design sketch of the present invention；
Fig. 4 is the infrared image master drawing that the present invention shoots；
Fig. 5 is infrared image processing design sketch of the present invention；
Fig. 6 is the ultraviolet image master drawing that the present invention shoots；
Fig. 7 is ultraviolet image treatment effect figure of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is a part of embodiment of the present invention, rather than whole embodiments.Based on this
Embodiment in bright, the every other reality that those of ordinary skill in the art are obtained on the premise of creative work is not made
Example is applied, should all belong to the scope of protection of the invention.
Embodiment
Based on the insulator contamination condition detection method of multispectral image information fusion, while by visible images, red
Outer image, three kinds of spectrum pictures of ultraviolet image detect that described visible images are by visible ray to insulator contamination state
Camera is shot, and described infrared image is shot by thermal infrared imager, and described ultraviolet image is entered by ultraviolet imager
Row is recorded, and three kinds of described spectrum pictures carry out information fusion by BP neural network, detect insulator contamination state.
As shown in figure 1, the insulator contamination condition detection method based on multispectral image information fusion is by combining insulation
Sub- visible images, three kinds of images of infrared image and ultraviolet image are detected to insulator contamination state.
Insulator visible images are shot by high definition Visible Light Camera under natural light, and as shown in Figure 2 (Fig. 2 is not
Must scheme), need to adjust camera position and parameter during shooting, image range is covered whole insulator and is ensured in image absolutely
Edge height is more than the 2/3 of picture altitude, while picture centre reply quasi-insulator card.Obtain insulator visible images
Afterwards, by Visual image processing, by insulator card and background segment, insulator card filth coloured image, such as Fig. 3 are obtained
(Fig. 3 is not required figure), because insulator disk face color and background color differ greatly, therefore in segmentation insulator card and background
Shi Caiyong regions seed split-run is carried out.By feature extraction, the various features value of insulator card filth coloured image is calculated,
Visible images can extract altogether R, G, B, H, S, the average of V component, intermediate value, maximum, minima, mode, extreme difference, variance, partially
66 eigenvalues such as degree, kurtosis, entropy, energy.The present invention by research defilement and insulation subsample, with Fisher criterions from numerous
Insulator card V component average is have selected in eigenvalue special as the visible images that can most show insulator card contamination data
Value indicative, therefore in detection, need to only extract the insulator card V component average of visible images.
Insulator Infrared Image is shot by thermal infrared imager, as shown in Figure 4 (Fig. 4 is not required figure), is shot in day
Between and night can carry out, need to adjust camera position and parameter during shooting, enable image range to cover whole insulator.Obtain
After Insulator Infrared Image, by infrared image processing, read infrared image temperature matrices and shown absolutely with the form of gray-scale maps
Edge subimage Distribution of temperature rise, because contaminated insulator surface temperature rise is apparently higher than environment temperature rise, the performance on gray-scale maps also has
Significantly difference, edge extracting is carried out using canny operators to image, realizes effective segmentation of insulator card and background,
Insulator card temperature rise image is obtained, as shown in Figure 5 (Fig. 5 is not required figure).By feature extraction, insulator card temperature is calculated
The various features value of image is risen, infrared image can extract altogether average, intermediate value, maximum, minima, the crowd of insulator card temperature rise
11 eigenvalues such as value, extreme difference, variance, the degree of bias, kurtosis, entropy, energy.The present invention is used by research defilement and insulation subsample
Fisher criterions are comformed and have selected in multiple characteristic values insulator card maximum temperature rise as can most show the filthy letter of insulator card
The Infrared Image Features value of breath, therefore in detection, need to only extract the insulator card maximum temperature rise of infrared image.
Insulator ultraviolet image is shot by ' day is blind ' type ultraviolet imager, as shown in Figure 6 (Fig. 6 is not required figure),
Shoot can be carried out with night in the daytime, need to adjust camera position and parameter during shooting, enable image range cover it is whole absolutely
Edge.Because Insulator Contaminant Discharge is dynamic process, so needing recording ultraviolet video to carry out Insulator Contaminant Discharge
Record, to record duration and be about 10s, recording frame number is 200 frames.After obtaining Insulator Contaminant Discharge ultraviolet video, need to video
In each frame ultraviolet image carry out ultraviolet image process, ultraviolet hot spot is partitioned into from ultraviolet image by binary segmentation
Come, obtain ultraviolet hot spot image, as shown in Figure 7 (Fig. 7 is not required figure), and calculate facula area size.By feature extraction,
Calculate the average of ultraviolet hot spot in 200 frame ultraviolet images, intermediate value, maximum, minima, mode, extreme difference, variance, the degree of bias, high and steep
11 eigenvalues such as degree, entropy, energy.The present invention is comformed multiple features by research defilement and insulation subsample with Fisher criterions
The maximum electric discharge facula area of insulator surface is have selected in value as the ultraviolet image that can most show insulator card contamination data
Eigenvalue, therefore in detection, need to only extract the maximum electric discharge facula area of insulator surface of ultraviolet image.
A certain amount of defilement and insulation subsample is obtained, with Visible Light Camera, thermal infrared imager, ultraviolet imager and meter
Calculation machine image processing techniquess obtain insulator card V component average, the insulator card of infrared image of its visible images most
Big temperature rise, the maximum electric discharge facula area of insulator surface of ultraviolet image, and determine insulator surface equivalent salt deposit density.Will be upper
Three eigenvalues are stated as input, insulator surface equivalent salt deposit density as output, with measured sample parameter to many
Spectrum picture BP neural network is trained.
When insulator contamination state-detection is carried out, with Visible Light Camera, thermal infrared imager, ultraviolet imager phase is shot
Visible images, infrared image and the ultraviolet image answered, by Visual image processing technology, infrared image processing technology, purple
Outer image processing techniquess and feature extraction obtain insulator card V component average, the insulation of infrared image of visible images
The maximum electric discharge facula area of the insulator surface of sub-disk face maximum temperature rise and ultraviolet image, three eigenvalue inputs are trained
Multispectral image BP neural network, you can obtain insulator surface equivalent salt deposit density.
The |input paramete of described BP neural network is visible images, infrared image, the eigenvalue of ultraviolet image, is exported
Parameter is insulator surface equivalent salt deposit density, and needs to obtain a certain amount of sample neutral net is trained.BP is neural
The training process of network is as follows：
(1) carry out netinit first, according to the practical situation of object of study determine the input layer of network, hidden layer and
Output layer neuron number n (n=3), m (m=10) and s (s=1), then carry out the initialization of each parameter of BP neural network, right
The weights of hidden layer and output layer carry out random assignment with threshold value, while determining error precision ε (ε=e-5), iterationses M (M=
1000), the parameter such as learning rate and each layer neuron excitation function.
(2) fl transmission signal of change is carried out using training sample.Input layer is input into P training sample, respectively X1,
X2,…,XP, wherein each sample is X=[x1,x2,…,xn]T, desired output is T1,T2,…,TP, wherein each be output as T=
[t1,t2,…,ts]T, the corresponding desired output of one training sample of expression.If the input of hidden neuron is hj, it is output as Oj,
ωijFor input layer and the network connection weights of hidden layer, θjFor the threshold value of hidden neuron, the input of hidden neuron, output point
It is not
If ωjkFor hidden layer and the network connection weights of output layer, θkFor the threshold value of output layer neuron, its input hkWith it is defeated
Go out ykRespectively
(3) adjustment of output layer and hidden layer connection weight is carried out using error backpropagation algorithm.Through forward calculation
Afterwards, by corresponding reality output Y of training sample1,Y2,…,YPWith desired output T1,T2,…,TPIt is compared, by correction error
Successively carry out back propagation from output layer to input layer, make the connection weight and neuron threshold value of output layer and hidden layer constantly to
The direction that reduces error function E is adjusted, and makes YPAnd TPBetween error reduce as far as possible.The mean square error letter of network
Number E is defined as follows
For the correction error of each group of sample, output layer and each neuron of hidden layerWithRespectively
For the connection weight of each group of sample, output layer and hidden layer and the adjustment formula of neuron threshold value are
In formula, n0To train iterationses, η is training pace.
(4) judge whether network training terminates according to given iterationses and error requirements.If reaching given iteration
Number of times meets error requirements, then stop iteration, and training terminates, and otherwise continues step (3), until reaching given iterationses
Or till network error function E meets required precision.
Described visible images eigenvalue is by the exhausted of Visual image processing, feature extraction and feature selection acquisition
Edge sub-disk face V component average.Described Visual image processing includes image gray processing, image segmentation and image restoring three
Step, described image gray processing is that color visible image is converted to into gray level image；What described image segmentation was taken is region
Seed split-run, separates insulator card and background；Described image reduction is to add original color information for insulator card.
Described Infrared Image Features value is the insulator obtained by infrared image processing, feature extraction and feature selection
Card maximum temperature rise.Described infrared image processing include obtain temperature matrices, draw temperature matrices gray-scale maps, edge extracting,
Four steps of image segmentation, the acquisition temperature matrices read the subsidiary temperature matrices of infrared image；The drafting temperature matrices
Gray-scale maps are the forms that temperature matrices are depicted as gray-scale maps, and minimum temperature gray scale 0 is represented, the maximum temperature table of gray scale 255
Show；The edge extracting is that the insulator contour on temperature gray-scale maps is extracted with canny operators；Described image is split
It is to be separated the gray level image in profile with the image outside profile, that is, splits insulator card and background.
Described ultraviolet image eigenvalue is the insulator obtained by ultraviolet image process, feature extraction and feature selection
The maximum electric discharge facula area in surface.The ultraviolet image is processed to be needed to carry out gradation of image to each two field picture in ultraviolet video
Change, binary segmentation, facula area calculate three steps, and described image gray processing is that color visible image is converted to into gray-scale maps
Picture；It by a threshold value by greyscale image transitions is bianry image that the binary segmentation is, the threshold value is set to 250；The light
Speckle areal calculation be by binary segmentation after white hot spot shared by pixel carry out statistical computation, facula area is represented with elemental area
Size.
Described feature selection is carried out by comparing Fisher criterions J value, selectes the maximum feature of Fisher criterions J value
It is worth as the eigenvalue extracted required for correspondence image.
The above, the only specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, various equivalent modifications can be readily occurred in or replaced
Change, these modifications or replacement all should be included within the scope of the present invention.Therefore, protection scope of the present invention should be with right
The protection domain of requirement is defined.
Claims (10)
1. a kind of insulator contamination condition detection method based on multispectral image information fusion, it is characterised in that the method bag
Include following steps：
S1, while being examined to insulator contamination state by visible images, infrared image, three kinds of spectrum pictures of ultraviolet image
Survey；
S2, three kinds of spectrum pictures according to obtained by S1 are by information fusion, overall merit insulator contamination state.
2. a kind of insulator contamination condition detection method based on multispectral image information fusion according to claim 1,
Characterized in that, three kinds of spectrum pictures obtain insulator surface equivalent salt deposit density after information fusion in step S2, pass through
Insulator surface equivalent salt deposit density evaluates insulator contamination state.
3. a kind of insulator contamination condition detection method based on multispectral image information fusion according to claim 2,
Characterized in that, respectively obtaining visible ray figure by visible images, infrared image, three kinds of spectrum pictures of ultraviolet image in step S1
As eigenvalue, Infrared Image Features value and ultraviolet image eigenvalue, it will be seen that light image eigenvalue, Infrared Image Features value and purple
Outer image feature value is by information fusion, overall merit insulator contamination state.
4. a kind of insulator contamination condition detection method based on multispectral image information fusion according to claim 3,
Characterized in that, described visible images can be insulated after Visual image processing, feature extraction and feature selection
Sub-disk face V component average is used as visible images eigenvalue.
5. a kind of insulator contamination condition detection method based on multispectral image information fusion according to claim 3,
Characterized in that, described infrared image is obtained insulator disk after infrared image processing, feature extraction and feature selection
Face maximum temperature rise is used as Infrared Image Features value.
6. a kind of insulator contamination condition detection method based on multispectral image information fusion according to claim 3,
Characterized in that, described ultraviolet image can obtain the sublist that insulate after ultraviolet image process, feature extraction and feature selection
The maximum electric discharge facula area in face is used as ultraviolet image eigenvalue.
7. a kind of insulator contamination condition detection method based on multispectral image information fusion according to claim 3,
Characterized in that, multispectral image BP neural network is built to described visible images, infrared image, ultraviolet image, it is described
The |input paramete of neutral net be visible images eigenvalue, Infrared Image Features value, ultraviolet image eigenvalue, be output as absolutely
Edge sublist face equivalent salt deposit density.
8. a kind of insulator contamination condition detection method based on multispectral image information fusion according to claim 7,
Characterized in that, the BP neural network needs sample to be trained it, accordingly by neural network information fusion method to exhausted
Edge filth state is estimated.
9. a kind of insulator contamination condition detection method based on multispectral image information fusion according to claim 8,
Characterized in that, the training step of BP neural network is as follows：
S1, netinit, according to the practical situation of object of study input layer, hidden layer and the output layer neuron of network are determined
Number；
S2, carry out fl transmission signal of change using training sample；
S3, the adjustment that output layer and hidden layer connection weight are carried out using error backpropagation algorithm；
The given iterationses of S4, basis and error requirements judge whether network training terminates, if reaching given iterationses
Or meet error requirements, then stop iteration, training terminates, and otherwise continues step S3, until reach given iterationses or
Till network error function E meets required precision.
10. a kind of insulator contamination condition detection method based on multispectral image information fusion according to claim 1,
Characterized in that, when arbitrary detection method cannot be carried out in visible images detection, infrared image detection, ultraviolet image detection,
Other detection methods still can be normally carried out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611004199.0A CN106596579A (en) | 2016-11-15 | 2016-11-15 | Insulator contamination condition detection method based on multispectral image information fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611004199.0A CN106596579A (en) | 2016-11-15 | 2016-11-15 | Insulator contamination condition detection method based on multispectral image information fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106596579A true CN106596579A (en) | 2017-04-26 |
Family
ID=58590926
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611004199.0A Pending CN106596579A (en) | 2016-11-15 | 2016-11-15 | Insulator contamination condition detection method based on multispectral image information fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106596579A (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108061847A (en) * | 2017-12-23 | 2018-05-22 | 华北电力大学（保定） | Dry-type reactor epoxy resin insulating medium cracking detection method |
| CN108072667A (en) * | 2017-09-28 | 2018-05-25 | 江苏省电力试验研究院有限公司 | Insulator contamination level detection method and system based on EO-1 hyperion |
| CN108280449A (en) * | 2018-02-06 | 2018-07-13 | 国网山西省电力公司电力科学研究院 | Power equipment image collecting method based on multispectral sensor group |
| CN108333488A (en) * | 2018-02-08 | 2018-07-27 | 南京视道信息技术有限公司 | The arcing detection method blended based on ultraviolet, infrared and optical imagery |
| CN108760814A (en) * | 2018-06-21 | 2018-11-06 | 湖南湖大华龙电气与信息技术有限公司 | A kind of composite insulator is infrared to combine intelligent detecting method and its device with millimeter wave |
| CN109283143A (en) * | 2018-11-23 | 2019-01-29 | 云南电网有限责任公司普洱供电局 | A kind of infrared, ultraviolet, visible light image procossing emerging system and method |
| CN109470628A (en) * | 2018-09-29 | 2019-03-15 | 江苏新绿能科技有限公司 | Contact net insulator contamination condition detection method |
| CN110346699A (en) * | 2019-07-26 | 2019-10-18 | 国网山东省电力公司电力科学研究院 | Insulator arc-over information extracting method and device based on ultraviolet image processing technique |
| CN110736507A (en) * | 2019-11-01 | 2020-01-31 | 国网河北省电力有限公司电力科学研究院 | method for detecting defect of insulator for transmission line and terminal equipment |
| CN111257242A (en) * | 2020-02-27 | 2020-06-09 | 西安交通大学 | High-spectrum identification method for pollutant components of insulator |
| CN112381784A (en) * | 2020-11-12 | 2021-02-19 | 国网浙江省电力有限公司信息通信分公司 | Equipment detecting system based on multispectral image |
| CN112414950A (en) * | 2020-11-05 | 2021-02-26 | 西南交通大学 | Insulator equivalent salt deposit density detection method cooperating with hyperspectral and infrared technologies |
| CN112541478A (en) * | 2020-12-25 | 2021-03-23 | 国网吉林省电力有限公司信息通信公司 | Insulator string stain detection method and system based on binocular camera |
| CN112611732A (en) * | 2020-12-21 | 2021-04-06 | 中国电力科学研究院有限公司 | Method and system for establishing intermediate infrared spectrum chart library for silicone rubber for composite insulator |
| US20210131987A1 (en) * | 2019-11-01 | 2021-05-06 | Caterpillar Inc. | Grading a piston with deposits using thermal scan data |
| CN112966576A (en) * | 2021-02-24 | 2021-06-15 | 西南交通大学 | System and method for aiming insulator water washing robot based on multi-light source image |
| CN113065484A (en) * | 2021-04-09 | 2021-07-02 | 华北电力大学（保定） | Insulator contamination state assessment method based on ultraviolet spectrum |
| CN113095499A (en) * | 2021-03-26 | 2021-07-09 | 云南电网有限责任公司电力科学研究院 | Insulator equivalent salt deposit density prediction method |
| CN113361631A (en) * | 2021-06-25 | 2021-09-07 | 海南电网有限责任公司电力科学研究院 | Insulator aging spectrum classification method based on transfer learning |
| CN113406448A (en) * | 2021-06-15 | 2021-09-17 | 中国铁道科学研究院集团有限公司基础设施检测研究所 | Method and device for detecting electrical state of railway insulator |
| CN113538351A (en) * | 2021-06-30 | 2021-10-22 | 国网山东省电力公司电力科学研究院 | External insulation equipment defect degree evaluation method fusing multi-parameter electric signals |
| CN113610768A (en) * | 2021-07-14 | 2021-11-05 | 南方电网科学研究院有限责任公司 | Method and device for measuring and calculating coverage rate of algae on surface of insulator and storage medium |
| CN114049507A (en) * | 2021-11-19 | 2022-02-15 | 国网湖南省电力有限公司 | Distribution network line insulator defect identification method, equipment and medium based on twin network |
| CN114539586A (en) * | 2022-04-27 | 2022-05-27 | 河南银金达新材料股份有限公司 | Surface treatment production process of polymer film |
| CN117611784A (en) * | 2023-11-30 | 2024-02-27 | 华北电力大学 | Cooperative control method and device for multispectral high-timeliness discharge detection |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5822053A (en) * | 1995-04-25 | 1998-10-13 | Thrailkill; William | Machine vision light source with improved optical efficiency |
| CN103247039A (en) * | 2013-05-09 | 2013-08-14 | 河海大学常州校区 | Charged detection method of high-voltage cable based on composite vision |
| CN103323460A (en) * | 2013-06-03 | 2013-09-25 | 深圳供电局有限公司 | Insulator detection method and device based on visible light image |
| CN103411970A (en) * | 2013-07-17 | 2013-11-27 | 同济大学 | Alternating current transmission line insulator contamination condition detection method based on infrared thermography |
| CN105043993A (en) * | 2015-07-14 | 2015-11-11 | 国网山东省电力公司电力科学研究院 | Method for detecting composite insulator based on multi-spectrum |
-
2016
- 2016-11-15 CN CN201611004199.0A patent/CN106596579A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5822053A (en) * | 1995-04-25 | 1998-10-13 | Thrailkill; William | Machine vision light source with improved optical efficiency |
| CN103247039A (en) * | 2013-05-09 | 2013-08-14 | 河海大学常州校区 | Charged detection method of high-voltage cable based on composite vision |
| CN103323460A (en) * | 2013-06-03 | 2013-09-25 | 深圳供电局有限公司 | Insulator detection method and device based on visible light image |
| CN103411970A (en) * | 2013-07-17 | 2013-11-27 | 同济大学 | Alternating current transmission line insulator contamination condition detection method based on infrared thermography |
| CN105043993A (en) * | 2015-07-14 | 2015-11-11 | 国网山东省电力公司电力科学研究院 | Method for detecting composite insulator based on multi-spectrum |
Non-Patent Citations (1)
| Title |
|---|
| 金立军等: ""基于红外与紫外图像信息融合的绝缘子污秽状态识别"", 《电工技术学报》 * |
Cited By (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108072667A (en) * | 2017-09-28 | 2018-05-25 | 江苏省电力试验研究院有限公司 | Insulator contamination level detection method and system based on EO-1 hyperion |
| CN108061847A (en) * | 2017-12-23 | 2018-05-22 | 华北电力大学（保定） | Dry-type reactor epoxy resin insulating medium cracking detection method |
| CN108280449A (en) * | 2018-02-06 | 2018-07-13 | 国网山西省电力公司电力科学研究院 | Power equipment image collecting method based on multispectral sensor group |
| CN108333488B (en) * | 2018-02-08 | 2020-11-24 | 南京视道信息技术有限公司 | Arc detection method based on fusion of ultraviolet, infrared and optical images |
| CN108333488A (en) * | 2018-02-08 | 2018-07-27 | 南京视道信息技术有限公司 | The arcing detection method blended based on ultraviolet, infrared and optical imagery |
| CN108760814A (en) * | 2018-06-21 | 2018-11-06 | 湖南湖大华龙电气与信息技术有限公司 | A kind of composite insulator is infrared to combine intelligent detecting method and its device with millimeter wave |
| CN109470628A (en) * | 2018-09-29 | 2019-03-15 | 江苏新绿能科技有限公司 | Contact net insulator contamination condition detection method |
| CN109283143A (en) * | 2018-11-23 | 2019-01-29 | 云南电网有限责任公司普洱供电局 | A kind of infrared, ultraviolet, visible light image procossing emerging system and method |
| CN110346699A (en) * | 2019-07-26 | 2019-10-18 | 国网山东省电力公司电力科学研究院 | Insulator arc-over information extracting method and device based on ultraviolet image processing technique |
| CN110346699B (en) * | 2019-07-26 | 2021-04-27 | 国网山东省电力公司电力科学研究院 | Insulator discharge information extraction method and device based on ultraviolet image processing technology |
| US20210131987A1 (en) * | 2019-11-01 | 2021-05-06 | Caterpillar Inc. | Grading a piston with deposits using thermal scan data |
| US11650173B2 (en) * | 2019-11-01 | 2023-05-16 | Caterpillar Inc. | Grading a piston with deposits using thermal scan data |
| CN110736507A (en) * | 2019-11-01 | 2020-01-31 | 国网河北省电力有限公司电力科学研究院 | method for detecting defect of insulator for transmission line and terminal equipment |
| CN111257242A (en) * | 2020-02-27 | 2020-06-09 | 西安交通大学 | High-spectrum identification method for pollutant components of insulator |
| CN112414950A (en) * | 2020-11-05 | 2021-02-26 | 西南交通大学 | Insulator equivalent salt deposit density detection method cooperating with hyperspectral and infrared technologies |
| CN112381784B (en) * | 2020-11-12 | 2024-06-25 | 国网浙江省电力有限公司信息通信分公司 | Equipment detecting system based on multispectral image |
| CN112381784A (en) * | 2020-11-12 | 2021-02-19 | 国网浙江省电力有限公司信息通信分公司 | Equipment detecting system based on multispectral image |
| CN112611732A (en) * | 2020-12-21 | 2021-04-06 | 中国电力科学研究院有限公司 | Method and system for establishing intermediate infrared spectrum chart library for silicone rubber for composite insulator |
| CN112611732B (en) * | 2020-12-21 | 2024-01-26 | 中国电力科学研究院有限公司 | Method and system for establishing mid-infrared spectrogram library of silicon rubber for composite insulator |
| CN112541478A (en) * | 2020-12-25 | 2021-03-23 | 国网吉林省电力有限公司信息通信公司 | Insulator string stain detection method and system based on binocular camera |
| CN112966576A (en) * | 2021-02-24 | 2021-06-15 | 西南交通大学 | System and method for aiming insulator water washing robot based on multi-light source image |
| CN113095499A (en) * | 2021-03-26 | 2021-07-09 | 云南电网有限责任公司电力科学研究院 | Insulator equivalent salt deposit density prediction method |
| CN113065484A (en) * | 2021-04-09 | 2021-07-02 | 华北电力大学（保定） | Insulator contamination state assessment method based on ultraviolet spectrum |
| CN113406448A (en) * | 2021-06-15 | 2021-09-17 | 中国铁道科学研究院集团有限公司基础设施检测研究所 | Method and device for detecting electrical state of railway insulator |
| CN113361631A (en) * | 2021-06-25 | 2021-09-07 | 海南电网有限责任公司电力科学研究院 | Insulator aging spectrum classification method based on transfer learning |
| CN113538351B (en) * | 2021-06-30 | 2024-01-19 | 国网山东省电力公司电力科学研究院 | Method for evaluating defect degree of external insulation equipment by fusing multiparameter electric signals |
| CN113538351A (en) * | 2021-06-30 | 2021-10-22 | 国网山东省电力公司电力科学研究院 | External insulation equipment defect degree evaluation method fusing multi-parameter electric signals |
| CN113610768A (en) * | 2021-07-14 | 2021-11-05 | 南方电网科学研究院有限责任公司 | Method and device for measuring and calculating coverage rate of algae on surface of insulator and storage medium |
| CN114049507A (en) * | 2021-11-19 | 2022-02-15 | 国网湖南省电力有限公司 | Distribution network line insulator defect identification method, equipment and medium based on twin network |
| CN114539586A (en) * | 2022-04-27 | 2022-05-27 | 河南银金达新材料股份有限公司 | Surface treatment production process of polymer film |
| CN114539586B (en) * | 2022-04-27 | 2022-07-19 | 河南银金达新材料股份有限公司 | Surface treatment production and detection process of polymer film |
| CN117611784A (en) * | 2023-11-30 | 2024-02-27 | 华北电力大学 | Cooperative control method and device for multispectral high-timeliness discharge detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106596579A (en) | Insulator contamination condition detection method based on multispectral image information fusion | |
| CN111784633B (en) | Insulator defect automatic detection algorithm for electric power inspection video | |
| CN106356757B (en) | A kind of power circuit unmanned plane method for inspecting based on human-eye visual characteristic | |
| CN103487729B (en) | Based on the power equipments defect detection method that ultraviolet video and infrared video merge | |
| CN103425967B (en) | A kind of based on stream of people's monitoring method of pedestrian detection and tracking | |
| CN112733950A (en) | Power equipment fault diagnosis method based on combination of image fusion and target detection | |
| CN109118479A (en) | Defects of insulator identification positioning device and method based on capsule network | |
| CN111611874B (en) | Face mask wearing detection method based on ResNet and Canny | |
| CN102288884B (en) | External insulation discharging detecting method based on ultraviolet light spots | |
| CN104899866A (en) | Intelligent infrared small target detection method | |
| CN109034184B (en) | Grading ring detection and identification method based on deep learning | |
| CN109631776B (en) | Automatic measurement method for icing thickness of high-voltage transmission line conductor | |
| CN103729620B (en) | A kind of multi-view pedestrian detection method based on multi-view Bayesian network | |
| CN111709888B (en) | Aerial image defogging method based on improved generation countermeasure network | |
| CN113947555A (en) | Infrared and visible light fused visual system and method based on deep neural network | |
| CN205507005U (en) | Portable supersound, infrared, ultraviolet detector | |
| Arif et al. | Adaptive deep learning detection model for multi-foggy images | |
| CN113762161B (en) | Intelligent obstacle monitoring method and system | |
| CN114463619A (en) | Infrared dim target detection method based on integrated fusion features | |
| CN114359167A (en) | Insulator defect detection method based on lightweight YOLOv4 in complex scene | |
| Shen et al. | Depth map enhancement method based on joint bilateral filter | |
| Tao et al. | Electric insulator detection of UAV images based on depth learning | |
| CN116485802B (en) | Insulator flashover defect detection method, device, equipment and storage medium | |
| CN112541478A (en) | Insulator string stain detection method and system based on binocular camera | |
| CN116740647A (en) | High-voltage transmission line galloping monitoring method based on binocular camera and deep learning |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170426 |