CN111833312A - Ultraviolet image diagnosis method and system for detecting discharge of fault insulator - Google Patents
Ultraviolet image diagnosis method and system for detecting discharge of fault insulator Download PDFInfo
- Publication number
- CN111833312A CN111833312A CN202010571139.7A CN202010571139A CN111833312A CN 111833312 A CN111833312 A CN 111833312A CN 202010571139 A CN202010571139 A CN 202010571139A CN 111833312 A CN111833312 A CN 111833312A
- Authority
- CN
- China
- Prior art keywords
- image
- ultraviolet
- value
- insulator
- threshold
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000012212 insulator Substances 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000003745 diagnosis Methods 0.000 title claims abstract description 20
- 239000002245 particle Substances 0.000 claims abstract description 48
- 238000003708 edge detection Methods 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 230000009466 transformation Effects 0.000 claims abstract description 19
- 230000011218 segmentation Effects 0.000 claims abstract description 18
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 238000000825 ultraviolet detection Methods 0.000 claims description 33
- 230000003044 adaptive effect Effects 0.000 claims description 14
- 238000003709 image segmentation Methods 0.000 claims description 12
- 238000000354 decomposition reaction Methods 0.000 claims description 11
- 238000003384 imaging method Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 5
- 230000001105 regulatory effect Effects 0.000 claims description 5
- 230000006978 adaptation Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 abstract description 6
- 238000013139 quantization Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 10
- 238000001514 detection method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000001931 thermography Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 239000006002 Pepper Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000010891 electric arc Methods 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
Images
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1218—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing using optical methods; using charged particle, e.g. electron, beams or X-rays
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06T2207/20036—Morphological image processing
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- 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
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an ultraviolet image diagnosis method and system for detecting a fault insulator, which are characterized in that an original ultraviolet image is processed by combining wavelet transformation and a particle swarm optimization algorithm to realize image denoising and enhancement, then an OTSU method is used for carrying out threshold segmentation on the image, then mathematical morphology binary open operation is carried out, finally edge detection and outline extraction of ultraviolet light spots are realized by a Canny edge detection operator fused with the wavelet transformation, and image parameters such as light spot area, perimeter, equivalent diameter and the like are calculated and used as characteristic parameters and quantization standards of insulator discharge intensity.
Description
Technical Field
The invention relates to the field of fault detection and diagnosis of high-voltage electrical equipment, in particular to an ultraviolet image diagnosis method and system for detecting a fault insulator.
Background
In an electric power system, an insulator is widely applied to a transmission line and a substation of each voltage class, and is one of key devices of the electric power system. The insulator operating under outdoor conditions is inevitably subjected to the effects of strong electric fields, high-temperature solarization, humidity, dirt, ice coating and mechanical stress or defects in the production process, so that the insulator can generate insulation faults in the operation process, and discharge phenomena such as corona, electric arc and the like are generated, the insulator can be further developed into flashover and breakdown, and even can cause large-scale collapse of an electric power system under severe conditions, thereby causing huge economic loss and potential safety hazards.
At present, various fault insulator detection methods are available, such as a distributed voltage method, an ultrasonic method, a leakage current method, an infrared thermal imaging method and the like. The distributed voltage method requires a person to be examined to climb a pole, and has certain potential safety hazards through empirical judgment; the ultrasonic detection method has the problem of coupling attenuation, and is not applied to long-distance engineering detection at present; in the leakage current method, if the voltage of the power transmission line changes, the magnitude of leakage current also changes, so that the leakage current of a fault insulator is not obvious, and the leakage detection or the false detection is caused; the infrared thermal imaging method is influenced by weather conditions, is limited to rainy days and even cannot detect the weather conditions.
The ultraviolet imaging technology is a new discharge detection technology, the discharge process of the insulator is accompanied with the radiation of optical signals, the ultraviolet imaging method utilizes an ultraviolet signal sensor in imaging equipment to convert ultraviolet signals into electric signals, and the electric signals are combined with visible light images after a series of signal processing, so that visual two-dimensional images can be obtained to observe the discharge condition of the insulator, field personnel can quickly and accurately position discharge points, and defective insulators can be timely processed. However, when the photographed image is blurred due to various factors, the final determination error is large, and therefore, it is most important to effectively process and extract and identify the ultraviolet image of the insulator discharge.
Disclosure of Invention
The purpose of the invention is as follows: in order to solve the problem of large error in insulator detection and judgment in the prior art, an ultraviolet image diagnosis method for detecting whether the insulator has defects is provided.
The technical scheme is as follows: an ultraviolet image diagnosis method for detecting a fault insulator comprises the following steps:
step 1: carrying out image segmentation on an original ultraviolet detection image, and carrying out mathematical morphology binary open operation on the segmented image to obtain an initial ultraviolet spot;
step 2: performing edge detection and contour extraction on the initial ultraviolet light spot to obtain a final ultraviolet light spot;
and step 3: calculating the final parameters of the ultraviolet light spots, and taking the parameters as the characteristic parameters and the quantitative standards of the discharge intensity of the insulator;
and 4, step 4: and judging whether the current insulator has a fault or not according to the characteristic parameters and the quantitative standards of the discharge intensity of the insulator.
Further, the image segmentation of the original ultraviolet detection image in the step 1 includes the following steps:
denoising the original ultraviolet detection image;
carrying out image enhancement operation on the de-noised ultraviolet detection image by adopting gray level transformation processing;
and carrying out image segmentation on the ultraviolet detection image subjected to the image enhancement operation.
Further, the denoising processing of the original ultraviolet detection image specifically includes the following substeps:
s110: decomposing an original ultraviolet detection image by adopting wavelet transformation to obtain a plurality of wavelet transformation decomposition layers, and determining the threshold value of each decomposition layer based on the formula (1);
T=σ*2lg(N)/lg(j+1) (1)
wherein, N is the pixel number of each wavelet transform decomposition layer, sigma is the noise standard deviation of each wavelet transform decomposition layer, and j is the decomposition layer number;
s120: taking the nth layer threshold as a particle adaptive value threshold, and calculating by adopting a particle swarm algorithm to obtain an adjusting factor corresponding to the nth layer threshold, wherein n is 1, 2.. j;
s130: taking the adjustment factor corresponding to the nth layer of threshold as the initial value of the adjustment factor of the next round of particle swarm algorithm iteration, taking the (n +1) th layer of threshold as the threshold of the particle adaptive value, and calculating by adopting the particle swarm algorithm to obtain the adjustment factor corresponding to the (n +1) th layer of threshold; s140: circularly executing S120 to S130 until the adjustment factor corresponding to the j-th layer threshold value is obtained or the set precision is reached, and outputting the current adjustment factor;
s150: carrying out thresholding treatment on the adjustment factor obtained in the step S140 to obtain a new wavelet transform coefficient;
s160: and based on the new wavelet transformation coefficient, performing image reconstruction by adopting wavelet inverse transformation to obtain a denoised ultraviolet image.
Further, the particle swarm algorithm specifically comprises the following steps:
s121: initializing a particle swarm;
s122: the fitness value for each particle is calculated according to equation (2):
vid.l=vid+c1r1(pid-xid)+c2r2(pgd-xid)
xid.l=xid+Vid(2)
wherein i is 1, 2.. N; d1, 2.. D; d is a vector dimension, c1 and c2 are regulating factors; r1 and r2 are 2 in [0, 1]]Random function within the range, left of the formula being the iterated value, pidRepresents the historical best point, P, experienced by the ith particlegdRepresenting historical best points experienced by all particles within the population; v. ofidDenotes the velocity, x, of the ith particleidIndicating the position of the ith particle;
s123: refreshing the maximum value of the suitable function of the individual history and the maximum value of the suitable function of the population history according to the adaptive value obtained in the step S122, and updating the position and the speed of each particle by taking the numerical value calculated by the formula as a result;
s124: and judging whether the maximum iteration number M is reached or the particle adaptation value is lower than the nth layer threshold value, if so, outputting the adjustment factor, otherwise, resetting the adjustment factors c1 and c2 and switching to S122.
Further, in S150, the adjustment factor obtained in S140 is subjected to hard thresholding, so as to obtain a new wavelet transform coefficient.
Further, the gray scale conversion process comprises the following steps:
defining a mobile sub-block;
and carrying out histogram equalization on the mobile sub-image block taking each pixel point as the center, and replacing the gray value of the center point of the corresponding mobile sub-image block with the equalized result to finally obtain the ultraviolet detection image after image enhancement.
Further, the step 1 of performing mathematical morphology binary open operation on the image obtained by segmentation to obtain the initial ultraviolet light spot includes the following substeps:
extracting insulator discharge ultraviolet spots and backgrounds in the ultraviolet detection image after image enhancement by using a threshold segmentation method, and counting to obtain the size of the insulator discharge ultraviolet spots:
in the formula, Y is the row number value of the binary image matrix, and Z is the column number value of the binary image matrix; b (i, j) is a binary image after mathematical morphology filtering;
obtaining a binary image after threshold segmentation;
and performing binary open operation on the binary image to obtain white noise points with zero gray value on the binary image and a white focusing window as initial ultraviolet spots.
Further, the step 2 specifically includes the following sub-steps:
adopting a Canny self-adaptive edge detection method for the initial ultraviolet light spots to obtain corresponding edge images;
adopting a wavelet maximum edge detection method for the initial ultraviolet light spots to obtain corresponding edge images;
and adding the two edge images through weighting factors to carry out edge fusion to obtain the final ultraviolet light spot.
Further, the parameters of the ultraviolet light spot comprise the area, the perimeter and the equivalent diameter of the ultraviolet light spot.
The invention also discloses an ultraviolet image diagnosis system for detecting the fault insulator, which comprises the following components:
the ultraviolet imaging module is used for acquiring an original ultraviolet detection image when the insulator discharges;
the image segmentation module is used for carrying out image threshold segmentation on the original ultraviolet detection image;
the binary open operation module is used for carrying out binary open operation on the image segmented by the image segmentation module;
the edge detection and contour extraction module is used for carrying out edge detection and contour extraction on the operation result of the binary open operation module;
the ultraviolet light spot parameter calculation module is used for carrying out parameter calculation on the result output by the edge detection and contour extraction module;
and the judging module is used for judging whether the current insulator has a fault according to the ultraviolet light spot parameters output by the ultraviolet light spot parameter calculating module.
The image processing module comprises a denoising processing module for denoising the original ultraviolet detection image and an image enhancement module for carrying out gray level processing on the denoised image.
Has the advantages that: the invention has the following advantages:
1. the method solves the problems that the traditional method only quantizes the discharge intensity through the number of photons, is easily interfered by external conditions and is difficult to quantize and analyze, and is more accurate and visual by taking image parameters such as the equivalent diameter of the area and the perimeter of the light spot of the processed edge image as quantization parameters;
2. according to the invention, a method combining a particle swarm optimization algorithm and wavelet transformation is adopted to realize self-adaptive image denoising and artificial intelligence optimization, so that the image processing effect is better;
3. in the aspect of edge detection, the Canny self-adaptive edge detection algorithm and the wavelet maximum edge detection algorithm are fused, so that the definition, the continuity and the integrity are obviously enhanced, and meanwhile, the robustness is good;
4. the method can better protect the image edge details, and is superior to several classical image enhancement algorithms in the aspects of image enhancement quality, accuracy and the like.
Drawings
FIG. 1 is a flow chart of ultraviolet inspection image processing;
FIG. 2 is a flow chart of the binding algorithm;
FIG. 3 is a flow chart of edge feature extraction;
FIG. 4 is an original image containing noise;
FIG. 5 is an image after denoising enhancement;
FIG. 6 is an image after threshold segmentation;
fig. 7 is an edge profile of image extraction.
Detailed Description
The technical solution of the present invention will be further explained with reference to the accompanying drawings and examples.
Example 1:
referring to fig. 1, in the embodiment, the ultraviolet imaging technology is applied to the inspection of the power system, and the fault insulator can be indirectly and accurately detected; the insulator can be irradiated by ultraviolet light during fault discharge, an ultraviolet detection image during insulator discharge is shot by a solar blind type ultraviolet imaging device, and the image is denoised and enhanced by wavelet transformation and particle swarm optimization, so that the background identification degree of the image is ensured, the ultraviolet light spot area is more obvious and prominent, and effective identification and discrimination of a discharge area are facilitated; then, threshold segmentation and filtering optimization of mathematical morphology of the image are carried out to remove the background in the image, and target characteristics are obtained; and then, edge detection and outline extraction of ultraviolet light spots are realized by a Canny edge detection algorithm fused with wavelet transformation, and image parameters such as the area, the perimeter and the equivalent diameter of the light spots are calculated and used as characteristic parameters and quantitative standards of the discharge intensity of the insulator. The invention has the advantages of accurate positioning, obvious enhancement of definition, continuity and integrity of the edge image, effective removal of unnecessary detail interference in the noise image and the like.
The embodiment specifically comprises the following steps:
s1: the method comprises the steps that most of noise generated when the discharging phenomenon occurs on the surface of an insulator is salt-pepper noise, an original ultraviolet detection image of the insulator during discharging is shot through solar blind type ultraviolet imaging equipment, wavelet transformation is adopted to decompose the original ultraviolet detection image to obtain a local image, and a first layer of threshold value for obtaining a wavelet coefficient is determined according to the formula (1) based on the size of the local image;
T=σ*2lg(N)/lg(j+1) (1)
in the formula, N is the pixel number of each layer, sigma is the noise standard deviation of each layer, and j is the number of decomposition layers;
after the wavelet transform, the threshold value required for denoising each layer coefficient is generally taken according to the signal-to-noise ratio of the original signal, which is expressed by the noise standard deviation (noise intensity) σ. After the noise intensity of the signal is obtained, determining the threshold of each layer according to the noise intensity sigma, determining the threshold of a first layer according to the size of a local image, wherein the threshold of the first layer is used for solving a wavelet coefficient in the subsequent step and solving an adjusting factor according to the fitness;
s2: initializing a particle swarm;
s3: calculating an adaptation value of each particle;
vid.l=vid+c1r1(pid-xid)+c2r2(pgd-xid)
xid.l=xid+vid(2)
wherein i is 1, 2.. N; d1, 2.. D; d is a vector dimension, c1 and c2 are regulating factors, namely acceleration constants; r1, r2 are 2 random functions in the range of [0, 1], with values after iteration on the left side of the formula.
S4: the adaptive value refreshes the maximum value (pbest) of the adaptive function of the individual history and the maximum value (gbest) of the adaptive function of the population history, and the position and the speed of each particle are updated by taking the numerical value calculated by the formula as a result;
s5: if the maximum iteration number M is reached or the particle adaptation value is lower than the first-layer threshold value, outputting a regulating factor, and turning to S6, and if the maximum iteration number M is not reached, modifying c1, c2 and turning to S3;
by changing the adjustment factor, the particles are searched in a large range in the initial searching stage so as to obtain high-quality particles with better diversity and get rid of the interference of local extreme values as far as possible. Setting a larger value of c1 may cause excessive local searching of particles; conversely, a larger value of c2 may cause the particle to converge to a local optimum prematurely. Therefore, a larger c1 value and a smaller c2 value are adopted at the early stage of the algorithm search; the adjustment factor of the embodiment can improve the identification resolution of the frequency domain and the time domain by adjusting the wavelet waveform.
S6: determining a second-layer threshold value by the formula (1), taking the adjusting factor corresponding to the first-layer threshold value as an initial value of the adjusting factor of the next round of particle swarm algorithm iteration, taking the second-layer threshold value as a particle adaptive value threshold value, and calculating by adopting a particle swarm algorithm to obtain the adjusting factor corresponding to the second-layer threshold value.
S7: determining a third-layer threshold value by the formula (1), taking an adjusting factor corresponding to the second-layer threshold value as an initial value of an adjusting factor of next round of particle swarm algorithm iteration, taking the third-layer threshold value as a particle adaptive value threshold value, and calculating by adopting a particle swarm algorithm to obtain the adjusting factor corresponding to the third-layer threshold value, wherein the accuracy achieved by the three-layer threshold value can basically meet the requirement.
S8: carrying out threshold processing on the adjustment factor corresponding to the threshold of the third layer to obtain a new wavelet transformation coefficient; at present, threshold processing comprises hard thresholding segmentation and soft thresholding segmentation, wherein the hard thresholding segmentation can cause high-frequency change on an image, and a reserved wavelet coefficient is the same as an original coefficient, so that the image is fidelity. When soft thresholding segmentation is adopted, although continuity and no break point are kept, no odd change occurs, wavelet coefficients with absolute values larger than a threshold value are reduced by the threshold value, so that an image is distorted; the present embodiment employs a hard thresholding method.
S9: based on the new wavelet transform coefficient, performing wavelet inverse transform to reconstruct the ultraviolet detection image, and completing denoising the ultraviolet detection image, where S1 to S9 are as shown in fig. 2.
S10: defining a mobile sub-image block with a proper size, carrying out histogram equalization on the mobile sub-image block taking each pixel point as the center, and replacing the gray value of the center point of the corresponding mobile sub-image block with the processing result to finish the enhancement of the ultraviolet detection image.
S11: selecting a threshold suitable for image denoising, extracting a target and a background in an ultraviolet detection image after image enhancement by adopting an OTSU method and utilizing the gray difference between the threshold and a pixel, namely setting a gray threshold for the image, setting part of pixels higher than the threshold as 1, setting part of pixels lower than the threshold as 0, and counting the number of pixels in a white area with the gray value of 1 so as to represent the size of an insulator discharge ultraviolet spot, namely the spot area S is defined as follows:
in the formula, Y is the row number value of the binary image matrix, and Z is the column number value of the binary image matrix; b (i, j) is a binary image after mathematical morphology filtering, so that the spot area S is the sum of the number of pixel points in the discharge spot area;
obtaining a binary image after threshold segmentation, and performing binary open operation on the binary image to obtain ultraviolet light spots, wherein the ultraviolet light spots are white noise points with zero gray values on the binary image and a white focusing window;
s12: referring to fig. 3, Canny adaptive edge detection and wavelet maximum edge detection are respectively adopted for the ultraviolet spots to obtain two edge images, and the two edge images are added through weighting factors to carry out edge fusion to obtain the final ultraviolet spots.
S13: and calculating final image parameters such as ultraviolet spot area, perimeter, equivalent diameter and the like as the characteristic parameters and the quantization standard of the discharge intensity of the insulator, and judging whether the insulator has faults or not according to the characteristic parameters and the quantization standard of the discharge intensity of the insulator.
In this embodiment, taking the original image in fig. 4 as an example, since the number of pixels in the digital image is large, the length of the selected signal is large, and therefore, the method with the adjustment factor 0 < c < 1 is selected, and the parameters of the particle swarm optimization algorithm are set as follows:
if the population number is too large, the defects of pseudo global convergence, slow convergence reaction, unstable data and the like can be caused, but if the population number is too small, the information quantity is small, and the obtained effect is not good; the number of the population is usually within the range of 100-800, and the size of the population is 200 in this embodiment.
Constant of acceleration c1、c2In order to increase the density of searches, the present embodiment takes c 1-0.9 and c 2-0.9 for controlling individual cognitive and group social information sharing regulatory parameters of each particle.
Theoretically, the larger the iteration number value is, the better the iteration number value is, but the real-time performance is affected by the overlarge value, so that the maximum iteration number is selected for 500 times in the embodiment.
The threshold value of the particle adaptive value is set by an improved formula T ═ σ ═ 2lg (N)/lg (j +1), where N is the number of pixels in each layer and σ is the standard deviation of each layer.
Now, after S1 to S9, the image after denoising enhancement shown in fig. 5 is obtained.
In this embodiment, gray level transformation is used to perform image enhancement, and histogram analysis shows that the gray level of the background image is concentrated on about 30, the gray level of the corona image is concentrated on about 245, what needs to be enhanced is the background image, that is, only a part of the gray level needs to be enhanced while keeping the high gray level constant, the value of the gray level belonging to [0, 120] is transformed into [0, 220], the slope of the transformation line is 1.83, and the image after threshold segmentation shown in fig. 6 is obtained.
In the embodiment, an image to be segmented is regarded as composed of a background and a target, a gray histogram of the target image is used as a statistical feature, a binary on operation is used for carrying out mathematical morphology filtering, and an on operation is carried out on an image set B through a structural element A to be recorded asAnd is defined as:the structural element of this embodiment is selected as a disc with a radius of 2, and the effect after treatment is shown in fig. 7.
In this embodiment, Canny adaptive edge detection and wavelet maximum edge detection are adopted to obtain two kinds of edge images, and then edge fusion is performed through weighting factor addition, where the fusion mathematical expression is: c (i, j) ═ λ a (i, j) + μ B (i, j), and λ is 0.4 and μ is 0.6 in this example.
The insulator ultraviolet discharge test samples under the laboratory environment and the field environment are selected to be used as test samples for 40 times respectively, operation is started from the step S1, the output is the insulator discharge intensity, the calculation result is consistent with the actual pollution grade, and the accuracy rate of the embodiment for judging the pollution grade can reach 95%.
Example 2:
the present embodiment discloses an ultraviolet image diagnosis system for detecting a faulty insulator on the basis of embodiment 1, including:
the ultraviolet imaging module is used for acquiring an original ultraviolet detection image when the insulator discharges;
the image denoising processing module is used for denoising the original ultraviolet detection image;
the image enhancement module is used for carrying out gray level processing on the denoised image;
the image segmentation module is used for carrying out image threshold segmentation on the image processed by the image enhancement module;
the binary open operation module is used for carrying out binary open operation on the image segmented by the image segmentation module;
the edge detection and contour extraction module is used for carrying out edge detection and contour extraction on the operation result of the binary open operation module;
the ultraviolet light spot parameter calculation module is used for carrying out parameter calculation on the result output by the edge detection and contour extraction module;
and the judging module is used for judging whether the current insulator has a fault according to the ultraviolet light spot parameters output by the ultraviolet light spot parameter calculating module.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (11)
1. An ultraviolet image diagnosis method for detecting a fault insulator is characterized by comprising the following steps: the method comprises the following steps:
step 1: carrying out image segmentation on an original ultraviolet detection image, and carrying out mathematical morphology binary open operation on the segmented image to obtain an initial ultraviolet spot;
step 2: performing edge detection and contour extraction on the initial ultraviolet light spot to obtain a final ultraviolet light spot;
and step 3: calculating the final parameters of the ultraviolet light spots, and taking the parameters as the characteristic parameters and the quantitative standards of the discharge intensity of the insulator;
and 4, step 4: and judging whether the current insulator has a fault or not according to the characteristic parameters and the quantitative standards of the discharge intensity of the insulator.
2. The ultraviolet image diagnosis method for detecting the faulty insulator according to claim 1, wherein: the image segmentation of the original ultraviolet detection image in the step 1 comprises the following steps:
denoising the original ultraviolet detection image;
carrying out image enhancement operation on the de-noised ultraviolet detection image by adopting gray level transformation processing;
and carrying out image segmentation on the ultraviolet detection image subjected to the image enhancement operation.
3. The ultraviolet image diagnosis method for detecting the faulty insulator according to claim 2, wherein: the denoising processing of the original ultraviolet detection image specifically comprises the following substeps:
s110: decomposing an original ultraviolet detection image by adopting wavelet transformation to obtain a plurality of wavelet transformation decomposition layers, and determining the threshold value of each decomposition layer based on the formula (1);
T=σ*2lg(N)/lg(j+1) (1)
wherein, N is the pixel number of each wavelet transform decomposition layer, sigma is the noise standard deviation of each wavelet transform decomposition layer, and j is the decomposition layer number;
s120: taking the nth layer of threshold as a particle adaptive value threshold, and calculating by adopting a particle swarm algorithm to obtain an adjusting factor corresponding to the nth layer of threshold, wherein n is 1,2 … … j;
s130: taking the adjustment factor corresponding to the nth layer of threshold as the initial value of the adjustment factor of the next round of particle swarm algorithm iteration, taking the (n +1) th layer of threshold as the threshold of the particle adaptive value, and calculating by adopting the particle swarm algorithm to obtain the adjustment factor corresponding to the (n +1) th layer of threshold;
s140: circularly executing S120 to S130 until the adjustment factor corresponding to the j-th layer threshold value is obtained or the set precision is reached, and outputting the current adjustment factor;
s150: carrying out thresholding treatment on the adjustment factor obtained in the step S140 to obtain a new wavelet transform coefficient;
s160: and based on the new wavelet transformation coefficient, performing image reconstruction by adopting wavelet inverse transformation to obtain a denoised ultraviolet image.
4. The ultraviolet image diagnosis method for detecting the faulty insulator according to claim 3, wherein: the particle swarm algorithm specifically comprises the following steps:
s121: initializing a particle swarm;
s122: the fitness value for each particle is calculated according to equation (2):
vid,1=vid+c1r1(pid-Xid)+c2r2(pgd-xid)
Xid,1=Xid+vid(2)
wherein i is 1,2 … N; d is 1,2 … D; d is a vector dimension, c1 and c2 are regulating factors; r1 and r2 are 2 in [0, 1]]Random function within the range, left of the formula being the iterated value, pidRepresenting the historical best point, p, experienced by the ith particlegdRepresenting all particles within a populationHistorical best points of experience; v. ofidDenotes the velocity, x, of the ith particleidIndicating the position of the ith particle;
s123: refreshing the maximum value of the suitable function of the individual history and the maximum value of the suitable function of the population history according to the adaptive value obtained in the step S122, and updating the position and the speed of each particle by taking the numerical value calculated by the formula as a result;
s124: and judging whether the maximum iteration number M is reached or the particle adaptation value is lower than the nth layer threshold value, if so, outputting the adjustment factor, otherwise, resetting the adjustment factors c1 and c2 and switching to S122.
5. The ultraviolet image diagnosis method for detecting the faulty insulator according to claim 3, wherein: in S150, the adjustment factor obtained in S140 is subjected to hard thresholding, so as to obtain a new wavelet transform coefficient.
6. The ultraviolet image diagnosis method for detecting the faulty insulator according to claim 3, wherein: the gray scale conversion processing comprises the following steps:
defining a mobile sub-block;
and carrying out histogram equalization on the mobile sub-image block taking each pixel point as the center, and replacing the gray value of the center point of the corresponding mobile sub-image block with the equalized result to finally obtain the ultraviolet detection image after image enhancement.
7. The ultraviolet image diagnosis method for detecting the faulty insulator according to claim 2, wherein: the step 1 of performing mathematical morphology binary open operation on the image obtained by segmentation to obtain the initial ultraviolet light spot comprises the following substeps:
extracting insulator discharge ultraviolet spots and backgrounds in the ultraviolet detection image after image enhancement by using a threshold segmentation method, and counting to obtain the size of the insulator discharge ultraviolet spots:
in the formula, Y is the row number value of the binary image matrix, and Z is the column number value of the binary image matrix; b (i, j) is a binary image after mathematical morphology filtering;
obtaining a binary image after threshold segmentation;
and performing binary open operation on the binary image to obtain white noise points with zero gray value on the binary image and a white focusing window as initial ultraviolet spots.
8. The ultraviolet image diagnosis method for detecting the faulty insulator according to claim 1, wherein: the step 2 specifically comprises the following substeps:
adopting a Canny self-adaptive edge detection method for the initial ultraviolet light spots to obtain corresponding edge images;
adopting a wavelet maximum edge detection method for the initial ultraviolet light spots to obtain corresponding edge images;
and adding the two edge images through weighting factors to carry out edge fusion to obtain the final ultraviolet light spot.
9. The ultraviolet image diagnosis method for detecting the faulty insulator according to claim 1, wherein: the parameters of the ultraviolet light spots comprise the area, the perimeter and the equivalent diameter of the ultraviolet light spots.
10. The diagnosis system of the ultraviolet image diagnosis method for detecting the faulty insulator according to any one of claims 1 to 9, wherein: the method comprises the following steps:
the ultraviolet imaging module is used for acquiring an original ultraviolet detection image when the insulator discharges;
the image segmentation module is used for carrying out image threshold segmentation on the original ultraviolet detection image;
the binary open operation module is used for carrying out binary open operation on the image segmented by the image segmentation module;
the edge detection and contour extraction module is used for carrying out edge detection and contour extraction on the operation result of the binary open operation module;
the ultraviolet light spot parameter calculation module is used for carrying out parameter calculation on the result output by the edge detection and contour extraction module;
and the judging module is used for judging whether the current insulator has a fault according to the ultraviolet light spot parameters output by the ultraviolet light spot parameter calculating module.
11. The diagnostic system of claim 9, wherein: the image processing module comprises a denoising processing module for denoising the original ultraviolet detection image and an image enhancement module for carrying out gray level processing on the denoised image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010571139.7A CN111833312B (en) | 2020-06-22 | 2020-06-22 | Ultraviolet image diagnosis method and system for detecting discharge of fault insulator |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010571139.7A CN111833312B (en) | 2020-06-22 | 2020-06-22 | Ultraviolet image diagnosis method and system for detecting discharge of fault insulator |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111833312A true CN111833312A (en) | 2020-10-27 |
CN111833312B CN111833312B (en) | 2022-09-09 |
Family
ID=72897774
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010571139.7A Active CN111833312B (en) | 2020-06-22 | 2020-06-22 | Ultraviolet image diagnosis method and system for detecting discharge of fault insulator |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111833312B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112666426A (en) * | 2020-11-13 | 2021-04-16 | 国网江苏省电力有限公司电力科学研究院 | Equipment fault detection method and system based on multispectral three-in-one image |
CN113160193A (en) * | 2021-04-28 | 2021-07-23 | 贵州电网有限责任公司 | Ultraviolet image segmentation method and system based on bat algorithm and Otsu method with Levy flight characteristics |
CN113610830A (en) * | 2021-08-18 | 2021-11-05 | 常州领创电气科技有限公司 | Detection system and method for lightning arrester |
CN114113947A (en) * | 2021-11-30 | 2022-03-01 | 国网辽宁省电力有限公司铁岭供电公司 | Switch cabinet based on ultraviolet imaging method and discharge state sensing method thereof |
CN114264915A (en) * | 2021-12-13 | 2022-04-01 | 国网甘肃省电力公司临夏供电公司 | Power distribution network cable joint operation condition assessment early warning device and method |
CN114779031A (en) * | 2022-06-21 | 2022-07-22 | 国网山东省电力公司电力科学研究院 | Digital power equipment ultraviolet imaging discharge abnormity detection method and system |
CN117152000A (en) * | 2023-08-08 | 2023-12-01 | 华中科技大学 | Rainy day image-clear background paired data set manufacturing method and device and application thereof |
CN114113947B (en) * | 2021-11-30 | 2024-08-02 | 国网辽宁省电力有限公司铁岭供电公司 | Switch cabinet based on ultraviolet imaging method and discharge state sensing method thereof |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107505546A (en) * | 2017-08-25 | 2017-12-22 | 国家电网公司 | A kind of method that corona discharge is monitored using ultraviolet imager |
CN107843818A (en) * | 2017-09-06 | 2018-03-27 | 同济大学 | Based on heterologous image temperature rise and local discharge characteristic high-voltage isulation method for diagnosing faults |
-
2020
- 2020-06-22 CN CN202010571139.7A patent/CN111833312B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107505546A (en) * | 2017-08-25 | 2017-12-22 | 国家电网公司 | A kind of method that corona discharge is monitored using ultraviolet imager |
CN107843818A (en) * | 2017-09-06 | 2018-03-27 | 同济大学 | Based on heterologous image temperature rise and local discharge characteristic high-voltage isulation method for diagnosing faults |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112666426A (en) * | 2020-11-13 | 2021-04-16 | 国网江苏省电力有限公司电力科学研究院 | Equipment fault detection method and system based on multispectral three-in-one image |
CN113160193A (en) * | 2021-04-28 | 2021-07-23 | 贵州电网有限责任公司 | Ultraviolet image segmentation method and system based on bat algorithm and Otsu method with Levy flight characteristics |
CN113610830A (en) * | 2021-08-18 | 2021-11-05 | 常州领创电气科技有限公司 | Detection system and method for lightning arrester |
CN113610830B (en) * | 2021-08-18 | 2023-12-29 | 常州领创电气科技有限公司 | Detection system and method for lightning arrester |
CN114113947A (en) * | 2021-11-30 | 2022-03-01 | 国网辽宁省电力有限公司铁岭供电公司 | Switch cabinet based on ultraviolet imaging method and discharge state sensing method thereof |
CN114113947B (en) * | 2021-11-30 | 2024-08-02 | 国网辽宁省电力有限公司铁岭供电公司 | Switch cabinet based on ultraviolet imaging method and discharge state sensing method thereof |
CN114264915A (en) * | 2021-12-13 | 2022-04-01 | 国网甘肃省电力公司临夏供电公司 | Power distribution network cable joint operation condition assessment early warning device and method |
CN114779031A (en) * | 2022-06-21 | 2022-07-22 | 国网山东省电力公司电力科学研究院 | Digital power equipment ultraviolet imaging discharge abnormity detection method and system |
CN117152000A (en) * | 2023-08-08 | 2023-12-01 | 华中科技大学 | Rainy day image-clear background paired data set manufacturing method and device and application thereof |
CN117152000B (en) * | 2023-08-08 | 2024-05-14 | 华中科技大学 | Rainy day image-clear background paired data set manufacturing method and device and application thereof |
Also Published As
Publication number | Publication date |
---|---|
CN111833312B (en) | 2022-09-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111833312B (en) | Ultraviolet image diagnosis method and system for detecting discharge of fault insulator | |
CN109596634B (en) | Cable defect detection method and device, storage medium and processor | |
CN110232380A (en) | Fire night scenes restored method based on Mask R-CNN neural network | |
CN112308860A (en) | Earth observation image semantic segmentation method based on self-supervision learning | |
CN110598613B (en) | Expressway agglomerate fog monitoring method | |
CN110660065B (en) | Infrared fault detection and identification algorithm | |
CN113344475B (en) | Transformer bushing defect identification method and system based on sequence modal decomposition | |
CN113936132B (en) | Method and system for detecting water pollution of chemical plant based on computer vision | |
CN112801949A (en) | Method and device for determining discharge area in ultraviolet imaging detection technology | |
CN113030244A (en) | Power transmission line tower corrosion defect magnetic leakage detection signal inversion imaging method and system | |
CN116309483A (en) | DDPM-based semi-supervised power transformation equipment characterization defect detection method and system | |
Arif et al. | Adaptive deep learning detection model for multi-foggy images | |
Zhao et al. | A multi-scale U-shaped attention network-based GAN method for single image dehazing | |
CN111160087A (en) | Method and system for automatically identifying porcelain insulator cap and disc surface in infrared image and storage medium | |
CN114359167A (en) | Insulator defect detection method based on lightweight YOLOv4 in complex scene | |
Jiang et al. | Pseudo‐Siamese residual atrous pyramid network for multi‐focus image fusion | |
CN113096103A (en) | Intelligent smoke image sensing method for emptying torch | |
CN112508862B (en) | Method for enhancing magneto-optical image of crack by improving GAN | |
CN115358947A (en) | Ferrographic abrasive particle image denoising method, device and equipment and readable storage medium | |
CN113506312A (en) | Ultraviolet discharge image segmentation method and computer readable medium | |
CN116823627A (en) | Image complexity evaluation-based oversized image rapid denoising method | |
CN114862803A (en) | Industrial image anomaly detection method based on fast Fourier convolution | |
CN109886133B (en) | Ship detection method and system based on optical remote sensing image | |
CN111242892A (en) | Method for detecting defects of solar photovoltaic cell | |
WO2015128302A1 (en) | Method and apparatus for filtering and analyzing a noise in an image |
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 |