CN112113667B - Current transformer fault diagnosis method based on infrared thermal image information - Google Patents
Current transformer fault diagnosis method based on infrared thermal image information Download PDFInfo
- Publication number
- CN112113667B CN112113667B CN202010996979.8A CN202010996979A CN112113667B CN 112113667 B CN112113667 B CN 112113667B CN 202010996979 A CN202010996979 A CN 202010996979A CN 112113667 B CN112113667 B CN 112113667B
- Authority
- CN
- China
- Prior art keywords
- fault
- current transformer
- temperature
- point
- heating type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003745 diagnosis Methods 0.000 title claims abstract description 24
- 238000010438 heat treatment Methods 0.000 claims abstract description 54
- 238000005516 engineering process Methods 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims abstract description 4
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 2
- 238000012795 verification Methods 0.000 claims description 2
- 238000001931 thermography Methods 0.000 claims 4
- 238000011156 evaluation Methods 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 239000002510 pyrogen Substances 0.000 abstract 1
- 230000007547 defect Effects 0.000 description 11
- 238000004458 analytical method Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 229910052573 porcelain Inorganic materials 0.000 description 2
- 230000001698 pyrogenic effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0096—Radiation pyrometry, e.g. infrared or optical thermometry for measuring wires, electrical contacts or electronic systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/48—Thermography; Techniques using wholly visual means
- G01J5/485—Temperature profile
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Multimedia (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention discloses a current transformer fault diagnosis method based on infrared thermal image information, which takes an OCR technology and a calculation formula of gray level and temperature as a means for automatically extracting temperature data in a picture. Then, each phase current transformer in the picture is independently segmented, the characteristic points of the current transformers are extracted from the segmented image by using a window sliding technology, and the heating type is judged by combining the temperature rise and the position characteristics of the characteristic points; and finally analyzing the running condition of the equipment by using a relative temperature difference method according to different pyrogenicity types to obtain a diagnosis conclusion. And (4) finishing outputting the fault diagnosis result of the current transformer by taking the coordinates of the fault point as initial seed points of a region growing method. The invention has the advantages that: the method can quickly and accurately analyze the thermal fault of the current transformer caused by current heating or voltage heating, and can evaluate the severity of the fault in a grading manner, thereby realizing the monitoring and state evaluation of the running state of the current transformer.
Description
Technical Field
The invention belongs to the field of intelligent diagnosis of infrared images and detection of running states of power equipment, and particularly relates to a current transformer fault diagnosis method based on infrared thermal image information.
Background
The current transformer is an important device for metering and protecting the power system, and if a fault occurs, the bus of the transformer substation is easily powered off, and large-area power failure occurs in an area. With the wide application of the infrared detection technology in the power grid, the method plays an active role in early finding and early preventing of the faults of the power equipment. In the existing fault analysis process, the requirement of power grid operation and inspection intellectualization cannot be met in a mode of manually analyzing faults; the automatic detection algorithm of part of faults only selects the current heating type defects with larger heating value for analysis, and neglects the detection of the faults caused by the voltage heating type defects. Therefore, the method still cannot meet the requirements of intellectualization of power grid operation and inspection and full type of fault analysis.
Disclosure of Invention
Aiming at the problems, the invention provides a current transformer fault diagnosis method based on infrared thermal image information, which realizes the analysis of full-type faults of the current transformer by using an intelligent algorithm.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows: a current transformer fault diagnosis method based on infrared thermal image information is characterized by comprising the following steps:
(1) intercepting a temperature bar from a picture to be detected, and identifying the upper limit and the lower limit of the temperature bar by using an OCR technology;
(2) calculating the temperature value corresponding to each gray value through a conversion formula of gray level and temperature, wherein the calculation formula is as follows:
in the formula TmaxAnd TminMaximum and minimum values of the temperature bar, respectively; i (x)i,yj) And T (x)i,yj) Respectively representing the gray value of a certain point in the picture and the temperature value of the corresponding point;
(3) cutting a three-phase current transformer in a picture into single-phase equipment;
(4) removing the background and the unreliable connection area of the intercepted current transformer image by using an Otsu method and morphological on-off operation;
(5) extracting characteristic points (suspicious fault points of the current transformer and reference points of reference corresponding parts) from the segmented image by using a window sliding technology, and judging the heating type by combining the temperature rise and the position characteristics of the characteristic points;
(6) calculating temperature data characteristics by using a relative temperature difference method and the like comparison method according to the heating type to judge whether the current transformer has a fault or not, and further judging the fault grade;
(7) and segmenting the fault region by using an improved region growing method, and visualizing the fault region.
Further, in the step (1), the OCR technology (character recognition technology) is used to automatically recognize the upper and lower limit data of the temperature in the picture, and the step can be divided into:
(1) automatically intercepting an area containing a temperature strip from a picture to be detected;
(2) identifying upper and lower temperature value limits of the temperature bar by using an OCR technology;
(3) carrying out manual verification on the identified data;
(4) and converting the checked text data into double-precision floating point type data.
Further, in step (5), the window sliding technique specifically includes: taking the width of the image of the single-phase current transformer as the width of a sliding window, taking one third of the height of the image as the height of the window, taking the height of the window as a step length, and screening a point with the maximum gray value in the current window from top to bottom in the image as a characteristic point;
if a plurality of points with the same gray value appear in a certain area in a window, a gray centroid method is adopted to enable the plurality of points to be equivalent to a centroid point to serve as a characteristic point.
Further, in step (5), the method for determining a heating type specifically determines the heating type of the feature point by using the coordinate information and the temperature rise value of the feature point, and the specific implementation steps are as follows:
(1) calculating the ratio of the distance between the feature point and the top center point of the picture to the height of the picture
(2) Calculating the temperature rise tau of the characteristic points;
when the characteristic point is tau>10K, judging that the heating mechanism is of current heating type, and when the characteristic point tau<10K,The heating type is a current heating type, when the temperature rise of the characteristic point is less than 10K,the heating type is a voltage heating type.
Further, in step (6), the method for determining the fault is:
(1) when the single-phase equipment feature points are extracted, converting the gray values corresponding to the feature points into temperature rise values, arranging the temperature rise values from top to bottom in sequence to form a one-dimensional array, and then arranging the array of A, B, C three-phase equipment into a matrix according to the row, wherein the formula is shown as (1-2);
(2) will min (tau)11,τ12,τ13) As a reference temperature rise point, wherein a point larger than the reference temperature rise is taken as a suspected fault point;
(3) according to the heating type, comparing the temperature difference of the surface of the equipment by using a similar comparison method to judge whether a suspected fault point of the voltage heating type is a fault or not, and judging whether the suspected fault point of the current heating type is a fault or not by using a relative temperature difference method;
(4) and finally, judging the fault level by combining DL/T664-2016 charged equipment infrared diagnosis application Specification. In this step, the relative temperature difference delta is calculatedtAnd the surface temperature difference Δ T is given by:
ΔT=τ1-τ2=T1-T2 (1-4)
wherein: tau is1Is the temperature rise of a suspected fault point of the current transformer2For reference to the temperature rise, T, of the corresponding part for the current transformer1Is the temperature, T, of a suspected fault point of the current transformer2Is the temperature of the corresponding reference part of the current transformer.
In step (7), the improved region growing method realizes automatic selection of growing seed points and automatic segmentation of fault regions. Specifically, the coordinates of a fault point are used as initial seed points for region growth, and if a plurality of fault regions occur in the same device, images obtained after multiple segmentation are superposed to realize multi-region segmentation.
The invention has the beneficial effects that: the invention introduces OCR character recognition technology to extract the maximum value and the minimum value of the temperature in the temperature bar, thereby realizing the automatic conversion of the gray scale and the temperature data in the picture. In addition, the method effectively solves the problem of classifying heating types of the current transformer, realizes fine diagnosis on different types of faults of the current transformer, and automatically divides fault areas. The method can quickly and accurately analyze the thermal fault of the current transformer caused by current heating or voltage heating, and can evaluate the severity of the fault in a grading manner, thereby realizing the monitoring and state evaluation of the running state of the current transformer.
Drawings
FIG. 1 is a flow chart of a current transformer fault intelligent diagnosis scheme of the present invention;
FIG. 2 is a flow chart of the current transformer heating type determination of the present invention;
FIG. 3 is an exemplary diagram of feature point extraction for a current transformer of the present invention;
FIG. 4 is an exemplary diagram of the automatic segmentation of the fault region of the current transformer of the present invention;
fig. 5 is an exemplary diagram of the current transformer fault diagnosis result of the present invention.
In fig. 5, 1 is a heating type, a current heating fault level: a warning; 2 is of the pyrogenic type, voltage pyrogenic fault class: a failure; and 3 is a current thermal fault grade: and generally fails.
Detailed Description
Hereinafter, the present invention will be described in detail with reference to the accompanying drawings in order to better show the present invention to researchers in the related field. It should be noted that the detailed description of the present invention with reference to the drawings is only for better conveying the contents of the present invention and the contents to be protected, and the present invention is not limited thereto.
In the embodiment, each phase current transformer in a picture is separately segmented, the characteristic points of the current transformers are extracted from the segmented image by using a window sliding technology, and the heating type is judged by combining the temperature rise and the position characteristics of the characteristic points; and calculating temperature difference of corresponding parts to distinguish suspected fault points and reference points in the characteristic points, and finally analyzing the operation condition of the equipment by using a relative temperature difference method or a similar equipment comparison method according to different heating types to obtain a diagnosis conclusion. And dividing the fault region by taking the coordinates of the fault point as initial seed points of a region growing method, realizing visualization of the size of the fault region and finishing the output of the fault diagnosis result of the current transformer.
In the embodiment, the technical scheme can realize automatic fault analysis, visualize the analysis result and realize the running state monitoring and state evaluation of the current transformer.
In one embodiment, as shown in fig. 1, the present disclosure provides a current transformer fault diagnosis method based on infrared images, including the following steps:
(1) intercepting a temperature bar from a picture to be detected, and identifying the upper limit and the lower limit of the temperature by using an OCR technology;
(2) calculating the temperature value corresponding to each gray value through a conversion formula of gray level and temperature, wherein the calculation formula is as follows:
in the formula TmaxAnd TminMaximum and minimum values of the temperature bar, respectively; i (x)i,yj) And T (x)i,yj) Respectively representing the gray value of a certain point in the picture and the temperature value of the corresponding point;
(3) cutting a three-phase current transformer in a picture into single-phase equipment;
(4) removing the background and the unreliable connection area of the intercepted current transformer image by using an Otsu method and morphological on-off operation;
(5) extracting characteristic points (suspicious fault points of the current transformer and reference points of reference corresponding parts) from the segmented image by using a window sliding technology, and judging the heating type by combining the temperature rise and the position characteristics of the characteristic points;
(6) calculating temperature data characteristics by using a relative temperature difference method and the like comparison method according to the heating type to judge whether the current transformer has a fault or not, and further judging the fault grade;
(7) and segmenting the fault region by using an improved region growing method, and visualizing the fault region.
As shown in fig. 3, the point with the maximum gray value in the current window is screened from top to bottom in the image by the window sliding technique as the feature point. The window size is set by taking the width of an image of the single-phase current transformer as the width of a sliding window, taking one third of the height of the image as the height of the window, taking the height of the window as a step length, and sliding from top to bottom in the image to extract feature data.
As shown in fig. 2, the specific implementation steps for determining the characteristic point heating type are as follows:
(5.1) calculating the ratio of the distance between the characteristic point and the top center point of the picture to the height of the picture
(5.2) calculating the temperature rise tau of the characteristic point;
when the characteristic point is tau>10K, judging that the heating mechanism is of current heating type, and when the characteristic point tau<10K,The heating type is a current heating type, when the temperature rise of the characteristic point is less than 10K,the heating type is a voltage heating type.
In fig. 3, in the current transformer fault judgment, when extracting the characteristic points of the single-phase device, the gray values corresponding to the characteristic points are converted into temperature rise values and are arranged from top to bottom in sequence to form a one-dimensional array, and then the array of A, B, C three-phase devices is arranged in a matrix according to the rows, as shown in formula (1-2).
Will min (tau)11,τ12,τ13) As a reference temperature rise point, a point larger than the reference temperature rise is taken as a suspected failure point. According to the type of the heat, the temperature difference on the surface of the equipment is compared by a similar comparison methodAnd judging whether the suspected fault point of the voltage heating type is a fault or not by using a relative temperature difference method. And finally, judging the fault level by combining DL/T664-2016 charged equipment infrared diagnosis application Specification.
The fault judgment level is as follows: relative temperature difference delta of suspected fault point when current is heatedtMore than or equal to 35 percent is a general defect, deltatThe temperature of more than or equal to 80 percent or suspected fault point is more than or equal to 55 ℃ and less than 80 ℃ which is a serious defect, deltatThe temperature of more than or equal to 95 percent and suspected fault points is more than 55 ℃ which is an emergency defect; when the surface temperature difference delta T of the voltage-induced thermal defect is larger than 4K, the fault can be judged. In addition, in the invention, the temperature threshold value can be flexibly set according to the temperature condition of the suspicious fault point, when the temperature difference of the similar comparison of the current heating type defects is more than 10K, but the relative temperature difference can not reach the common fault defect, so that the warning defect can be judged in the fault diagnosis conclusion.
In the left diagram of fig. 5, if the device is regarded as A, B, C three phases from left to right, the gray values of the heat source points of the primary junction box, the porcelain bushing and the secondary outlet end are listed from top to bottom in table 1 according to the above formula (1-5) and the highest temperature value in the picture: 26.6 ℃, minimum temperature: 7.7 ℃, the temperature values of the heat source points are calculated and are respectively shown in the following table; the data in the table show that the temperature of the heat source point of the C-phase equipment is obviously increased compared with the other two phases, and the ambient temperature is taken as: 7.7 ℃, the C-phase primary junction box belongs to a current heating type, the calculated result delta t of the relative temperature difference method is 20 percent smaller than the diagnostic standard 35 percent, but the similar comparison method can be used for obtaining that the position has a certain temperature difference, so that the condition gives a warning in the diagnostic result and the running condition of the equipment needs to be closely tracked; the porcelain bushing part belongs to a voltage heating type, and the temperature difference of similar comparison is more than 2-3 ℃ at 6.9 ℃, so that the diagnosis conclusion is that the fault is a fault defect; the secondary junction box belongs to a current heating type, the relative temperature difference delta t is 41.5% > 35%, and the hot spot temperature is less than 55 ℃, so the fault type is a common defect.
Table 1 fig. 5 current transformer A, B, C three-phase hot spot data table
As shown in fig. 4, the failure region is divided by the region growing method, and the coordinates of the failure point are used as the seed point of the region growing method to realize automatic division of the failure region. And sequentially taking the coordinates of the fault points as initial seed points to segment the same picture, and finally overlapping the regions segmented for multiple times to obtain the segmentation result of the multiple fault regions.
Claims (5)
1. A current transformer fault diagnosis method based on infrared thermal image information is characterized by comprising the following steps:
(1) intercepting a temperature bar from a picture to be detected, and identifying the upper limit and the lower limit of the temperature bar by using an OCR technology;
(2) calculating the temperature value corresponding to each gray value through a conversion formula of gray level and temperature, wherein the calculation formula is as follows:
in the formula TmaxAnd TminMaximum and minimum values of the temperature bar, respectively; i (x)i,yj) And T (x)i,yj) Respectively representing the gray value of a certain point in the picture and the temperature value of the corresponding point;
(3) cutting a three-phase current transformer in a picture into single-phase equipment;
(4) removing the background and the unreliable connection area of the intercepted current transformer image by using an Otsu method and morphological on-off operation;
(5) extracting characteristic points from the segmented image by using a window sliding technology, and judging the heating type by combining the temperature rise and the position characteristics of the characteristic points;
the window sliding technology specifically comprises the following steps: taking the width of the image of the single-phase current transformer as the width of a sliding window, taking one third of the height of the image as the height of the window, taking the height of the window as a step length, and screening a point with the maximum gray value in the current window from top to bottom in the image as a characteristic point;
if a plurality of points with the same gray value appear in a certain area in a window, a gray centroid method is adopted to enable the plurality of points to be equivalent to a centroid point as a characteristic point;
(6) calculating temperature data characteristics by using a relative temperature difference method or the like comparison method according to the heating type to judge whether the current transformer has a fault or not, and further judging the fault grade;
(7) and segmenting the fault region by using an improved region growing method, and visualizing the fault region.
2. The current transformer fault diagnosis method based on infrared thermography information according to claim 1, characterized in that: in the step (1), the OCR technology is used for automatically identifying the upper and lower limit data of the temperature in the picture, and the step can be divided into the following steps:
(1) automatically intercepting an area containing a temperature strip from a picture to be detected;
(2) identifying upper and lower temperature value limits of the temperature bar by using an OCR technology;
(3) carrying out manual verification on the identified data;
(4) and converting the checked text data into double-precision floating point type data.
3. The current transformer fault diagnosis method based on infrared thermography information according to claim 1, characterized in that: in the step (5), the method for judging the heating type judges the heating type of the characteristic point by using the coordinate information and the temperature rise value of the characteristic point, and the specific implementation steps are as follows:
(1) calculating the ratio of the distance between the feature point and the top center point of the picture to the height of the picture
(2) Calculating the temperature rise tau of the characteristic points;
when the characteristic point is tau>10K, judging that the heating mechanism is of current heating type, and when the characteristic point tau<10K,The heating type is a current heating type, when the temperature rise of the characteristic point is less than 10K,the heating type is a voltage heating type.
4. The current transformer fault diagnosis method based on infrared thermography information according to claim 1, characterized in that: in step (6), the method for determining the fault is:
(1) when the single-phase equipment feature points are extracted, converting the gray values corresponding to the feature points into temperature rise values, arranging the temperature rise values from top to bottom in sequence to form a one-dimensional array, and then arranging the array of A, B, C three-phase equipment into a matrix according to the row, wherein the formula is shown as (1-2);
(2) will min (tau)11,τ12,τ13) As a reference temperature rise point, wherein a point larger than the reference temperature rise is taken as a suspected fault point;
(3) according to the heating type, comparing the temperature difference of the surface of the equipment by using a similar comparison method to judge whether a suspected fault point of the voltage heating type is a fault or not, and judging whether the suspected fault point of the current heating type is a fault or not by using a relative temperature difference method;
(4) finally, judging the fault level; in this step, the relative temperature difference delta is calculatedtAnd the surface temperature difference Δ T is given by:
ΔT=τ1-τ2=T1-T2 (1-4)
wherein: tau is1Is the temperature rise of a suspected fault point of the current transformer2For reference to the temperature rise, T, of the corresponding part for the current transformer1Is the temperature, T, of a suspected fault point of the current transformer2Is the temperature of the corresponding reference part of the current transformer.
5. The current transformer fault diagnosis method based on infrared thermography information according to claim 1, characterized in that: in the step (7), the improved region growing method realizes automatic selection of growing seed points and automatic segmentation of fault regions; specifically, the coordinates of a fault point are used as initial seed points for region growth, and if a plurality of fault regions occur in the same device, images obtained after multiple segmentation are superposed to realize multi-region segmentation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010996979.8A CN112113667B (en) | 2020-09-21 | 2020-09-21 | Current transformer fault diagnosis method based on infrared thermal image information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010996979.8A CN112113667B (en) | 2020-09-21 | 2020-09-21 | Current transformer fault diagnosis method based on infrared thermal image information |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112113667A CN112113667A (en) | 2020-12-22 |
CN112113667B true CN112113667B (en) | 2021-08-24 |
Family
ID=73800932
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010996979.8A Active CN112113667B (en) | 2020-09-21 | 2020-09-21 | Current transformer fault diagnosis method based on infrared thermal image information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112113667B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113687156B (en) * | 2021-08-07 | 2022-09-20 | 郑州海威光电科技有限公司 | Method for assisting in judging hidden danger of power equipment by utilizing infrared chart |
CN116127858B (en) * | 2023-04-13 | 2023-06-27 | 南昌工程学院 | GIS equipment temperature rise prediction method and system based on improved sand cat algorithm optimization |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103384805A (en) * | 2011-01-31 | 2013-11-06 | 东北大学 | Operation fault detection device for electric arc furnace and method thereof |
CN107024506A (en) * | 2017-03-09 | 2017-08-08 | 深圳市朗驰欣创科技股份有限公司 | A kind of pyrogenicity defect inspection method and system |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5255152A (en) * | 1991-08-21 | 1993-10-19 | Eaton Corporation | Controller for fixed-time pull-in of a relay |
CN107784661B (en) * | 2017-09-08 | 2021-10-08 | 上海电力学院 | Transformer substation equipment infrared image classification and identification method based on region growing method |
CN111044570A (en) * | 2019-12-28 | 2020-04-21 | 广东电网有限责任公司 | Defect identification and early warning method and device for power equipment and computer equipment |
CN111339482B (en) * | 2020-03-17 | 2023-07-14 | 南昌工程学院 | Outlier distribution transformer identification method based on maximum mutual information |
-
2020
- 2020-09-21 CN CN202010996979.8A patent/CN112113667B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103384805A (en) * | 2011-01-31 | 2013-11-06 | 东北大学 | Operation fault detection device for electric arc furnace and method thereof |
CN107024506A (en) * | 2017-03-09 | 2017-08-08 | 深圳市朗驰欣创科技股份有限公司 | A kind of pyrogenicity defect inspection method and system |
Also Published As
Publication number | Publication date |
---|---|
CN112113667A (en) | 2020-12-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112113667B (en) | Current transformer fault diagnosis method based on infrared thermal image information | |
Jaffery et al. | Scheme for predictive fault diagnosis in photo-voltaic modules using thermal imaging | |
CN110266268B (en) | Photovoltaic module fault detection method based on image fusion recognition | |
CN111242123B (en) | Power equipment fault diagnosis method based on infrared image | |
CN104809732B (en) | A kind of power equipment appearance method for detecting abnormality compared based on image | |
CN111798412B (en) | Intelligent diagnosis method and system for defects of power transformation equipment based on infrared image | |
CN107103598A (en) | A kind of power cable thermal fault detection method based on infrared image clustering processing | |
CN107727662B (en) | Battery piece EL black spot defect detection method based on region growing algorithm | |
CN108254077B (en) | GIS thermal fault diagnosis method based on local and global feature information fusion | |
Di Tommaso et al. | A multi-stage model based on YOLOv3 for defect detection in PV panels based on IR and visible imaging by unmanned aerial vehicle | |
CN105445607B (en) | A kind of electrical equipment fault detection method drawn based on thermoisopleth | |
Dutta et al. | Condition monitoring of electrical equipment using thermal image processing | |
CN108680833B (en) | Composite insulator defect detection system based on unmanned aerial vehicle | |
CN112085037B (en) | Infrared thermal fault feature extraction and digital expression method for power transformation equipment | |
CN110619623B (en) | Automatic identification method for heating of joint of power transformation equipment | |
CN113723189B (en) | Intelligent power equipment fault diagnosis method based on single-order infrared image target detection | |
CN106920240A (en) | A kind of insulator identification and method for diagnosing faults based on infrared image | |
CN115290696A (en) | Infrared thermal imaging defect detection method and device for transformer substation insulator | |
CN115690012A (en) | Detection method for wrong connection line of electric energy meter | |
Zhang et al. | Intelligent detection technology of infrared image of substation equipment based on deep learning algorithm | |
Jadin et al. | Image processing methods for evaluating infrared thermographic image of electrical equipments | |
CN114694050A (en) | Power equipment running state detection method based on infrared image | |
CN116167999A (en) | Distribution line zero-value insulator infrared thermal image detection method based on image matching | |
CN109492617A (en) | Power cable diagnostic method based on K-means clustering algorithm | |
Taib et al. | Thermal imaging for qualitative-based measurements of thermal anomalies in electrical components |
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 |