CN117953401B - Automatic identification method and system for complex background infrared image composite insulator heating defects - Google Patents
Automatic identification method and system for complex background infrared image composite insulator heating defects Download PDFInfo
- Publication number
- CN117953401B CN117953401B CN202410346502.3A CN202410346502A CN117953401B CN 117953401 B CN117953401 B CN 117953401B CN 202410346502 A CN202410346502 A CN 202410346502A CN 117953401 B CN117953401 B CN 117953401B
- Authority
- CN
- China
- Prior art keywords
- composite insulator
- central axis
- core rod
- infrared
- frequency component
- 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
- 239000012212 insulator Substances 0.000 title claims abstract description 305
- 239000002131 composite material Substances 0.000 title claims abstract description 281
- 238000010438 heat treatment Methods 0.000 title claims abstract description 52
- 230000007547 defect Effects 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000001514 detection method Methods 0.000 claims abstract description 23
- 230000011218 segmentation Effects 0.000 claims abstract description 23
- 238000009529 body temperature measurement Methods 0.000 claims description 58
- 238000012360 testing method Methods 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 15
- 238000007689 inspection Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 12
- 230000001413 cellular effect Effects 0.000 claims description 11
- 238000005516 engineering process Methods 0.000 claims description 11
- 238000000354 decomposition reaction Methods 0.000 claims description 10
- 238000002372 labelling Methods 0.000 claims description 10
- 230000005540 biological transmission Effects 0.000 claims description 8
- 238000012805 post-processing Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- GNFTZDOKVXKIBK-UHFFFAOYSA-N 3-(2-methoxyethoxy)benzohydrazide Chemical compound COCCOC1=CC=CC(C(=O)NN)=C1 GNFTZDOKVXKIBK-UHFFFAOYSA-N 0.000 claims description 3
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
- G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
- G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
- G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Biodiversity & Conservation Biology (AREA)
- Remote Sensing (AREA)
- Radiation Pyrometers (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention discloses a complex background infrared image composite insulator heating defect automatic identification method and system. The existing identification method depends on manual operation, or needs priori equipment parameters, or has insufficient segmentation and positioning precision on a composite insulator in a complex background infrared image, so that rapid processing of a large number of infrared images is limited. According to the invention, the positioning of the central axis of the composite insulator core rod in complex background infrared images of mountain bodies, ground surfaces, towers and the like and the acquisition of a temperature curve thereof are realized through image processing, and the length of a composite insulator region corresponding to the temperature curve is obtained by combining unmanned aerial vehicle infrared autonomous air route parameters, so that whether the target composite insulator has a heating defect is judged through the maximum value of the absolute value of the gradient of the low-frequency component of the central axis temperature of the core rod and the gradient kurtosis of the gradient of the low-frequency component of the central axis temperature of the core rod, and the infrared detection and analysis precision of on-site complex background composite insulator equipment is obviously improved on the premise of not depending on priori information.
Description
Technical Field
The invention belongs to the field of composite insulators of power grids, relates to intelligent analysis and judgment of heating defects of a field composite insulator, and particularly relates to an automatic identification method and system of the heating defects of an infrared image composite insulator, which are combined with autonomous routing inspection route parameters and are suitable for a field complex background environment.
Background
The composite insulator has huge specification, and the composite insulator mainly faces the heating problems caused by core rod decay, surface dirt and the like during operation, and when the heating defects continuously develop, the composite insulator is further broken, so that serious faults such as power transmission line disconnection and the like are caused. For the heating defect, unmanned aerial vehicle infrared detection is a common means at present.
At present, the infrared detection of the unmanned aerial vehicle on site generates a large amount of infrared detection images, and the existing analysis method comprises the following modes: firstly, a temperature measuring line or a temperature measuring frame is added manually to obtain temperature differences of different parts of the composite insulator, so that heating defect judgment is carried out; secondly, a temperature measuring line is added manually, the temperature measuring line is analyzed, and whether the heating defect exists or not is judged by utilizing the temperature distribution characteristics; and thirdly, the composite insulator is segmented by an artificial intelligence means, the central line of a core rod of the composite insulator is obtained, a temperature curve of the composite insulator is obtained, and whether the heating defect exists or not is judged by utilizing the temperature distribution characteristics.
The first method relies on manual operation and judgment, so that the workload is heavy, and the analysis is influenced by subjective factors of staff. The second mode reduces the influence of subjective factors of personnel, but a temperature measuring line still needs to be manually added, so that the degree of automation is insufficient; meanwhile, the prior parameters such as the length, the number of umbrella skirts and the like of the composite insulator are calculated to realize the calculation of the characteristic quantity. The third mode realizes automatic analysis, but has insufficient adaptability to complex backgrounds such as mountain, towers, ground and the like which are common in the field, and the segmentation of the composite insulator is often larger in deviation under the complex backgrounds, so that a temperature measuring line deviates from the insulator, and the final result is influenced.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides an automatic identification method and an automatic identification system for the heating defects of a complex background infrared image composite insulator combined with an autonomous routing inspection route.
For this purpose, the invention adopts a technical scheme as follows: a complex background infrared image composite insulator heating defect automatic identification method comprises the following steps:
a) Collecting or drawing an infrared autonomous routing inspection route of the unmanned aerial vehicle of the power transmission line, and obtaining an infrared test distance of the composite insulator, a height direction resolution of infrared equipment of the unmanned aerial vehicle and a spatial resolution of infrared equipment of the unmanned aerial vehicle;
b) Carrying out infrared temperature measurement on the in-process composite insulator to obtain an infrared temperature measurement image of the composite insulator;
c) Establishing a composite insulator core rod central axis detection model by using a machine vision target segmentation technology based on a Mask R-CNN algorithm and a skeleton extraction method based on a cellular automaton, obtaining a composite insulator core rod central axis, and obtaining a composite insulator core rod central axis temperature curve by combining temperature field data of a composite insulator infrared temperature measurement image;
d) Obtaining the geometrical length of the insulator corresponding to the central axis of the composite insulator core rod according to the included angle between the central axis of the composite insulator core rod and the vertical direction in the shot infrared temperature measurement image, the resolution in the height direction of the infrared equipment of the unmanned aerial vehicle and the spatial resolution of the infrared equipment of the unmanned aerial vehicle;
e) Acquiring a low-frequency component of the temperature of the central axis of the composite insulator core rod;
f) Carrying out gradient calculation on the low-frequency component of the central axis temperature of the composite insulator core rod to obtain the maximum value of the gradient absolute value of the low-frequency component of the central axis temperature of the core rod;
g) Kurtosis calculation is carried out on the low-frequency component gradient of the temperature of the central axis of the core rod, so that the kurtosis of the low-frequency component gradient of the temperature of the central axis of the core rod is obtained;
h) And carrying out composite insulator heating identification based on the maximum value of the absolute value of the low-frequency component gradient of the central axis temperature of the core rod and the kurtosis of the low-frequency component gradient of the central axis temperature of the core rod.
According to the method, the positioning of the central axis of the composite insulator core rod in complex background infrared images of mountain bodies, ground surfaces, towers and the like and the acquisition of a temperature curve thereof are realized through image processing, the length of a composite insulator region corresponding to the temperature curve is obtained by combining unmanned aerial vehicle infrared autonomous air route parameters, and then whether the target composite insulator has a heating defect is judged through the maximum value of the gradient absolute value of the central axis temperature low-frequency component and the gradient kurtosis of the central axis temperature low-frequency component of the core rod.
Further, in the step c), the composite insulator core rod central axis detection model is established through the following steps:
c1 Collecting a historical composite insulator infrared temperature measurement image;
c2 Selecting a part of the acquired composite insulator infrared temperature measurement image as a training set and the rest part as a testing set;
c3 Labeling the infrared temperature measurement image in the training set, labeling the external contour line of the composite insulator, and generating a labeled data set and a corresponding label data set;
c4 Performing Mask R-CNN model training by using the marked data set and the corresponding label data set through a machine vision target segmentation technology based on a Mask R-CNN algorithm;
c5 Performing target segmentation on the infrared temperature measurement image in the test set by using the trained Mask R-CNN model to obtain the detected bounding box and segmentation Mask information of the composite insulator, further performing contour boundary post-processing by using a Douglas-Peucker algorithm, highlighting a polygonal main line, removing detail points which do not affect a contour structure, and realizing contour simplification;
c6 Aiming at the composite insulator contour processed in c 5), adopting a skeleton extraction method based on a cellular automaton, and obtaining the central axis of the composite insulator core rod by iteratively extracting the skeleton of the composite insulator contour to form a composite insulator core rod central axis detection model.
Further, in step d), the geometric length H m of the insulator corresponding to the central axis of the composite insulator mandrel is calculated by the following steps:
d1 Determining unmanned aerial vehicle infrared equipment parameters including unmanned aerial vehicle infrared equipment height direction resolution Pc and unmanned aerial vehicle infrared equipment spatial resolution Rs;
d2 Determining an included angle theta between the central axis of the composite insulator core rod and the vertical direction in the shot infrared temperature measurement image based on the central axis of the composite insulator obtained in the step c);
d3 The infrared test distance is converted, and the shooting distance L c after conversion is as follows:
,
Wherein L is a composite insulator infrared test distance obtained according to an unmanned aerial vehicle infrared autonomous routing inspection route, pc is unmanned aerial vehicle infrared equipment height direction resolution, and Rs is unmanned aerial vehicle infrared equipment spatial resolution;
d4 Calculating the geometrical length H m of the insulator corresponding to the central axis of the composite insulator core rod:
,
Wherein m is the number of data points of the central axis temperature curve of the composite insulator core rod; n represents the number of the temperature curve data points of the central axis of the composite insulator core rod corresponding to the straight line formed between the two intersection points, wherein the central axis of the core rod extends towards the two ends in the direction of the central axis of the core rod and is respectively connected with the upper boundary and the lower boundary of the infrared temperature measurement image.
Further, in step e), the low-frequency component f LT of the central axis temperature of the composite insulator core rod is obtained by wavelet decomposition and low-frequency component reconstruction from the central axis temperature curve of the composite insulator core rod, the adopted wavelet basis is dmey, and the decomposition layer number is3 or 4.
Further, in step f), the relationship between the maximum value k Lmax of the absolute value of the gradient of the low frequency component of the central axis temperature of the composite insulator core rod and the low frequency component f LT of the central axis temperature of the composite insulator core rod is:
,
Wherein k 2 (i) is the gradient of the ith data position in the low-frequency component f LT of the central axis temperature of the composite insulator core rod.
Further, in step g), the relationship between the gradient kurtosis F d of the low-frequency component of the temperature of the central axis of the mandrel and the gradient k 2 of the low-frequency component of the temperature of the central axis of the mandrel is:
In the method, in the process of the invention, The average value of the low-frequency component gradient of the central axis temperature of the composite insulator core rod is obtained, and q is the number of data points of the low-frequency component gradient k 2 of the central axis temperature of the core rod.
Further, in the step h), the criterion of the composite insulator heating identification is as follows:
,
Wherein F d represents the gradient kurtosis of the low-frequency component of the temperature of the central axis of the composite insulator core rod, and k Lmax represents the maximum value of the absolute value of the gradient of the low-frequency component of the temperature of the central axis of the composite insulator core rod;
When G is larger than 0, judging that the composite insulator has a heating defect; and when G is smaller than 0, judging that the composite insulator is in a normal state.
The invention adopts another technical scheme that: a complex background infrared image composite insulator heating defect automatic identification system comprises:
Unmanned aerial vehicle infrared equipment parameter acquisition unit: collecting or drawing an infrared autonomous routing inspection route of the unmanned aerial vehicle of the power transmission line, and obtaining an infrared test distance of the composite insulator, a height direction resolution of infrared equipment of the unmanned aerial vehicle and a spatial resolution of infrared equipment of the unmanned aerial vehicle;
The composite insulator infrared temperature measurement image acquisition unit comprises: carrying out infrared temperature measurement on the in-process composite insulator to obtain an infrared temperature measurement image of the composite insulator;
The central axis temperature curve acquisition unit of the composite insulator core rod: establishing a composite insulator core rod central axis detection model by using a machine vision target segmentation technology based on a Mask R-CNN algorithm and a skeleton extraction method based on a cellular automaton, obtaining a composite insulator core rod central axis, and obtaining a composite insulator core rod central axis temperature curve by combining temperature field data of a composite insulator infrared temperature measurement image;
insulator geometry length acquisition unit: obtaining the geometrical length of the insulator corresponding to the central axis of the composite insulator core rod according to the included angle between the central axis of the composite insulator core rod and the vertical direction in the shot infrared temperature measurement image, the resolution in the height direction of the infrared equipment of the unmanned aerial vehicle and the spatial resolution of the infrared equipment of the unmanned aerial vehicle;
A low frequency component acquisition unit: acquiring a low-frequency component of the temperature of the central axis of the composite insulator core rod;
Maximum value calculation unit of low frequency component gradient absolute value: carrying out gradient calculation on the low-frequency component of the central axis temperature of the composite insulator core rod to obtain the maximum value of the gradient absolute value of the low-frequency component of the central axis temperature of the core rod;
A calculation unit of gradient kurtosis of the low-frequency component: kurtosis calculation is carried out on the low-frequency component gradient of the temperature of the central axis of the core rod, so that the kurtosis of the low-frequency component gradient of the temperature of the central axis of the core rod is obtained;
composite insulator identification element that generates heat: and carrying out composite insulator heating identification based on the maximum value of the absolute value of the low-frequency component gradient of the central axis temperature of the core rod and the kurtosis of the low-frequency component gradient of the central axis temperature of the core rod.
Compared with the prior art, the method and the device have the advantages that the positioning of the central axis of the composite insulator core rod in complex background infrared images of mountain bodies, ground surfaces, towers and the like and the acquisition of the temperature curve of the composite insulator core rod are realized by utilizing image processing, the length of the composite insulator region corresponding to the temperature curve is obtained by combining unmanned aerial vehicle infrared autonomous air route parameters, and then whether the target composite insulator has a heating defect is judged by the maximum value of the absolute value of the gradient of the low-frequency component of the central axis temperature of the core rod and the gradient kurtosis of the low-frequency component of the central axis temperature of the core rod, and on the premise of not depending on priori information, the infrared detection and analysis precision of on-site complex background composite insulator equipment is remarkably improved.
Drawings
FIG. 1 is a flow chart of a method for automatically identifying heating defects of a complex background infrared image composite insulator according to the invention;
FIG. 2 is a flow chart of the acquisition of the geometrical length of the insulator corresponding to the central axis temperature curve of the mandrel in the invention;
FIG. 3 is a block diagram of a complex background infrared image composite insulator heating defect automatic identification system;
FIG. 4 is a graph showing an example of the detection result of the central axis of the composite insulator core rod with the complex background of the ground, the tower and the wire in the specific embodiment of the invention;
FIG. 5 is a graph of the temperature profile of the central axis of the core rod of the target composite insulator in accordance with an embodiment of the present invention;
FIG. 6 is a graph of a low frequency component of the temperature of the central axis of the core rod of the target composite insulator in an embodiment of the invention;
FIG. 7 is a graph showing the gradient of the low frequency component of the temperature of the central axis of the core rod of the target composite insulator in the embodiment of the invention.
Detailed Description
The invention is further described below with reference to the drawings and the detailed description.
Example 1
The embodiment is a complex background infrared image composite insulator heating defect automatic identification method, as shown in fig. 1, comprising the following steps:
a) Collecting or drawing an infrared autonomous routing inspection route of the unmanned aerial vehicle of the power transmission line, and obtaining an infrared test distance of the composite insulator, a height direction resolution of infrared equipment of the unmanned aerial vehicle and a spatial resolution of infrared equipment of the unmanned aerial vehicle;
b) Carrying out infrared temperature measurement on the in-process composite insulator to obtain an infrared temperature measurement image of the composite insulator;
c) Establishing a composite insulator core rod central axis detection model by using a machine vision target segmentation technology based on a Mask R-CNN algorithm and a skeleton extraction method based on a cellular automaton, obtaining a composite insulator core rod central axis, and obtaining a composite insulator core rod central axis temperature curve by combining temperature field data of a composite insulator infrared temperature measurement image;
d) Obtaining the geometrical length of the insulator corresponding to the central axis of the composite insulator core rod according to the included angle between the central axis of the composite insulator core rod and the vertical direction in the shot infrared temperature measurement image, the resolution in the height direction of the infrared equipment of the unmanned aerial vehicle and the spatial resolution of the infrared equipment of the unmanned aerial vehicle;
e) Acquiring a low-frequency component of the temperature of the central axis of the composite insulator core rod;
f) Carrying out gradient calculation on the low-frequency component of the central axis temperature of the composite insulator core rod to obtain the maximum value of the gradient absolute value of the low-frequency component of the central axis temperature of the core rod;
g) Kurtosis calculation is carried out on the low-frequency component gradient of the temperature of the central axis of the core rod, so that the kurtosis of the low-frequency component gradient of the temperature of the central axis of the core rod is obtained;
h) And carrying out composite insulator heating identification based on the maximum value of the absolute value of the low-frequency component gradient of the central axis temperature of the core rod and the kurtosis of the low-frequency component gradient of the central axis temperature of the core rod.
Specifically, in the step c), the composite insulator core rod central axis detection model is established through the following steps:
c1 Collecting a historical composite insulator infrared temperature measurement image;
c2 Selecting a part of the acquired composite insulator infrared temperature measurement image as a training set and the rest part as a testing set;
c3 Labeling the infrared temperature measurement image in the training set, labeling the external contour line of the composite insulator, and generating a labeled data set and a corresponding label data set;
c4 Performing Mask R-CNN model training by using the marked data set and the corresponding label data set through a machine vision target segmentation technology based on a Mask R-CNN algorithm;
c5 Performing target segmentation on the infrared temperature measurement image in the test set by using the trained Mask R-CNN model to obtain the detected bounding box and segmentation Mask information of the composite insulator, further performing contour boundary post-processing by using a Douglas-Peucker algorithm, highlighting a polygonal main line, removing detail points which do not affect a contour structure, and realizing contour simplification;
c6 Aiming at the composite insulator contour processed in c 5), adopting a skeleton extraction method based on a cellular automaton, and obtaining the central axis of the composite insulator core rod by iteratively extracting the skeleton of the composite insulator contour to form a composite insulator core rod central axis detection model.
Specifically, in step d), the geometric length H m of the insulator corresponding to the central axis of the composite insulator mandrel is calculated as shown in fig. 2 by the following steps:
d1 Determining unmanned aerial vehicle infrared equipment parameters including unmanned aerial vehicle infrared equipment height direction resolution Pc and unmanned aerial vehicle infrared equipment spatial resolution Rs;
d2 Determining an included angle theta between the central axis of the composite insulator core rod and the vertical direction in the shot infrared temperature measurement image based on the central axis of the composite insulator obtained in the step c);
d3 The infrared test distance is converted, and the shooting distance L c after conversion is as follows:
,
Wherein L is a composite insulator infrared test distance obtained according to an unmanned aerial vehicle infrared autonomous routing inspection route, pc is unmanned aerial vehicle infrared equipment height direction resolution, and Rs is unmanned aerial vehicle infrared equipment spatial resolution;
d4 Calculating the geometrical length H m of the insulator corresponding to the central axis of the composite insulator core rod:
,
Wherein m is the number of data points of the central axis temperature curve of the composite insulator core rod; n represents the number of the temperature curve data points of the central axis of the composite insulator core rod corresponding to the straight line formed between the two intersection points, wherein the central axis of the core rod extends towards the two ends in the direction of the central axis of the core rod and is respectively connected with the upper boundary and the lower boundary of the infrared temperature measurement image.
Specifically, in step e), the low-frequency component f LT of the central axis temperature of the composite insulator core rod is obtained by wavelet decomposition and low-frequency component reconstruction from the central axis temperature curve of the composite insulator core rod, the adopted wavelet basis is dmey, and the decomposition layer number is 3 or 4.
Specifically, in step f), the relationship between the maximum value k Lmax of the absolute value of the gradient of the low-frequency component of the central axis temperature of the composite insulator core rod and the low-frequency component f LT of the central axis temperature of the composite insulator core rod is:
,
Wherein k 2 (i) is the gradient of the ith data position in the low-frequency component f LT of the central axis temperature of the composite insulator core rod,
Specifically, in step g), the relationship between the gradient kurtosis F d of the low-frequency component of the temperature of the central axis of the mandrel and the gradient k 2 of the low-frequency component of the temperature of the central axis of the mandrel is:
In the method, in the process of the invention, The average value of the low-frequency component gradient of the central axis temperature of the composite insulator core rod is obtained, and q is the number of data points of the low-frequency component gradient k 2 of the central axis temperature of the core rod.
Specifically, in the step h), the criterion of the composite insulator heating identification is as follows:
,
Wherein F d represents the gradient kurtosis of the low-frequency component of the temperature of the central axis of the composite insulator core rod, and k Lmax represents the maximum value of the absolute value of the gradient of the low-frequency component of the temperature of the central axis of the composite insulator core rod;
When G is larger than 0, judging that the composite insulator has a heating defect; and when G is smaller than 0, judging that the composite insulator is in a normal state.
Example 2
The embodiment provides a complex background infrared image composite insulator heating defect automatic identification system, which is composed of an unmanned aerial vehicle infrared equipment parameter acquisition unit, a composite insulator infrared temperature measurement image acquisition unit, a composite insulator core rod central axis temperature curve acquisition unit, an insulator geometric length acquisition unit, a low-frequency component acquisition unit, a maximum value calculation unit of a low-frequency component gradient absolute value, a calculation unit of low-frequency component gradient kurtosis and a composite insulator heating identification unit, as shown in fig. 3.
The unmanned aerial vehicle infrared equipment parameter acquisition unit: and collecting or drawing an infrared autonomous inspection route of the unmanned aerial vehicle of the power transmission line to obtain the infrared test distance of the composite insulator, the height direction resolution of the infrared equipment of the unmanned aerial vehicle and the spatial resolution of the infrared equipment of the unmanned aerial vehicle.
The composite insulator infrared temperature measurement image acquisition unit comprises: and carrying out infrared temperature measurement on the in-process composite insulator to obtain an infrared temperature measurement image of the composite insulator.
The central axis temperature curve acquisition unit of the composite insulator core rod comprises a central axis temperature curve acquisition unit: and establishing a composite insulator core rod central axis detection model by using a machine vision target segmentation technology based on a Mask R-CNN algorithm and a skeleton extraction method based on a cellular automaton, obtaining a composite insulator core rod central axis, and obtaining a composite insulator core rod central axis temperature curve by combining temperature field data of a composite insulator infrared temperature measurement image.
The geometrical length acquisition unit of the insulator comprises: and obtaining the geometrical length of the insulator corresponding to the central axis of the composite insulator core rod according to the included angle between the central axis of the composite insulator core rod and the vertical direction in the shot infrared temperature measurement image, the resolution in the height direction of the infrared equipment of the unmanned aerial vehicle and the spatial resolution of the infrared equipment of the unmanned aerial vehicle.
The low frequency component acquisition unit: acquiring a low-frequency component of the temperature of the central axis of the composite insulator core rod; the low-frequency component f LT of the central axis temperature of the composite insulator core rod is obtained by wavelet decomposition and low-frequency component reconstruction of the central axis temperature curve of the composite insulator core rod, the adopted wavelet basis is dmey, and the decomposition layer number is 3 or 4.
The maximum value calculating unit of the gradient absolute value of the low-frequency component: and carrying out gradient calculation on the low-frequency component of the central axis temperature of the composite insulator core rod to obtain the maximum value of the gradient absolute value of the low-frequency component of the central axis temperature of the core rod.
The calculating unit of the gradient kurtosis of the low-frequency component comprises: and (3) kurtosis calculation is carried out on the low-frequency component gradient of the central axis temperature of the core rod, so that the kurtosis of the low-frequency component gradient of the central axis temperature of the core rod is obtained.
The composite insulator heating identification unit comprises: and carrying out composite insulator heating identification based on the maximum value of the absolute value of the low-frequency component gradient of the central axis temperature of the core rod and the kurtosis of the low-frequency component gradient of the central axis temperature of the core rod.
In the composite insulator core rod central axis temperature curve acquisition unit, the composite insulator core rod central axis detection model is established through the following steps:
c1 Collecting a historical composite insulator infrared temperature measurement image;
c2 Selecting a part of the acquired composite insulator infrared temperature measurement image as a training set and the rest part as a testing set;
c3 Labeling the infrared temperature measurement image in the training set, labeling the external contour line of the composite insulator, and generating a labeled data set and a corresponding label data set;
c4 Performing Mask R-CNN model training by using the marked data set and the corresponding label data set through a machine vision target segmentation technology based on a Mask R-CNN algorithm;
c5 Performing target segmentation on the infrared temperature measurement image in the test set by using the trained Mask R-CNN model to obtain the detected bounding box and segmentation Mask information of the composite insulator, further performing contour boundary post-processing by using a Douglas-Peucker algorithm, highlighting a polygonal main line, removing detail points which do not affect a contour structure, and realizing contour simplification;
c6 Aiming at the composite insulator contour processed in c 5), adopting a skeleton extraction method based on a cellular automaton, and obtaining the central axis of the composite insulator core rod by iteratively extracting the skeleton of the composite insulator contour to form a composite insulator core rod central axis detection model.
In the insulator geometric length obtaining unit, the insulator geometric length H m corresponding to the central axis of the composite insulator core rod is calculated through the following steps:
d1 Determining unmanned aerial vehicle infrared equipment parameters including unmanned aerial vehicle infrared equipment height direction resolution Pc and unmanned aerial vehicle infrared equipment spatial resolution Rs;
d2 Determining an included angle theta between the central axis of the composite insulator core rod and the vertical direction in the shot infrared temperature measurement image based on the central axis of the composite insulator obtained in the step c);
d3 The infrared test distance is converted, and the shooting distance L c after conversion is as follows:
,
Wherein L is a composite insulator infrared test distance obtained according to an unmanned aerial vehicle infrared autonomous routing inspection route, pc is unmanned aerial vehicle infrared equipment height direction resolution, and Rs is unmanned aerial vehicle infrared equipment spatial resolution;
d4 Calculating the geometrical length H m of the insulator corresponding to the central axis of the composite insulator core rod:
,
Wherein m is the number of data points of the central axis temperature curve of the composite insulator core rod; n represents the number of the temperature curve data points of the central axis of the composite insulator core rod corresponding to the straight line formed between the two intersection points, wherein the central axis of the core rod extends towards the two ends in the direction of the central axis of the core rod and is respectively connected with the upper boundary and the lower boundary of the infrared temperature measurement image.
In the maximum value calculation unit of the low-frequency component gradient absolute value, the relation between the maximum value k Lmax of the low-frequency component gradient absolute value of the central axis temperature of the composite insulator core rod and the low-frequency component f LT of the central axis temperature of the composite insulator core rod is as follows:
,
Wherein k 2 (i) is the gradient of the ith data position in the low-frequency component f LT of the central axis temperature of the composite insulator core rod.
In the calculation unit of the low-frequency component gradient kurtosis, the relation between the low-frequency component gradient kurtosis F d of the central axis temperature of the core rod and the low-frequency component gradient k 2 of the central axis temperature of the core rod is as follows:
,
In the method, in the process of the invention, The average value of the low-frequency component gradient of the central axis temperature of the composite insulator core rod is obtained, and q is the number of data points of the low-frequency component gradient k 2 of the central axis temperature of the core rod.
In the composite insulator heating identification unit, the criterion of composite insulator heating identification is as follows:
,
Wherein F d represents the gradient kurtosis of the low-frequency component of the temperature of the central axis of the composite insulator core rod, and k Lmax represents the maximum value of the absolute value of the gradient of the low-frequency component of the temperature of the central axis of the composite insulator core rod;
When G is larger than 0, judging that the composite insulator has a heating defect; and when G is smaller than 0, judging that the composite insulator is in a normal state.
Application example
Taking inspection analysis of a 220kV composite insulator under a complex ground background as an example, the automatic identification method of the invention is applied to judge whether the insulator generates heat or not, and the specific steps are as follows:
1) Drawing an infrared autonomous routing inspection route of the unmanned aerial vehicle of the transmission line, and determining that the infrared test distance of the composite insulator is 5.5m, the height direction resolution of infrared equipment of the unmanned aerial vehicle is 512, and the spatial resolution of infrared equipment of the unmanned aerial vehicle is 1.32mrad;
2) Carrying out infrared test on the in-process composite insulator to obtain an infrared temperature measurement image of the composite insulator;
3) Obtaining the central axis of the composite insulator core rod by utilizing the central axis detection model of the composite insulator core rod, as shown in fig. 4, successfully completing the extraction of the central axis of the composite insulator core rod under the complex background comprising the ground, the tower and the wires; combining the temperature field data of the infrared temperature measurement image of the composite insulator to obtain a central axis temperature curve of the composite insulator core rod, as shown in fig. 5;
4) Determining an included angle between the central axis of the composite insulator core rod and the vertical direction to be 5 degrees based on the central axis of the composite insulator core rod determined in the previous step, and obtaining the geometrical length of the insulator corresponding to the central axis of the composite insulator core rod by combining the infrared equipment of the unmanned aerial vehicle with the height direction resolution of 512 and the infrared equipment spatial resolution of the unmanned aerial vehicle of 1.32 mrad;
5) Performing wavelet decomposition and low-frequency component reconstruction on the central axis temperature curve of the composite insulator core rod, wherein the adopted wavelet is dmey, the decomposition layer number is 4, and the central axis temperature low-frequency component of the composite insulator core rod is shown in figure 6;
6) Performing gradient calculation on the low-frequency component of the temperature of the central axis of the composite insulator core rod according to the formula (1), wherein a low-frequency component gradient curve is shown in fig. 7, and the maximum value of the absolute value of the low-frequency component gradient of the temperature of the central axis of the core rod is 0.0032K/mm;
(1)
Wherein k 2 (i) is a gradient value of the ith data position in the composite insulator temperature low-frequency component f LT, and f LT is a core rod central axis temperature low-frequency component.
7) And (3) calculating the gradient kurtosis of the low-frequency component of the central axis temperature of the core rod of the composite insulator according to the formula (2), wherein the result is 4.5419.
(2)
Wherein F d is the gradient kurtosis of the low-frequency component of the central axis temperature of the core rod,The average value of the low-frequency component gradient of the central axis temperature of the composite insulator core rod is obtained, and q is the number of data points of the low-frequency component gradient k 2 of the central axis temperature of the core rod.
8) Calculating the result of the formula (3), and judging whether the composite insulator heats or not;
(3)
When G is larger than 0, judging that the composite insulator has a heating defect; and when G is smaller than 0, judging that the composite insulator is in a normal state. The result of the calculation is-9.82, and the insulator is judged to have no heating.
The embodiments described above are described in order to facilitate the understanding and application of the present invention to those skilled in the art, and it will be apparent to those skilled in the art that various modifications may be made to the embodiments described above and that the general principles described herein may be applied to other embodiments without the need for inventive faculty. Therefore, the present invention is not limited to the above-described embodiments, and those skilled in the art, based on the present disclosure, should make improvements and modifications within the scope of the present invention.
Claims (10)
1. The automatic identification method for the heating defect of the complex background infrared image composite insulator is characterized by comprising the following steps of:
a) Collecting or drawing an infrared autonomous routing inspection route of the unmanned aerial vehicle of the power transmission line, and obtaining an infrared test distance of the composite insulator, a height direction resolution of infrared equipment of the unmanned aerial vehicle and a spatial resolution of infrared equipment of the unmanned aerial vehicle;
b) Carrying out infrared temperature measurement on the in-process composite insulator to obtain an infrared temperature measurement image of the composite insulator;
c) Establishing a composite insulator core rod central axis detection model by using a machine vision target segmentation technology based on a Mask R-CNN algorithm and a skeleton extraction method based on a cellular automaton, obtaining a composite insulator core rod central axis, and obtaining a composite insulator core rod central axis temperature curve by combining temperature field data of a composite insulator infrared temperature measurement image;
d) Obtaining the geometrical length of the insulator corresponding to the central axis of the composite insulator core rod according to the included angle between the central axis of the composite insulator core rod and the vertical direction in the shot infrared temperature measurement image, the resolution in the height direction of the infrared equipment of the unmanned aerial vehicle and the spatial resolution of the infrared equipment of the unmanned aerial vehicle;
e) Acquiring a low-frequency component of the temperature of the central axis of the composite insulator core rod;
f) Carrying out gradient calculation on the low-frequency component of the central axis temperature of the composite insulator core rod to obtain the maximum value of the gradient absolute value of the low-frequency component of the central axis temperature of the core rod;
g) Kurtosis calculation is carried out on the low-frequency component gradient of the temperature of the central axis of the core rod, so that the kurtosis of the low-frequency component gradient of the temperature of the central axis of the core rod is obtained;
h) And carrying out composite insulator heating identification based on the maximum value of the absolute value of the low-frequency component gradient of the central axis temperature of the core rod and the kurtosis of the low-frequency component gradient of the central axis temperature of the core rod.
2. The method for automatically identifying the heating defect of the complex background infrared image composite insulator according to claim 1, wherein in the step c), the central axis detection model of the composite insulator core rod is established by the following steps:
c1 Collecting a historical composite insulator infrared temperature measurement image;
c2 Selecting a part of the acquired composite insulator infrared temperature measurement image as a training set and the rest part as a testing set;
c3 Labeling the infrared temperature measurement image in the training set, labeling the external contour line of the composite insulator, and generating a labeled data set and a corresponding label data set;
c4 Performing Mask R-CNN model training by using the marked data set and the corresponding label data set through a machine vision target segmentation technology based on a Mask R-CNN algorithm;
c5 Performing target segmentation on the infrared temperature measurement image in the test set by using the trained Mask R-CNN model to obtain the detected bounding box and segmentation Mask information of the composite insulator, further performing contour boundary post-processing by using a Douglas-Peucker algorithm, highlighting a polygonal main line, removing detail points which do not affect a contour structure, and realizing contour simplification;
c6 Aiming at the composite insulator contour processed in c 5), adopting a skeleton extraction method based on a cellular automaton, and obtaining the central axis of the composite insulator core rod by iteratively extracting the skeleton of the composite insulator contour to form a composite insulator core rod central axis detection model.
3. The method for automatically identifying the heating defect of the complex background infrared image composite insulator according to claim 1, wherein in the step d), the geometrical length H m of the insulator corresponding to the central axis of the composite insulator core rod is calculated by the following steps:
d1 Determining unmanned aerial vehicle infrared equipment parameters including unmanned aerial vehicle infrared equipment height direction resolution Pc and unmanned aerial vehicle infrared equipment spatial resolution Rs;
d2 Determining an included angle theta between the central axis of the composite insulator core rod and the vertical direction in the shot infrared temperature measurement image based on the central axis of the composite insulator obtained in the step c);
d3 The infrared test distance is converted, and the shooting distance L c after conversion is as follows:
,
Wherein L is the infrared test distance of the composite insulator obtained according to the unmanned aerial vehicle infrared autonomous routing inspection route;
d4 Calculating the geometrical length H m of the insulator corresponding to the central axis of the composite insulator core rod:
,
Wherein m is the number of data points of the central axis temperature curve of the composite insulator core rod; n represents the number of the temperature curve data points of the central axis of the composite insulator core rod corresponding to the straight line formed between the two intersection points, wherein the central axis of the core rod extends towards the two ends in the direction of the central axis of the core rod and is respectively connected with the upper boundary and the lower boundary of the infrared temperature measurement image.
4. The method for automatically identifying the heating defect of the complex background infrared image composite insulator according to claim 1, wherein in the step e), the low-frequency component f LT of the central axis temperature of the composite insulator core rod is obtained by wavelet decomposition and low-frequency component reconstruction of the central axis temperature curve of the composite insulator core rod, the adopted wavelet basis is dmey, and the decomposition layer number is 3 or 4.
5. The method for automatically identifying heating defects of a composite insulator based on complex background infrared images according to claim 3, wherein in the step f), the relation between the maximum value k Lmax of the gradient absolute value of the low-frequency component of the central axis temperature of the composite insulator core rod and the low-frequency component f LT of the central axis temperature of the composite insulator core rod is:
,
Wherein k 2 (i) is the gradient of the ith data position in the low-frequency component f LT of the central axis temperature of the composite insulator core rod.
6. The method for automatically identifying the heating defect of the complex background infrared image composite insulator according to claim 1, wherein in the step g), the relation between the gradient kurtosis F d of the low-frequency component of the central axis temperature of the core rod and the gradient k 2 of the low-frequency component of the central axis temperature of the core rod is as follows:
,
In the method, in the process of the invention, The average value of the gradient of the low-frequency component of the central axis temperature of the composite insulator core rod is calculated, q is the number of data points of the gradient k 2 of the low-frequency component of the central axis temperature of the core rod, and k 2 (i) is the gradient of the ith data position in the f LT of the low-frequency component of the central axis temperature of the composite insulator core rod.
7. The method for automatically identifying the heating defect of the complex background infrared image composite insulator according to claim 1, wherein in the step h), the criterion of the heating identification of the composite insulator is as follows:
,
Wherein F d represents the gradient kurtosis of the low-frequency component of the temperature of the central axis of the composite insulator core rod, and k Lmax represents the maximum value of the absolute value of the gradient of the low-frequency component of the temperature of the central axis of the composite insulator core rod;
When G is larger than 0, judging that the composite insulator has a heating defect; and when G is smaller than 0, judging that the composite insulator is in a normal state.
8. The utility model provides a complex background infrared image composite insulator defect automatic identification system that generates heat which characterized in that includes:
Unmanned aerial vehicle infrared equipment parameter acquisition unit: collecting or drawing an infrared autonomous routing inspection route of the unmanned aerial vehicle of the power transmission line, and obtaining an infrared test distance of the composite insulator, a height direction resolution of infrared equipment of the unmanned aerial vehicle and a spatial resolution of infrared equipment of the unmanned aerial vehicle;
The composite insulator infrared temperature measurement image acquisition unit comprises: carrying out infrared temperature measurement on the in-process composite insulator to obtain an infrared temperature measurement image of the composite insulator;
The central axis temperature curve acquisition unit of the composite insulator core rod: establishing a composite insulator core rod central axis detection model by using a machine vision target segmentation technology based on a Mask R-CNN algorithm and a skeleton extraction method based on a cellular automaton, obtaining a composite insulator core rod central axis, and obtaining a composite insulator core rod central axis temperature curve by combining temperature field data of a composite insulator infrared temperature measurement image;
insulator geometry length acquisition unit: obtaining the geometrical length of the insulator corresponding to the central axis of the composite insulator core rod according to the included angle between the central axis of the composite insulator core rod and the vertical direction in the shot infrared temperature measurement image, the resolution in the height direction of the infrared equipment of the unmanned aerial vehicle and the spatial resolution of the infrared equipment of the unmanned aerial vehicle;
A low frequency component acquisition unit: acquiring a low-frequency component of the temperature of the central axis of the composite insulator core rod;
Maximum value calculation unit of low frequency component gradient absolute value: carrying out gradient calculation on the low-frequency component of the central axis temperature of the composite insulator core rod to obtain the maximum value of the gradient absolute value of the low-frequency component of the central axis temperature of the core rod;
A calculation unit of gradient kurtosis of the low-frequency component: kurtosis calculation is carried out on the low-frequency component gradient of the temperature of the central axis of the core rod, so that the kurtosis of the low-frequency component gradient of the temperature of the central axis of the core rod is obtained;
composite insulator identification element that generates heat: and carrying out composite insulator heating identification based on the maximum value of the absolute value of the low-frequency component gradient of the central axis temperature of the core rod and the kurtosis of the low-frequency component gradient of the central axis temperature of the core rod.
9. The automatic identification system for the heating defects of the complex background infrared image composite insulator according to claim 8, wherein in the composite insulator core rod central axis temperature curve acquisition unit, the composite insulator core rod central axis detection model is established by the following steps:
c1 Collecting a historical composite insulator infrared temperature measurement image;
c2 Selecting a part of the acquired composite insulator infrared temperature measurement image as a training set and the rest part as a testing set;
c3 Labeling the infrared temperature measurement image in the training set, labeling the external contour line of the composite insulator, and generating a labeled data set and a corresponding label data set;
c4 Performing Mask R-CNN model training by using the marked data set and the corresponding label data set through a machine vision target segmentation technology based on a Mask R-CNN algorithm;
c5 Performing target segmentation on the infrared temperature measurement image in the test set by using the trained Mask R-CNN model to obtain the detected bounding box and segmentation Mask information of the composite insulator, further performing contour boundary post-processing by using a Douglas-Peucker algorithm, highlighting a polygonal main line, removing detail points which do not affect a contour structure, and realizing contour simplification;
c6 Aiming at the composite insulator contour processed in c 5), adopting a skeleton extraction method based on a cellular automaton, and obtaining the central axis of the composite insulator core rod by iteratively extracting the skeleton of the composite insulator contour to form a composite insulator core rod central axis detection model.
10. The automatic recognition system for the heating defect of the complex background infrared image composite insulator according to claim 8, wherein in the composite insulator heating recognition unit, the criterion of the composite insulator heating recognition is as follows:
,
Wherein F d represents the gradient kurtosis of the low-frequency component of the temperature of the central axis of the composite insulator core rod, and k Lmax represents the maximum value of the absolute value of the gradient of the low-frequency component of the temperature of the central axis of the composite insulator core rod;
When G is larger than 0, judging that the composite insulator has a heating defect; and when G is smaller than 0, judging that the composite insulator is in a normal state.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410346502.3A CN117953401B (en) | 2024-03-26 | 2024-03-26 | Automatic identification method and system for complex background infrared image composite insulator heating defects |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410346502.3A CN117953401B (en) | 2024-03-26 | 2024-03-26 | Automatic identification method and system for complex background infrared image composite insulator heating defects |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117953401A CN117953401A (en) | 2024-04-30 |
CN117953401B true CN117953401B (en) | 2024-06-25 |
Family
ID=90799825
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410346502.3A Active CN117953401B (en) | 2024-03-26 | 2024-03-26 | Automatic identification method and system for complex background infrared image composite insulator heating defects |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117953401B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104568991A (en) * | 2014-12-18 | 2015-04-29 | 中国南方电网有限责任公司超高压输电公司天生桥局 | Detection method for defects of compound insulator, equipment and system |
CN110827278A (en) * | 2019-11-27 | 2020-02-21 | 云南电网有限责任公司电力科学研究院 | Transformer substation insulator defect online detection method and device |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106780438B (en) * | 2016-11-11 | 2020-09-25 | 广东电网有限责任公司清远供电局 | Insulator defect detection method and system based on image processing |
CN111398339B (en) * | 2020-03-26 | 2022-08-30 | 国网浙江省电力有限公司电力科学研究院 | Method and system for analyzing and judging heating defects of composite insulator of on-site overhead line |
CN111965214B (en) * | 2020-07-09 | 2023-05-16 | 国网浙江省电力有限公司电力科学研究院 | Method and system for judging heating defect of composite insulator of overhead line |
CN113358227B (en) * | 2021-04-21 | 2022-10-14 | 国网浙江省电力有限公司电力科学研究院 | Method and system for calculating local temperature difference of heating defect of composite insulator |
CN114577853B (en) * | 2022-05-05 | 2022-09-02 | 国网浙江省电力有限公司电力科学研究院 | Automatic judging method for heating defect of composite insulator |
CN115290696A (en) * | 2022-08-03 | 2022-11-04 | 重庆大学 | Infrared thermal imaging defect detection method and device for transformer substation insulator |
-
2024
- 2024-03-26 CN CN202410346502.3A patent/CN117953401B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104568991A (en) * | 2014-12-18 | 2015-04-29 | 中国南方电网有限责任公司超高压输电公司天生桥局 | Detection method for defects of compound insulator, equipment and system |
CN110827278A (en) * | 2019-11-27 | 2020-02-21 | 云南电网有限责任公司电力科学研究院 | Transformer substation insulator defect online detection method and device |
Also Published As
Publication number | Publication date |
---|---|
CN117953401A (en) | 2024-04-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110838112A (en) | Insulator defect detection method based on Hough transform and YOLOv3 network | |
CN110910440B (en) | Power transmission line length determination method and system based on power image data | |
CN112698303A (en) | Method and system for measuring point cloud tower inclination parameters based on unmanned aerial vehicle laser radar | |
CN113160184B (en) | Unmanned aerial vehicle intelligent inspection cable surface defect detection method based on deep learning | |
CN113205039B (en) | Power equipment fault image recognition disaster investigation system and method based on multiple DCNN networks | |
CN114577853B (en) | Automatic judging method for heating defect of composite insulator | |
CN114241364A (en) | Method for quickly calibrating foreign object target of overhead transmission line | |
CN113554595A (en) | Unmanned aerial vehicle laser radar point cloud tower head deformation detection device and method | |
CN113406107A (en) | Fan blade defect detection system | |
CN112455676A (en) | Intelligent monitoring and analyzing system and method for health state of photovoltaic panel | |
CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
CN113256602A (en) | Unsupervised fan blade defect detection method and system based on self-encoder | |
CN112991432A (en) | Icing shape identification method based on image processing | |
CN114943904A (en) | Operation monitoring method based on unmanned aerial vehicle inspection | |
CN108537792B (en) | Power defect image identification method based on convolutional neural network | |
CN114037694A (en) | Composite insulator defect diagnosis method based on U-net segmentation | |
CN117953401B (en) | Automatic identification method and system for complex background infrared image composite insulator heating defects | |
CN114387261A (en) | Automatic detection method suitable for railway steel bridge bolt diseases | |
CN117252840A (en) | Photovoltaic array defect elimination evaluation method and device and computer equipment | |
CN112396604B (en) | Multi-view-angle-based aircraft skin defect detection method | |
CN114565581A (en) | Detection method, recording medium and system for low-value insulator of distribution line | |
CN114220029A (en) | Detection method and device for rotary joint of groove type photo-thermal power station | |
CN113989209A (en) | Power line foreign matter detection method based on fast R-CNN | |
CN108229530B (en) | Wrist arm fault analysis method and analysis device thereof | |
CN112801120A (en) | Intelligent analysis method for unmanned aerial vehicle inspection image defects |
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 |