CN106934802B - Decision tree-based cracked porcelain insulator judgment and diagnosis method - Google Patents
Decision tree-based cracked porcelain insulator judgment and diagnosis method Download PDFInfo
- Publication number
- CN106934802B CN106934802B CN201710137103.6A CN201710137103A CN106934802B CN 106934802 B CN106934802 B CN 106934802B CN 201710137103 A CN201710137103 A CN 201710137103A CN 106934802 B CN106934802 B CN 106934802B
- Authority
- CN
- China
- Prior art keywords
- insulator
- feature
- temperature
- cracked
- decision tree
- 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 79
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000003066 decision tree Methods 0.000 title claims abstract description 19
- 229910052573 porcelain Inorganic materials 0.000 title claims abstract description 16
- 238000003745 diagnosis Methods 0.000 title claims abstract description 8
- 239000011159 matrix material Substances 0.000 claims abstract description 4
- 239000000919 ceramic Substances 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 9
- 229910000831 Steel Inorganic materials 0.000 claims description 5
- 238000005336 cracking Methods 0.000 claims description 5
- 239000010959 steel Substances 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 2
- 238000002405 diagnostic procedure Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 17
- 230000007547 defect Effects 0.000 abstract description 3
- 238000007689 inspection Methods 0.000 abstract description 2
- 230000009286 beneficial effect Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000009194 climbing Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Theoretical Computer Science (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Radiation Pyrometers (AREA)
- Insulators (AREA)
Abstract
The invention discloses a decision tree-based cracked porcelain insulator judgment and diagnosis method, which comprises the following steps of: A. photographing the insulator, and carrying out image recognition to distinguish different insulators; B. and analyzing temperature values displayed by different insulators in the image, sorting the temperature values to form a characteristic value matrix, and judging and identifying the cracked insulator by a decision tree. The invention can improve the defects of the prior art, reduces the phenomena of normal sheet false detection and cracked sheet missing detection in the infrared detection process, improves the accuracy of the detection of the cracked porcelain insulator, can accurately and efficiently process a large number of infrared pictures in the inspection process and find out the cracked sheets.
Description
Technical Field
The invention relates to the technical field of power grid fault identification and diagnosis, in particular to a decision tree-based cracked porcelain insulator judgment and diagnosis method.
Background
At present, insulators are used in a large amount in a power transmission line, the operating environment of the insulators is an outdoor power transmission line, a traditional detection method needs to carry out pole climbing detection, a large amount of manpower and material resources are needed, and the accuracy rate of the traditional detection method is greatly influenced by factors such as the environment, the manual adjustment of the spark gap distance and the experience of operators. Even if the detection is carried out once every year, a considerable number of defective insulators still run on the line, and the potential safety operation hazard of the line is formed.
The method for detecting the defect porcelain suspension insulator is not influenced by the environment or instruments due to large workload at present, and cannot achieve the purposes of simple, quick and effective detection.
Under the influence of the saddle-shaped voltage curve, the voltage born by the insulator sheets at the two ends of the insulator string is larger, and under the high-humidity climate environment, the surface of the insulator is polluted and dissolved, and the leakage current flowing through the insulator is increased, so that the temperature rise of the normal sheets at the two ends is serious, even exceeds the normal sheets, and the false detection is easy to occur.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a decision tree-based cracked porcelain insulator judgment and diagnosis method, which can solve the defects of the prior art, reduce the phenomena of normal sheet false detection and cracked sheet missing detection in the infrared detection process, improve the accuracy of cracked porcelain insulator detection, accurately and efficiently process a large number of infrared pictures in the routing inspection process and find out cracked sheets.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows.
A decision tree-based cracked porcelain insulator judgment and diagnosis method comprises the following steps:
A. photographing the insulator, and carrying out image recognition to distinguish different insulators;
B. and analyzing temperature values displayed by different insulators in the image, sorting the temperature values to form a characteristic value matrix, and judging and identifying the cracked insulator by a decision tree.
Preferably, in the step a, all surf feature points in the infrared image are calculated, then K neighbor matching is performed on the surf feature points and a feature point set of the template data, feature points which do not belong to the insulator are screened out, and then all the feature points are spatially clustered to distinguish different insulators.
Preferably, in the K-nearest neighbor matching process, the center of a feature space composed of feature points is calculated, a mapping relationship between each feature point and the center point of the feature space is calculated, a component of each dimension of the mapping relationship is compared with the feature points, and if the correlation degree between the feature points and the dimension components of the mapping relationship is smaller than a threshold value, the feature points are deleted.
Preferably, the step B of judging and identifying the cracked insulator comprises the steps of,
b1, extracting a color legend of the infrared image to obtain temperature values corresponding to each group of RGB, and taking the temperature of the insulator porcelain in the middle of the insulator string as the ambient temperature;
b2, segmenting the insulator string image to obtain a single insulator image, and obtaining six characteristic quantities of the ceramic piece temperature, the steel cap ceramic piece temperature difference, the ceramic piece environment temperature difference, the single insulator maximum temperature and the single insulator temperature variance of the single insulator;
b3, taking the six characteristic quantities as input quantities of the decision tree to evaluate the state of the insulator;
and B4, finding out a cracking insulator.
Preferably, the selection of the attributes is measured by information gain, the attribute with the maximum information gain after splitting is selected for splitting, and a top-down greedy search is adopted to traverse a possible decision space; the value of the characteristic quantity X is { X1,xnGet each probability of { p }1,pnThe entropy of x is defined as
The information gain is for a feature, namely, the information amount of the system with the feature and the information amount of the system without the feature are respectively considered, and the difference value of the two is the information amount, namely the information gain, brought to the system by the feature;
s, where is the set of all samples, V (A) is the set of all values of attribute A, v is one of the attribute values, SvIs a sample set with the value of the attribute A in S as v;
before each non-leaf node of the decision tree is divided, information gain brought by each attribute is calculated, and the attribute with the largest information gain is selected for division.
Adopt the beneficial effect that above-mentioned technical scheme brought to lie in: the cracking insulator can be judged and identified most effectively by extracting 6 characteristic quantities of the ceramic temperature, the steel cap temperature, the ceramic steel cap temperature difference, the ceramic environment temperature difference, the single insulator temperature variance and the single insulator maximum temperature of the single insulator and utilizing a decision tree to judge which characteristic quantity or combination of the characteristic quantities. The traditional method is only a general threshold value method, and cannot overcome the influence of environment humidity and insulator position on temperature rise. The method is beneficial to improving the accuracy of detecting the cracked porcelain insulator, and has important significance in improving the detection efficiency, saving manpower and material resources and the like.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
Referring to fig. 1, one embodiment of the present invention includes the steps of:
A. photographing the insulator, and carrying out image recognition to distinguish different insulators;
B. and analyzing temperature values displayed by different insulators in the image, sorting the temperature values to form a characteristic value matrix, and judging and identifying the cracked insulator by a decision tree.
In the step A, firstly, calculating all surf characteristic points in the infrared image, then carrying out K neighbor matching with a characteristic point set of template data, screening out characteristic points which do not belong to the insulator, and then carrying out spatial clustering on all the characteristic points to distinguish different insulators.
In the K-nearest neighbor matching process, the center of a feature space formed by feature points is calculated, the mapping relation between each feature point and the center point of the feature space is calculated, the component of each dimension of the mapping relation is compared with the feature points, and if the correlation degree of the feature points and the dimension components of the mapping relation is smaller than a threshold value, the feature points are deleted.
In the step B, the step of judging and identifying the cracked insulator comprises the following steps,
b1, extracting a color legend of the infrared image to obtain temperature values corresponding to each group of RGB, and taking the temperature of the insulator porcelain in the middle of the insulator string as the ambient temperature;
b2, segmenting the insulator string image to obtain a single insulator image, and obtaining six characteristic quantities of the ceramic piece temperature, the steel cap ceramic piece temperature difference, the ceramic piece environment temperature difference, the single insulator maximum temperature and the single insulator temperature variance of the single insulator;
b3, taking the six characteristic quantities as input quantities of the decision tree to evaluate the state of the insulator;
and B4, finding out a cracking insulator.
Measuring the selection of attributes by information gain, selecting the attribute with the maximum information gain after splitting to split, and traversing possible decision space by top-down greedy search; the value of the characteristic quantity X is { X1,xnGet each probability of { p }1,pnThe entropy of x is defined as
The information gain is for a feature, namely, the information amount of the system with the feature and the information amount of the system without the feature are respectively considered, and the difference value of the two is the information amount, namely the information gain, brought to the system by the feature;
s, where is the set of all samples, V (A) is the set of all values of attribute A, v is one of the attribute values, SvIs a sample set with the value of the attribute A in S as v;
before each non-leaf node of the decision tree is divided, information gain brought by each attribute is calculated, and the attribute with the largest information gain is selected for division.
According to the invention, the infrared image of the insulator string is segmented, a plurality of temperature characteristic values of the single insulator are extracted, and the temperature characteristic values are compared with the ambient temperature to diagnose and judge the cracking sheet. The detection method is beneficial to improving the accuracy of detecting the cracked porcelain insulator, and has important significance in improving the detection efficiency, saving manpower and material resources and the like.
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, are merely for convenience of description of the present invention, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (2)
1. A decision tree-based cracked porcelain insulator judgment and diagnosis method is characterized by comprising the following steps:
A. photographing the insulator, and carrying out image recognition to distinguish different insulators;
B. analyzing temperature values displayed by different insulators in the image, sorting the temperature values to form a characteristic value matrix, and judging and identifying cracked insulators by a decision tree;
in the step A, firstly, calculating all surf characteristic points in an infrared image, then carrying out K neighbor matching with a characteristic point set of template data, screening out characteristic points which do not belong to insulators, and then carrying out spatial clustering on all the characteristic points to distinguish different insulators;
in the K-nearest neighbor matching process, calculating the center of a feature space consisting of feature points, calculating the mapping relation between each feature point and the center point of the feature space, comparing the component of each dimension of the mapping relation with the feature points, and deleting the feature points if the correlation degree of the feature points and the dimension components of the mapping relation is less than a threshold value;
in the step B, judging and identifying the cracked insulator comprises the following steps,
b1, extracting a color legend of the infrared image to obtain a temperature value, and taking the temperature of the insulator porcelain in the middle of the insulator string as the ambient temperature;
b2, segmenting the insulator string image to obtain a single insulator image, and obtaining six characteristic quantities of the ceramic piece temperature, the steel cap ceramic piece temperature difference, the ceramic piece environment temperature difference, the single insulator maximum temperature and the single insulator temperature variance of the single insulator;
b3, taking the six characteristic quantities as input quantities of the decision tree to evaluate the state of the insulator;
and B4, finding out a cracking insulator.
2. The decision tree based cracked porcelain insulator decision diagnostic method of claim 1, wherein: measuring the selection of attributes by information gain, selecting the attribute with the maximum information gain after splitting to split, and traversing possible decision space by top-down greedy search; the value of the characteristic quantity X is { X1...xnGet each probability of { p }1...pnX is a set { x }1...xnOne value of x, the entropy of x being defined as
The information gain is for a feature, namely, the information amount of the system with the feature and the information amount of the system without the feature are respectively considered, and the difference value of the two is the information amount, namely the information gain, brought to the system by the feature;
s is the set of all samples, V (A) is the set of all values of the attribute A, v is one attribute value, SvIs a sample set with the value of the attribute A in S as v;
before each non-leaf node of the decision tree is divided, information gain brought by each attribute is calculated, and the attribute with the largest information gain is selected for division.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710137103.6A CN106934802B (en) | 2017-03-09 | 2017-03-09 | Decision tree-based cracked porcelain insulator judgment and diagnosis method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710137103.6A CN106934802B (en) | 2017-03-09 | 2017-03-09 | Decision tree-based cracked porcelain insulator judgment and diagnosis method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106934802A CN106934802A (en) | 2017-07-07 |
CN106934802B true CN106934802B (en) | 2020-10-27 |
Family
ID=59432058
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710137103.6A Active CN106934802B (en) | 2017-03-09 | 2017-03-09 | Decision tree-based cracked porcelain insulator judgment and diagnosis method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106934802B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109142991B (en) * | 2018-07-05 | 2020-08-07 | 国网湖南省电力有限公司电力科学研究院 | Porcelain insulator infrared zero temperature threshold judgment method based on Burr distribution |
CN112700424B (en) * | 2021-01-07 | 2022-11-11 | 国网山东省电力公司电力科学研究院 | Infrared detection quality evaluation method for live detection of power transformation equipment |
CN114236327B (en) * | 2021-11-29 | 2024-05-31 | 国网福建省电力有限公司检修分公司 | Detection device and detection method for core rod decay defect of composite insulator |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7349889B1 (en) * | 2000-11-20 | 2008-03-25 | Rohm And Haas Electronic Materials Llc | System and method for remotely diagnosing faults |
CN102519625A (en) * | 2011-12-20 | 2012-06-27 | 昆明理工大学 | Method for measuring temperature of porcelain insulators by aid of optical fiber Bragg grating temperature sensors |
CN103792238A (en) * | 2014-02-07 | 2014-05-14 | 国家电网公司 | Porcelain suspension type insulator fault diagnosis method |
CN105846780A (en) * | 2016-03-19 | 2016-08-10 | 上海大学 | Decision tree model-based photovoltaic assembly fault diagnosis method |
CN106124949A (en) * | 2016-08-30 | 2016-11-16 | 国网山东省电力公司济南供电公司 | A kind of based on thermal infrared imaging technology to insulator breakdown on-line monitoring method |
-
2017
- 2017-03-09 CN CN201710137103.6A patent/CN106934802B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7349889B1 (en) * | 2000-11-20 | 2008-03-25 | Rohm And Haas Electronic Materials Llc | System and method for remotely diagnosing faults |
CN102519625A (en) * | 2011-12-20 | 2012-06-27 | 昆明理工大学 | Method for measuring temperature of porcelain insulators by aid of optical fiber Bragg grating temperature sensors |
CN103792238A (en) * | 2014-02-07 | 2014-05-14 | 国家电网公司 | Porcelain suspension type insulator fault diagnosis method |
CN105846780A (en) * | 2016-03-19 | 2016-08-10 | 上海大学 | Decision tree model-based photovoltaic assembly fault diagnosis method |
CN106124949A (en) * | 2016-08-30 | 2016-11-16 | 国网山东省电力公司济南供电公司 | A kind of based on thermal infrared imaging technology to insulator breakdown on-line monitoring method |
Non-Patent Citations (2)
Title |
---|
一种基于SURF特征的零件识别算法;袁安富等;《计算机应用与软件》;20150131;第32卷(第1期);摘要、第186-189页 * |
基于组合决策树的油浸式电力变压器故障诊断;董明等;《中国电机工程学报》;20050831;第25卷(第16期);摘要,第35-39页 * |
Also Published As
Publication number | Publication date |
---|---|
CN106934802A (en) | 2017-07-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108765373B (en) | Insulator abnormity automatic detection method based on integrated classifier online learning | |
CN108562589B (en) | Method for detecting surface defects of magnetic circuit material | |
CN111242123B (en) | Power equipment fault diagnosis method based on infrared image | |
CN107507194B (en) | Insulator string fault detection method based on infrared image temperature distribution rule and BP neural network | |
WO2017190574A1 (en) | Fast pedestrian detection method based on aggregation channel features | |
CN106570853B (en) | Shape and color fused insulator identification and defect detection method | |
CN106326808B (en) | Method for detecting bird nest on power transmission line tower based on unmanned aerial vehicle image | |
CN114419025A (en) | Fiberboard quality evaluation method based on image processing | |
CN106934802B (en) | Decision tree-based cracked porcelain insulator judgment and diagnosis method | |
CN105205488B (en) | Word area detection method based on Harris angle points and stroke width | |
CN103529362B (en) | Based on insulator identification and the defect diagnostic method of perception | |
CN108520514B (en) | Consistency detection method for electronic elements of printed circuit board based on computer vision | |
WO2018010387A1 (en) | Reversed element detection method and system | |
CN107833211B (en) | Infrared image-based zero value insulator automatic detection method and device | |
CN116109635B (en) | Method, device, equipment and medium for detecting surface quality of composite suspension insulator | |
CN105513039A (en) | Charged insulator string icing bridging degree intelligent image analysis method | |
CN110688958A (en) | Intersection identification method based on GoogleLeNet neural network | |
CN112529901B (en) | Crack identification method in complex environment | |
CN112489026A (en) | Asphalt pavement disease detection method based on multi-branch parallel convolution neural network | |
CN110826571B (en) | Image traversal algorithm for rapid image identification and feature matching | |
CN104881668B (en) | A kind of image fingerprint extracting method and system based on representative local mode | |
CN108596196A (en) | A kind of filthy state evaluating method based on insulator characteristics of image dictionary | |
CN115294109A (en) | Real wood board production defect identification system based on artificial intelligence, and electronic equipment | |
CN115019294A (en) | Pointer instrument reading identification method and system | |
CN111507189A (en) | Insulator string defect rapid detection method based on image processing technology |
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 |