CN114581405A - Method for detecting appearance abnormity of electrical equipment based on textural features - Google Patents

Method for detecting appearance abnormity of electrical equipment based on textural features Download PDF

Info

Publication number
CN114581405A
CN114581405A CN202210209968.XA CN202210209968A CN114581405A CN 114581405 A CN114581405 A CN 114581405A CN 202210209968 A CN202210209968 A CN 202210209968A CN 114581405 A CN114581405 A CN 114581405A
Authority
CN
China
Prior art keywords
image
same
current shot
historical
condition
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210209968.XA
Other languages
Chinese (zh)
Inventor
王磊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Binzhou University
Original Assignee
Binzhou University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Binzhou University filed Critical Binzhou University
Priority to CN202210209968.XA priority Critical patent/CN114581405A/en
Publication of CN114581405A publication Critical patent/CN114581405A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/32—Determination of transform parameters for the alignment of images, i.e. image registration using correlation-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20021—Dividing image into blocks, subimages or windows
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The invention relates to a method for detecting appearance abnormity of electric power equipment based on textural features, which comprises the following steps: acquiring image information of the power equipment and preprocessing the image information; comparing the current shot image with the historical image with normal appearance under the same environmental factors, and judging that the historical image is the same image or similar image; when the number of the same images and the number of the similar images are more than or equal to 1, judging whether the current shot image is normal or abnormal; when the same image and the similar image are only 1, judging whether the current shot image is normal or abnormal; and if the same image and the similar image do not exist, recording the related information. The invention provides a method for detecting the appearance abnormity of monitored electric equipment by comparing the similarity of the same or similar images with the current shot image through detecting environmental variables; the method can monitor equipment under various different application scenes, has stronger adaptability, and can effectively improve the accuracy of appearance abnormity detection.

Description

Texture feature-based power equipment appearance abnormity detection method
Technical Field
The invention relates to the technical field of power system equipment detection, in particular to a power equipment appearance abnormity detection method based on texture characteristics.
Background
The power transmission and transformation equipment of the power system has multiple points and wide range, most of the power transmission and transformation equipment is outdoors for a long time, and the power transmission and transformation equipment is extremely easy to be threatened by various natural disasters, meteorological conditions and external damage, and brings hidden dangers to the running stability and safety of the power system to a certain extent. According to user statistics, tripping events caused by external hidden dangers such as fire disasters, ice damage, galloping, pollution flashover, deterioration, external damage and the like are in a trend of increasing year by year. With the large-scale application of video monitoring and the theoretical research and application of image processing and recognition technology, good application effects such as transformer, high-voltage insulator, disconnecting link state in a substation and foreign matter invasion of a power transmission line are obtained, but the problems of limited detection function, low recognition accuracy and the like still exist in the prior art.
Patent application No. 201610207490.1 entitled "method and system for identifying abnormal power equipment images" describes identifying abnormal power equipment images by extracting power equipment features from power equipment images, identifying power equipment and its image area based on the power equipment features, and then comparing the image of the image area with a corresponding comparison image to determine whether there is an abnormal change, but the method does not refer to specific method steps for extracting image features.
The patent application with the application number of 201510229248.X and the invention name of "a method for detecting appearance abnormality of electric equipment based on image comparison" proposes to compare two images shot by an inspection robot at the same stopping point and at the same angle and different time, and to realize abnormality detection of damage, foreign matter suspension and the like of the electric equipment by judging the regional change of the current shot image and the historical inspection shot image with the same content, but the method does not mention a specific method how to eliminate image recognition detection under different environmental backgrounds.
Disclosure of Invention
The invention aims to provide a texture feature-based power equipment appearance abnormity detection method which judges whether power equipment in a current shot image is abnormal or not by acquiring image information of the power equipment, comparing conditions according to environmental factor information and comparing similarity of the same or similar images.
In order to achieve the purpose, the invention adopts the following technical scheme: a method for detecting appearance abnormality of electric equipment based on textural features comprises the following steps:
(1) acquiring image information of the power equipment and preprocessing the image information, wherein the preprocessed image information of the power equipment contains environmental factor information;
(2) comparing the current shot image with the historical image with normal appearance under the same environmental factors, and judging that the historical image is the same image or similar image;
(3) if the number of the same images and the number of the similar images are more than or equal to 1, dividing the current shot image and one of the same images into a plurality of parts, performing cosine similarity calculation on the parts at the same positions after division to obtain a plurality of cosine similarities, and averaging the cosine similarities to obtain a cosine similarity mean value; by analogy, cosine similarity calculation is carried out on the current shot image and all the same images, if all cosine similarity mean values are greater than or equal to 0.9, the current shot image is considered to be normal, otherwise, the current shot image is considered to be abnormal; calculating cosine similarity of a segmented part with the cosine similarity smaller than 0.9 in the current shot image and a part at the same position after segmentation of a similar image to obtain a plurality of cosine similarities, and averaging the plurality of cosine similarities to obtain a cosine similarity mean value; by analogy, cosine similarity calculation is carried out on the current shot image and all similar images, if all cosine similarity mean values are greater than or equal to 0.8, the current shot image is considered to be normal, otherwise, the current shot image is considered to be abnormal;
(4) if the same image and the similar image are only 1, the current shot image, the same image and the similar image are divided into a plurality of parts, cosine similarity calculation is carried out on the parts at the same positions after division, if all cosine similarity mean values are more than or equal to 0.8, the current shot image is considered to be normal, otherwise, the current shot image is considered to be abnormal;
(5) and if the same image and the similar image do not exist, recording the related information.
The step (1) specifically comprises the following steps: the method comprises the steps of obtaining image information of the power equipment, processing the image information according to environmental factors, and enabling data information of the image information to have environmental factor information, wherein the environmental factor information comprises illumination adaptability information and natural weather information, the illumination adaptability information comprises illumination sensor data, longitude and latitude of a shooting image place and date and time of shooting an image, and the natural weather information comprises rain and snow sensor data, environment dust and haze sensor data and temperature and humidity and wind sensor data.
The step (2) specifically comprises the following steps: comparing the current shot image with the historical image with normal appearance under the same environmental factor, if all five conditions from condition 1 to condition 5 are met, judging that the current shot image is the same as the historical image with normal appearance under the same environmental factor, and judging that the historical image is the same image; if the five conditions from the condition 1 to the condition 5 are at least two and include the condition 2, judging that the current shot image is similar to the historical image with normal appearance under the same environmental factors, and judging that the historical image is a similar image;
condition 1: calling longitude and latitude of a current image shooting place and date and time of shooting an image, comparing the longitude and latitude of the current image shooting place with a historical image, and if the longitude and latitude of the image shooting place are the same and the date and time of shooting the image is within 10 days, considering that the historical image meets the conditions;
condition 2: the method comprises the steps of calling illumination sensor data of a current shooting image place, comparing the illumination sensor data with a historical image, and if the difference value of illumination is less than +/-10%, determining that the historical image meets the condition;
condition 3: calling the data of the rain and snow sensor at the current shot image location, comparing the data with the historical image, and if the data are the same, determining that the historical image meets the condition;
condition 4: the method comprises the steps of calling environmental dust haze sensor data of a current shot image place, comparing the environmental dust haze sensor data with a historical image, and if the difference value of the data is less than +/-20%, determining that the historical image meets the condition;
condition 5: and (3) transferring the temperature, humidity and wind sensor data of the current shooting image site, comparing the data with the historical image, and if the data difference is less than +/-10%, determining that the historical image meets the condition.
The step (3) specifically comprises the following steps:
if the number of the same image and the number of the similar images are both more than or equal to 1, dividing the current shot image and the same image into small squares by average according to areas, wherein each small square is named as (n m), n represents a column, m represents a row, cosine similarity calculation is carried out on the same part (n m) of the current shot image and the same image, a vector of the small square (n m) in the current shot image is represented by A, a vector of the small square (n m) in the same image is represented by B, and cosine values among A, B are obtained by using an Euclidean dot product formula:
A·B＝∣∣A∣∣∣∣B∣∣cosθ
where θ represents the angle between A, B two phasors, the cosine of the angle θ is found by the following equation:
Figure BDA0003530600150000031
a hereini、BiRepresenting the components of vectors a and B, respectively;
the similarity given ranges from-1 to 1: a 1 means that the two vectors point in exactly the opposite direction, a 1 means that their points are exactly the same, a 0 usually means that they are independent, and a value between them means an intermediate similarity or dissimilarity.
According to the technical scheme, the invention has the beneficial effects that: firstly, the invention provides a method for comparing the similarity of the same or similar images with the current shot image by detecting environmental variables, so as to achieve the purpose of detecting the appearance abnormality of the monitored electric power equipment; secondly, the method can monitor equipment under various different application scenes, has stronger adaptability and can effectively improve the accuracy of appearance abnormity detection.
Drawings
FIG. 1 is a flow chart of a method of the present invention;
fig. 2 is a schematic diagram of the corresponding positions of image segmentation.
Detailed Description
As shown in fig. 1, a method for detecting appearance abnormality of an electrical device based on texture features includes the following steps:
(1) acquiring image information of the power equipment and preprocessing the image information, wherein the preprocessed image information of the power equipment contains environmental factor information;
(2) comparing the current shot image with the historical image with normal appearance under the same environmental factors, and judging that the historical image is the same image or similar image;
(3) if the number of the same images and the number of the similar images are more than or equal to 1, dividing the current shot image and one of the same images into a plurality of parts, calculating cosine similarity of the parts at the same positions after division to obtain a plurality of cosine similarities, and averaging the cosine similarities to obtain a cosine similarity mean value; by analogy, cosine similarity calculation is carried out on the current shot image and all the same images, if all cosine similarity mean values are greater than or equal to 0.9, the current shot image is considered to be normal, otherwise, the current shot image is considered to be abnormal; calculating cosine similarity of a segmented part with the cosine similarity smaller than 0.9 in the current shot image and a part at the same position after segmentation of a similar image to obtain a plurality of cosine similarities, and averaging the plurality of cosine similarities to obtain a cosine similarity mean value; by analogy, cosine similarity calculation is carried out on the current shot image and all similar images, if all cosine similarity mean values are greater than or equal to 0.8, the current shot image is considered to be normal, otherwise, the current shot image is considered to be abnormal;
(4) if the same image and the similar image are only 1, the current shot image, the same image and the similar image are divided into a plurality of parts, cosine similarity calculation is carried out on the parts at the same positions after division, if all cosine similarity mean values are more than or equal to 0.8, the current shot image is considered to be normal, otherwise, the current shot image is considered to be abnormal;
(5) and if the same image and the similar image do not exist, recording the related information.
The step (1) specifically comprises the following steps: the method comprises the steps of obtaining image information of the power equipment, processing the image information according to environmental factors, enabling the data information to have environmental factor information, wherein the environmental factor information comprises illumination adaptability information and natural weather information, the illumination adaptability information comprises illumination sensor data, longitude and latitude of a shooting image place and date and time of shooting an image, and the natural weather information comprises rain and snow sensor data, environment dust and haze sensor data and temperature and humidity and wind sensor data.
The step (2) specifically comprises the following steps: comparing the current shot image with the historical image with normal appearance under the same environmental factor, if all five conditions from condition 1 to condition 5 are met, judging that the current shot image is the same as the historical image with normal appearance under the same environmental factor, and judging that the historical image is the same image; if the five conditions from the condition 1 to the condition 5 are at least two and include the condition 2, judging that the current shot image is similar to the historical image with normal appearance under the same environmental factors, and judging that the historical image is a similar image;
condition 1: calling longitude and latitude of a current image shooting place and date and time of shooting an image, comparing the longitude and latitude of the current image shooting place with a historical image, and if the longitude and latitude of the image shooting place are the same and the date and time of shooting the image is within 10 days, considering that the historical image meets the conditions;
condition 2: the method comprises the steps of calling illumination sensor data of a current shooting image place, comparing the illumination sensor data with a historical image, and if the difference value of illumination is less than +/-10%, determining that the historical image meets the condition;
condition 3: calling the data of the rain and snow sensor at the current shot image location, comparing the data with the historical image, and if the data are the same, determining that the historical image meets the condition;
condition 4: the method comprises the steps of calling environmental dust haze sensor data of a current shot image place, comparing the environmental dust haze sensor data with a historical image, and if the difference value of the data is less than +/-20%, determining that the historical image meets the condition;
condition 5: and (3) transferring the temperature, humidity and wind power sensor data of the current image shooting site, comparing the temperature, humidity and wind power sensor data with the historical image, and if the data difference is less than +/-10%, determining that the historical image meets the conditions.
The step (3) specifically comprises the following steps:
as shown in fig. 2, if the number of the same image and the number of the similar images are both equal to or greater than 1, the current captured image and the same image are divided into small squares by area, each small square is named as (nm), n represents a column, m represents a row, the same part (n m) in the current captured image and the same image is subjected to cosine similarity calculation, the vector of the small square (n m) in the current captured image is represented by a, the vector of the small square (n m) in the same image is represented by B, and the cosine value between A, B is obtained by using the euclidean dot product formula:
A·B＝∣∣A∣∣∣∣B∣∣cosθ
where θ represents the angle between A, B two phasors, the cosine of the angle θ is found by the following equation:
Figure BDA0003530600150000061
a hereini、BiRepresenting the components of vectors a and B, respectively;
the similarity given ranges from-1 to 1: a 1 means that the two vectors point in exactly the opposite direction, a 1 means that their points are exactly the same, a 0 usually means that they are independent, and a value between them means an intermediate similarity or dissimilarity.
In summary, the invention proposes that the similarity of the same or similar images is compared with the similarity of the current shot image by detecting the environmental variables, so as to achieve the purpose of detecting the appearance abnormality of the monitored power equipment; secondly, the method can monitor equipment under various different application scenes, has stronger adaptability and can effectively improve the accuracy of appearance abnormity detection.

Claims (4)

1. A method for detecting appearance abnormity of electrical equipment based on textural features is characterized in that: the method comprises the following steps in sequence:
(1) acquiring image information of the power equipment and preprocessing the image information, wherein the preprocessed image information of the power equipment contains environmental factor information;
(2) comparing the current shot image with the historical image with normal appearance under the same environmental factors, and judging that the historical image is the same image or similar image;
(3) if the number of the same images and the number of the similar images are more than or equal to 1, dividing the current shot image and one of the same images into a plurality of parts, calculating cosine similarity of the parts at the same positions after division to obtain a plurality of cosine similarities, and averaging the cosine similarities to obtain a cosine similarity mean value; by analogy, cosine similarity calculation is carried out on the current shot image and all the same images, if all cosine similarity mean values are greater than or equal to 0.9, the current shot image is considered to be normal, otherwise, the current shot image is considered to be abnormal; calculating cosine similarity of a segmented part with the cosine similarity smaller than 0.9 in the current shot image and a part at the same position after segmentation of a similar image to obtain a plurality of cosine similarities, and averaging the plurality of cosine similarities to obtain a cosine similarity mean value; by analogy, cosine similarity calculation is carried out on the current shot image and all similar images, if all cosine similarity mean values are greater than or equal to 0.8, the current shot image is considered to be normal, otherwise, the current shot image is considered to be abnormal;
(4) if the same image and the similar image are only 1, the current shot image, the same image and the similar image are divided into a plurality of parts, cosine similarity calculation is carried out on the parts at the same positions after division, if all cosine similarity mean values are more than or equal to 0.8, the current shot image is considered to be normal, otherwise, the current shot image is considered to be abnormal;
(5) and if the same image and the similar image do not exist, recording the related information.
2. The method according to claim 1, wherein the method comprises: the step (1) specifically comprises the following steps: the method comprises the steps of obtaining image information of the power equipment, processing the image information according to environmental factors, enabling the data information to have environmental factor information, wherein the environmental factor information comprises illumination adaptability information and natural weather information, the illumination adaptability information comprises illumination sensor data, longitude and latitude of a shooting image place and date and time of shooting an image, and the natural weather information comprises rain and snow sensor data, environment dust and haze sensor data and temperature and humidity and wind sensor data.
3. The method according to claim 1, wherein the method comprises: the step (2) specifically comprises the following steps: comparing the current shot image with the historical image with normal appearance under the same environmental factors, if the five conditions from the condition 1 to the condition 5 are all met, judging that the current shot image is the same as the historical image with normal appearance under the same environmental factors, and judging that the historical image is the same image; if the five conditions from the condition 1 to the condition 5 are at least two and include the condition 2, judging that the current shot image is similar to the historical image with normal appearance under the same environmental factors, and judging that the historical image is a similar image;
condition 1: calling longitude and latitude of a current image shooting place and date and time of shooting an image, comparing the longitude and latitude of the current image shooting place with a historical image, and if the longitude and latitude of the image shooting place are the same and the date and time of shooting the image is within 10 days, considering that the historical image meets the conditions;
condition 2: the method comprises the steps of calling illumination sensor data of a current shooting image place, comparing the illumination sensor data with a historical image, and if the difference value of illumination is less than +/-10%, determining that the historical image meets the condition;
condition 3: calling the data of the rain and snow sensor at the current shot image location, comparing the data with the historical image, and if the data are the same, determining that the historical image meets the condition;
condition 4: the method comprises the steps of calling environmental dust haze sensor data of a current shot image place, comparing the environmental dust haze sensor data with a historical image, and if the difference value of the data is less than +/-20%, determining that the historical image meets the condition;
condition 5: and (3) transferring the temperature, humidity and wind power sensor data of the current image shooting site, comparing the temperature, humidity and wind power sensor data with the historical image, and if the data difference is less than +/-10%, determining that the historical image meets the conditions.
4. The method according to claim 1, wherein the method comprises: the step (3) specifically comprises the following steps:
if the number of the same image and the number of the similar images are both more than or equal to 1, dividing the current shot image and the same image into small squares by average according to areas, wherein each small square is named as (nm), n represents a column, m represents a row, cosine similarity calculation is carried out on the same part of the current shot image and the same image, A represents a vector of the small squares (nm) in the current shot image, B represents a vector of the small squares (nm) in the same image, and the cosine value between A, B is obtained by using an Euclidean dot product formula:
A·B＝∣∣A∣∣∣∣B∣∣cosθ
where θ represents the angle between A, B phasors, the cosine of the angle θ is found by the following formula:
Figure FDA0003530600140000031
a hereini、BiRepresenting the components of vectors a and B, respectively;
the similarity given ranges from-1 to 1: a 1 means that the two vectors point in exactly the opposite direction, a 1 means that their points are exactly the same, a 0 usually means that they are independent, and a value between them means an intermediate similarity or dissimilarity.
CN202210209968.XA 2022-03-03 2022-03-03 Method for detecting appearance abnormity of electrical equipment based on textural features Pending CN114581405A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210209968.XA CN114581405A (en) 2022-03-03 2022-03-03 Method for detecting appearance abnormity of electrical equipment based on textural features

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210209968.XA CN114581405A (en) 2022-03-03 2022-03-03 Method for detecting appearance abnormity of electrical equipment based on textural features

Publications (1)

Publication Number Publication Date
CN114581405A true CN114581405A (en) 2022-06-03

Family

ID=81778631

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210209968.XA Pending CN114581405A (en) 2022-03-03 2022-03-03 Method for detecting appearance abnormity of electrical equipment based on textural features

Country Status (1)

Country Link
CN (1) CN114581405A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116189023A (en) * 2023-04-28 2023-05-30 成都市环境应急指挥保障中心 Method and system for realizing environment emergency monitoring based on unmanned aerial vehicle

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116189023A (en) * 2023-04-28 2023-05-30 成都市环境应急指挥保障中心 Method and system for realizing environment emergency monitoring based on unmanned aerial vehicle

Similar Documents

Publication Publication Date Title
CN111754465B (en) Insulator positioning and string dropping detection method
CN112200178B (en) Transformer substation insulator infrared image detection method based on artificial intelligence
CN108537170A (en) A kind of power equipment firmware unmanned plane inspection pin missing detection method
CN113486877B (en) Power equipment infrared image real-time detection and diagnosis method based on light artificial intelligent model
CN115512252B (en) Unmanned aerial vehicle-based power grid inspection automation method and system
CN114581405A (en) Method for detecting appearance abnormity of electrical equipment based on textural features
CN111337789A (en) Method and system for detecting fault electrical element in high-voltage transmission line
CN109523543A (en) A kind of wire strand breakage detection method based on Edge Distance
CN113095189A (en) Machine vision and data analysis-based intelligent monitoring and management system for operating environment safety of power system transformer substation
CN115184726A (en) Intelligent power grid fault real-time monitoring and positioning system and method
CN114387558B (en) Transformer substation monitoring method and system based on multi-dimensional video
CN113076899A (en) High-voltage transmission line foreign matter detection method based on target tracking algorithm
CN112595936A (en) Power transmission line composite insulator intelligent detection system based on unmanned aerial vehicle patrols and examines
Nassu et al. A computer vision system for monitoring disconnect switches in distribution substations
CN113744267B (en) Method for detecting icing and estimating thickness of transmission conductor based on deep learning
Zhang et al. Intelligent detection technology of infrared image of substation equipment based on deep learning algorithm
Weng et al. Newly designed identifying method for ice thickness on high‐voltage transmission lines via machine vision
CN116958841A (en) Unmanned aerial vehicle inspection system for power distribution line based on image recognition
CN115902541A (en) Method and system for diagnosing discharge and defects of insulator of power transmission line
CN110990792A (en) Power grid equipment icing fault rate calculation method considering meteorological factors
CN116309407A (en) Method for detecting abnormal state of railway contact net bolt
CN115147591A (en) Transformer equipment infrared image voltage heating type defect diagnosis method and system
CN111950508A (en) Substation circuit breaker appearance damage identification method
CN112884720A (en) Distribution line pollution flashover insulator detection method and system
Huang et al. Insulator detection based on deep learning method in aerial images for power line patrol

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