WO2021190056A1 - 一种瓷质绝缘子串红外零值诊断方法及系统 - Google Patents

一种瓷质绝缘子串红外零值诊断方法及系统 Download PDF

Info

Publication number
WO2021190056A1
WO2021190056A1 PCT/CN2020/142016 CN2020142016W WO2021190056A1 WO 2021190056 A1 WO2021190056 A1 WO 2021190056A1 CN 2020142016 W CN2020142016 W CN 2020142016W WO 2021190056 A1 WO2021190056 A1 WO 2021190056A1
Authority
WO
WIPO (PCT)
Prior art keywords
insulator
temperature gradient
insulator string
diagnosed
value
Prior art date
Application number
PCT/CN2020/142016
Other languages
English (en)
French (fr)
Inventor
周学明
胡丹晖
毛晓坡
尹骏刚
付剑津
冯志强
张耀东
黄泽琦
史天如
Original Assignee
国网湖北省电力有限公司电力科学研究院
湖南大学
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 国网湖北省电力有限公司电力科学研究院, 湖南大学 filed Critical 国网湖北省电力有限公司电力科学研究院
Priority to US17/276,480 priority Critical patent/US11397208B2/en
Publication of WO2021190056A1 publication Critical patent/WO2021190056A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
    • G01R31/1218—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing using optical methods; using charged particle, e.g. electron, beams or X-rays
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
    • G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
    • G01R31/1245—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of line insulators or spacers, e.g. ceramic overhead line cap insulators; of insulators in HV bushings

Definitions

  • the invention relates to the technical field of detection of porcelain insulators in substations and transmission lines, in particular to an infrared zero value diagnosis method and system for porcelain insulator strings.
  • Porcelain insulator is an important electrical insulation equipment, which is widely used in transmission lines and substations of various voltage levels.
  • the insulator string is affected by multiple complex factors such as strong electromechanical load, acid rain, strong wind, icing, ultraviolet rays, pollution, and drastic changes in temperature and humidity. It is prone to degradation failures such as low zero value, resulting in a gradual decline in insulation performance.
  • the existence of low zero-value insulators may cause partial discharge, flashover or even burst, string drop, etc., posing a huge threat to the safe and stable operation of the power grid.
  • the low zero value detection methods of porcelain insulators are mainly divided into two categories.
  • One is the electric quantity detection method: it mainly includes the spark gap method, the insulation resistance method, the voltage distribution method, and the leakage current method. When using these methods to detect, manual operation is difficult, high risk, low efficiency, and easy to cause false detection and missed detection.
  • the other is the non-electricity detection method: mainly includes infrared thermal imaging method, ultraviolet imaging method, ultrasonic method and so on. Among them, the infrared thermal imaging method is the most commonly used non-contact live detection method. The principle is based on the difference in temperature rise characteristics of the degraded insulator iron cap compared with the adjacent normal insulator iron cap (iron cap temperature difference threshold method).
  • the current standard of the electric power industry DL/T 664-2016 "Infrared Diagnosis Application Specification for Live Equipment” is generally based on the positive and negative 1K temperature difference at the iron cap as the basis for the infrared detection of low and zero insulators. . Due to the influence of various environmental factors such as temperature, humidity, wind speed, air pressure, illuminance, pollution, etc., the temperature rise law and infrared characteristics of low zero value insulators often present a certain degree of dynamics and complexity. Therefore, infrared temperature measurement needs to be carried out under suitable environmental conditions, that is, to a certain extent, restricted by the detection window. For the insulator temperature measurement data obtained on site, if the low zero value is judged based on a single iron cap temperature difference index, there will be a certain probability of misdetection and missed detection.
  • the purpose of the present invention is to provide a method and system for diagnosing the infrared zero value of a porcelain insulator string, which combines the iron cap temperature difference value and the temperature difference gradient correlation coefficient for comprehensive research and judgment, and further improves the accuracy of the insulator infrared zero value diagnosis.
  • a method for diagnosing the infrared zero value of a porcelain insulator string includes the following specific steps:
  • the temperature gradient distribution curve, the temperature gradient distribution matrix of the porcelain insulator string to be diagnosed and the scatter diagram are comprehensively analyzed and judged, and the infrared zero value diagnosis of the porcelain insulator string to be diagnosed is completed.
  • the iron cap temperature of each insulator in the infrared thermal image map of the ceramic insulator string to be diagnosed Before extracting the iron cap temperature of each insulator in the infrared thermal image map of the ceramic insulator string to be diagnosed, it also includes preprocessing of background elimination, image denoising and image enhancement on the collected infrared thermal image map of the ceramic insulator string to be diagnosed step.
  • the specific method for calculating the temperature gradient value of each insulator in the porcelain insulator string to be diagnosed is as follows:
  • ⁇ is the scale factor
  • Is the temperature gradient between two adjacent insulators
  • T n+1 is the temperature of the iron cap of the n+1 insulator
  • T n is the temperature of the iron cap of the n insulator
  • the method of numbering each insulator is to start numbering from the wire side, and number each insulator in the porcelain insulator string to be diagnosed.
  • the position of the first insulator on the side of the wire is numbered 1, and the other insulators are numbered in sequence .
  • the value of the scale factor ⁇ is 1000.
  • Cov(X,Y) is the covariance of variable X and variable Y
  • Var[X] is the variance of X
  • Var[Y] is the variance of Y
  • the independent variable X and the independent variable Y are taken from the temperature gradient distribution curve; when calculating the correlation coefficient of the average curve, the independent variable X and the independent variable Y are taken from the average Take the value in the value curve.
  • the comprehensive analysis and discrimination of the temperature gradient distribution curve, the temperature gradient distribution matrix of the porcelain insulator string to be diagnosed, and the scatter diagram include the discrimination of the iron cap temperature difference threshold method and the discrimination of the porcelain insulator correlation coefficient method.
  • the determination process of the iron cap temperature difference threshold method is to obtain the absolute value of the temperature difference of each insulator in each insulator string according to the temperature gradient distribution curve corresponding to each insulator string, and screen all the insulator strings to see if any of the insulators appear The absolute value of the temperature difference is greater than the threshold value of the low-zero insulator.
  • the screening of all insulator strings is carried out according to the DL/T 664-2016 standard, and the absolute value of the temperature difference threshold is set to 1K according to the DL/T 664-2016 standard.
  • the determination process of the porcelain insulator correlation coefficient method is:
  • the temperature gradient distribution curve of the insulator string has a local sudden change, and it is judged that the sudden change position is a degraded insulator;
  • the insulator string is a normal insulator
  • the correlation coefficient is calculated. If the overall dispersion of the correlation coefficient is concentrated and the correlation coefficient is greater than 0.8, a strong correlation coefficient cluster is formed, and it is judged that the insulator string has no degraded insulators.
  • a correlation analysis system of infrared characteristics of porcelain insulator strings including:
  • the infrared thermal image spectrum acquisition module is used to collect the infrared thermal image spectrum of the porcelain insulator string to be diagnosed;
  • the infrared thermal image atlas preprocessing module is used to preprocess the collected infrared thermal image atlas of the porcelain insulator string to be diagnosed, and extract the iron cap temperature of each insulator in the infrared thermal image atlas of the porcelain insulator string to be diagnosed;
  • the temperature gradient value calculation module is used to calculate the temperature gradient value of each insulator in the porcelain insulator string to be diagnosed
  • the curve drawing module is used to draw the temperature gradient distribution curve and the average value curve
  • the correlation coefficient calculation module is used to calculate the correlation coefficient of the temperature gradient distribution curve and the average curve of each string of insulators
  • Display module used to display temperature gradient distribution curve, average curve and correlation coefficient scatter plot
  • the analysis and discrimination module is used to comprehensively analyze and discriminate the temperature gradient distribution curve, the temperature gradient distribution matrix of the porcelain insulator string to be diagnosed, and the scatter diagram, and complete the detection of the porcelain insulator string to be diagnosed.
  • the existing infrared zero measurement technology for porcelain insulators mainly relies on the iron cap temperature difference method, which is limited to local deterioration characteristics and overly relies on the naked eye, which is likely to cause missed judgments and misjudgments.
  • the invention preprocesses the infrared image, calculates the temperature difference gradient value of the iron cap, draws the entire temperature difference gradient distribution curve and the average curve, and uses the correlation analysis method to comprehensively study the local and overall temperature characteristics, which can effectively improve the infrared zero of the porcelain insulator.
  • the accuracy of the value diagnosis Compared with the prior art, the present invention has the beneficial effect of combining the iron cap temperature difference value and the temperature difference gradient correlation coefficient for comprehensive research and judgment, and further improving the accuracy of the insulator infrared zero value diagnosis.
  • Figure 1 is a flow chart of the method of the present invention
  • FIG. 2 is a system block diagram of the present invention
  • Fig. 3 is a temperature distribution curve diagram of a normal insulator string of the present invention.
  • Figure 4 is a temperature gradient distribution diagram of the normal insulator string of the present invention.
  • Figure 5 is a temperature gradient distribution diagram of the zero-value insulator string of the present invention.
  • Fig. 6 is a scatter diagram of the correlation coefficients of the insulator string to be diagnosed in the embodiment of the present invention.
  • a method for diagnosing the infrared zero value of a porcelain insulator string includes the following specific steps:
  • the temperature gradient distribution curve, the temperature gradient distribution matrix of the porcelain insulator string to be diagnosed and the scatter diagram are comprehensively analyzed and judged, and the detection of the porcelain insulator string to be diagnosed is completed.
  • the preprocessing of the collected infrared thermal image atlas of the ceramic insulator string to be diagnosed specifically includes background elimination, image denoising and image enhancement.
  • the specific method for calculating the temperature gradient value of each insulator in the porcelain insulator string to be diagnosed is as follows:
  • ⁇ is the scale factor
  • Is the temperature gradient between two adjacent insulators
  • T n+1 is the temperature of the iron cap of the n+1 insulator
  • T n is the temperature of the iron cap of the n insulator
  • the value of the scale factor ⁇ is 1000.
  • Cov(X,Y) is the covariance of variable X and variable Y
  • Var[X] is the variance of X
  • Var[Y] is the variance of Y
  • the independent variable X and the independent variable Y are taken from the temperature gradient distribution curve; when calculating the correlation coefficient of the average curve, the independent variable X and the independent variable Y are taken from the average Take the value in the value curve.
  • the comprehensive analysis and discrimination of the temperature gradient distribution curve, the temperature gradient distribution matrix of the porcelain insulator string to be diagnosed, and the scatter diagram include the discrimination of the iron cap temperature difference threshold method and the discrimination of the porcelain insulator correlation coefficient method.
  • the determination process of the iron cap temperature difference threshold method is to obtain the absolute value of the temperature difference of each insulator in each insulator string according to the temperature gradient distribution curve corresponding to each insulator string, and screen all the insulator strings according to the DL/T 664-2016 standard to see if A low zero value insulator with an absolute value of temperature difference greater than 1K for any piece of insulator appears.
  • the determination process of the porcelain insulator correlation coefficient method is:
  • the temperature value gradient distribution curve of the insulator string has a local sudden change, and the insulator corresponding to the sudden change position is judged to be a degraded insulator;
  • the insulator string is a normal insulator
  • the correlation coefficient is calculated. If the overall dispersion of the correlation coefficient is concentrated and the correlation coefficient is greater than 0.8, a strong correlation coefficient cluster is formed, and it is judged that the insulator string has no degraded insulators.
  • a ceramic insulator string infrared zero value diagnosis system includes:
  • the infrared thermal image spectrum acquisition module is used to collect the infrared thermal image spectrum of the porcelain insulator string to be diagnosed;
  • the infrared thermal image atlas preprocessing module is used to preprocess the collected infrared thermal image atlas of the porcelain insulator string to be diagnosed, and extract the iron cap temperature of each insulator in the infrared thermal image atlas of the porcelain insulator string to be diagnosed;
  • the temperature gradient value calculation module is used to calculate the temperature gradient value of each insulator in the porcelain insulator string to be diagnosed
  • the curve drawing module is used to draw the temperature gradient distribution curve and the average value curve
  • the correlation coefficient calculation module is used to calculate the correlation coefficient of the temperature gradient distribution curve and the average curve of each string of insulators
  • Display module used to display temperature gradient distribution curve, average curve and correlation coefficient scatter plot
  • the analysis and discrimination module is used to comprehensively analyze and discriminate the temperature gradient distribution curve, the temperature gradient distribution matrix of the porcelain insulator string to be diagnosed, and the scatter diagram, and complete the detection of the porcelain insulator string to be diagnosed.
  • the ceramic insulator string infrared zero value diagnosis system includes: a processor, wherein the processor is used to execute the following program modules stored in the memory: infrared thermal image atlas
  • the acquisition module is used to collect the infrared thermal image spectrum of the porcelain insulator string to be diagnosed
  • the infrared thermal image atlas preprocessing module is used to preprocess the collected infrared thermal image spectrum of the porcelain insulator string to be diagnosed, and extract the porcelain to be diagnosed
  • the temperature gradient value calculation module is used to calculate the temperature gradient value of each insulator in the porcelain insulator string to be diagnosed
  • the curve drawing module is used to draw the temperature gradient distribution curve, And the average curve
  • the correlation coefficient calculation module is used to calculate the correlation coefficients of the temperature gradient distribution curve and the average curve of each string of insulators
  • the display module is used to display the temperature gradient distribution curve, the average curve and the correlation coefficient scatter
  • An insulator string in a 500kV substation was tested using the infrared detection method of disk-shaped suspension porcelain insulators based on infrared thermal imaging.
  • Each insulator string contained 28 insulators of the same type. The following is the diagnosis process:
  • Figure 3 is the temperature distribution curve of the normal insulator string
  • Figure 4 is the temperature gradient distribution of the normal insulator string
  • insulators there are three series of insulators (the 5th series, the 21st series, and the 32nd series) with relatively small correlation coefficients, and they are judged to be degraded insulators.
  • the iron cap temperature difference value and the temperature difference gradient correlation coefficient are combined for comprehensive research and judgment, in order to further improve the accuracy of the insulator infrared zero value diagnosis.
  • the correlation coefficient is a statistic that studies the degree of linear correlation between variables, which can be used to describe the co-occurrence or co-variation of two events.
  • the value range of the correlation coefficient is [-1,1]; if the correlation coefficient is 0, it means that the two are not correlated. Correlation coefficient analysis methods are widely used in science, engineering, economics, statistics, medicine and other multidisciplinary fields.
  • this application can be provided as methods, systems, or computer program products. Therefore, this application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment.
  • the instructions provide steps for implementing the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Ceramic Engineering (AREA)
  • Investigating Or Analyzing Materials Using Thermal Means (AREA)
  • Radiation Pyrometers (AREA)
  • Insulators (AREA)

Abstract

一种瓷质绝缘子串红外零值诊断方法及系统，方法包括以下具体步骤：采集待诊断瓷质绝缘子串的红外热像图谱；取待诊断瓷质绝缘子串红外热像图谱中每片绝缘子的铁帽温度；计算待诊断瓷质绝缘子串中每片绝缘子温度梯度值，绘制温度梯度分布曲线，并形成所有待诊断瓷质绝缘子串温度梯度分布矩阵；分别计算每串绝缘子温度梯度分布曲线和平均值曲线的相关系数，并通过散点图进行展示；对形成的温度梯度分布曲线、待诊断瓷质绝缘子串温度梯度分布矩阵以及散点图进行综分析判别，完成待诊断瓷质绝缘子串的检测。将铁帽温差值与温差梯度相关系数相结合进行综合研判，进一步提高绝缘子红外零值诊断的准确率。

Description

一种瓷质绝缘子串红外零值诊断方法及系统 技术领域
本发明涉及变电站及输电线路瓷绝缘子检测技术领域，具体是一种瓷质绝缘子串红外零值诊断方法及系统。
背景技术
瓷绝缘子是一种重要的电气绝缘设备，在各电压等级输电线路、变电站中应用十分广泛。在长期运行过程中，绝缘子串受到强机电负荷、酸雨、大风、覆冰、紫外线、污秽、温湿度剧变等多种复杂因素影响，易出现低零值等劣化故障，导致其绝缘性能逐渐下降。低零值绝缘子的存在，将可能导致局放、闪络甚至炸裂、掉串等现象，对电网安全稳定运行构成巨大威胁。例如，近年来在江西、安徽、甘肃、广西等地，曾相继发生绝缘子严重劣化事件。因此，对于在役瓷绝缘子的劣化检测正引起越来越多的关注。
目前，瓷绝缘子低零值检测方法主要分为两类。一类是电量检测法：主要包括火花间隙法、绝缘电阻法、电压分布法、泄露电流法等。使用这些方法检测时，人工操作难度大，风险高，效率低且易造成误检和漏检。另一类是非电量检测法：主要包括红外热像法、紫外成像法、超声波法等。其中，红外热像法是最常用的非接触式带电检测方法。其原理是根据劣化绝缘子铁帽与相邻正常绝缘子铁帽相比呈现不同温升特征来进行判别(铁帽温差阈值法)。在现场运维检修过程中，目前普遍以电力行业标准DL/T 664-2016《带电设备红外诊断应用规范》中规定的铁帽处正负1K温差分别作为低、零值绝缘子红外检测的判别依据。由于受到温度、湿度、风速、气压、光照度、污秽等多种环境因素的影响，低零值绝缘子的温升规律和红外特征往往呈现出一定的动态性和复杂性。所以，红外测温需要在适宜的环境条件下进行，即在一定程度上受到检测窗口 的约束。对于在现场所获取的绝缘子测温数据，若依据单一的铁帽温差指标进行低零值判别，将存在一定的误检和漏检概率。
发明内容
本发明的目的在于提供一种瓷质绝缘子串红外零值诊断方法及系统，将铁帽温差值与温差梯度相关系数相结合进行综合研判，进一步提高绝缘子红外零值诊断的准确率。
本发明的技术方案：
一种瓷质绝缘子串红外零值诊断方法，包括以下具体步骤：
采集待诊断瓷质绝缘子串的红外热像图谱；
提取待诊断瓷质绝缘子串红外热像图谱中每片绝缘子的铁帽温度；
根据每片绝缘子的铁帽温度计算待诊断瓷质绝缘子串中每片绝缘子温度梯度值，绘制温度梯度分布曲线和平均值曲线，并形成所有待诊断瓷质绝缘子串温度梯度分布矩阵；
分别计算每串绝缘子温度梯度分布曲线和平均值曲线的相关系数，并通过散点图进行展示；
对上述形成的温度梯度分布曲线、待诊断瓷质绝缘子串温度梯度分布矩阵以及散点图进行综合分析判别，完成待诊断瓷质绝缘子串的红外零值诊断。
所述提取待诊断瓷质绝缘子串红外热像图谱中每片绝缘子的铁帽温度前还包括对采集的待诊断瓷质绝缘子串红外热像图谱进行背景消除、图像去噪及图像增强的预处理步骤。
所述计算待诊断瓷质绝缘子串中每片绝缘子温度梯度值具体方法为，
给待诊断瓷质绝缘子串中的每片绝缘子进行编号；
第n片绝缘子温度梯度值的计算公式如下：
Figure PCTCN2020142016-appb-000001
式中，β为比例因子，
Figure PCTCN2020142016-appb-000002
为两片相邻绝缘子之间的温度变化梯度，T n+1为第n+1片绝缘子铁帽温度，T n为第n片绝缘子铁帽温度，待诊断瓷质绝缘子串的绝缘子片数量为M，n＝1,2,3……M-1；
所述给每片绝缘子编号的方法为，从导线侧开始编号，给待诊断瓷质绝缘子串中的每片绝缘子进行编号，靠近导线侧的第一片绝缘子的位置编号为1，其它绝缘子依次编号。
所述比例因子β的取值为1000。
所述计算每串绝缘子温度梯度分布曲线和平均值曲线的相关系数的具体方法为，
Figure PCTCN2020142016-appb-000003
其中，Cov(X,Y)为变量X与变量Y的协方差，Var[X]为X的方差，Var[Y]为Y的方差，即：
Figure PCTCN2020142016-appb-000004
式中，x i为自变量X的标志值，i＝1,2…n；
Figure PCTCN2020142016-appb-000005
为自变量X的平均值；
y i为自变量Y的标志值，i＝1,2…n；
Figure PCTCN2020142016-appb-000006
为自变量Y的平均值；
在计算所述温度梯度分布曲线的相关系数时，自变量X和自变量Y从温度梯度分布曲线中取值；在计算所述平均值曲线的相关系数时，自变量X和自变量Y从平均值曲线中取值。
所述对上述形成的温度梯度分布曲线、待诊断瓷质绝缘子串温度梯度分布矩阵以及散点图进行综合分析判别包括铁帽温差阈值法判别及瓷质绝缘子相关系数法判别。
所述铁帽温差阈值法判别过程为，根据各个绝缘子串对应的所述温度梯度分布曲线得到各个绝缘子串中各片绝缘子的温差绝对值，筛查所有绝缘子串，看是否出现任一片所述绝缘子的温差绝对值大于阈值的低零值绝缘子。
所述筛查所有绝缘子串按照DL/T 664-2016标准进行，所述温差绝对值阈 值大小按照DL/T 664-2016标准设定为1K。
所述瓷质绝缘子相关系数法判别过程为，
绝缘子串温度值梯度分布曲线出现局部突变，判断该突变位置为劣化绝缘子；
绝缘子串温度值梯度分布曲线无局部突变，则判断该绝缘子串为正常绝缘子；
对于非末片绝缘子片温差绝对值介于0.3K和1K之间的绝缘子串，计算相关系数，若相关系数形成强相关系数簇和弱相关系数簇，且两簇之间最小距离不小于0.4，则判别该串存在劣化；
对于非末片绝缘子片温差绝对值小于0.3K的绝缘子串，计算相关系数，若相关系数整体分散性集中且相关系数大于0.8，形成强相关系数簇，判断该绝缘子串无劣化绝缘子。
一种瓷质绝缘子串红外特征相关性分析系统，包括：
红外热像图谱采集模块，用于采集待诊断瓷质绝缘子串的红外热像图谱；
红外热像图谱预处理模块，用于对采集的待诊断瓷质绝缘子串红外热像图谱进行预处理，提取待诊断瓷质绝缘子串红外热像图谱中每片绝缘子的铁帽温度；
温度梯度值计算模块，用于计算待诊断瓷质绝缘子串中每片绝缘子温度梯度值；
曲线绘制模块，用于绘制温度梯度分布曲线，以及平均值曲线；
相关系数计算模块，用于分别计算每串绝缘子温度梯度分布曲线和平均值曲线的相关系数；
展示模块，用于展示温度梯度分布曲线、平均值曲线以及相关系数散点图；
分析判别模块，用于对上述形成的温度梯度分布曲线、待诊断瓷质绝缘子串温度梯度分布矩阵以及散点图进行综合分析判别，完成待诊断瓷质绝缘子串 的检测。
现有瓷绝缘子红外测零技术主要依靠铁帽温差法，该方法局限于局部劣化特征，且过度依赖肉眼，易造成漏判和误判。本发明通过对红外图像预处理，计算铁帽温差梯度值，绘制整串温差梯度分布曲线及平均值曲线，利用相关性分析方法对局部和整体温度特征进行综合研判，可有效提高瓷绝缘子红外零值诊断的准确率。与现有技术相比，本发明的有益效果是：将铁帽温差值与温差梯度相关系数相结合进行综合研判，进一步提高了绝缘子红外零值诊断的准确率。
附图说明
图1是本发明的方法流程图；
图2是本发明的系统框图；
图3是本发明正常绝缘子串温度分布曲线图；
图4是本发明正常绝缘子串温度梯度分布图；
图5是本发明含零值绝缘子串温度梯度分布图；
图6是本发明实施例中待诊断绝缘子串相关系数散点图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
如图1所示，一种瓷质绝缘子串红外零值诊断方法，包括以下具体步骤：
采集待诊断瓷质绝缘子串的红外热像图谱；
对采集的待诊断瓷质绝缘子串红外热像图谱进行预处理，提取待诊断瓷质绝缘子串红外热像图谱中每片绝缘子的铁帽温度；
计算待诊断瓷质绝缘子串中每片绝缘子温度梯度值，绘制温度梯度分布曲线，并形成所有待诊断瓷质绝缘子串温度梯度分布矩阵；
分别计算每串绝缘子温度梯度分布曲线和平均值曲线的相关系数，并通过散点图进行展示；
对上述形成的温度梯度分布曲线、待诊断瓷质绝缘子串温度梯度分布矩阵以及散点图进行综分析判别，完成待诊断瓷质绝缘子串的检测。
所述对采集的待诊断瓷质绝缘子串红外热像图谱进行预处理具体包括背景消除、图像去噪及图像增强。
所述计算待诊断瓷质绝缘子串中每片绝缘子温度梯度值具体方法为，
从导线侧开始编号，给待诊断瓷质绝缘子串中的每片绝缘子进行编号，靠近导线侧的第一片绝缘子的位置编号为1，其它绝缘子依次编号；
第n片绝缘子温度梯度值的计算公式如下：
Figure PCTCN2020142016-appb-000007
式中，β为比例因子，
Figure PCTCN2020142016-appb-000008
为两片相邻绝缘子之间的温度变化梯度，T n+1为第n+1片绝缘子铁帽温度，T n为第n片绝缘子铁帽温度，待诊断瓷质绝缘子串的绝缘子片数量为M，n＝1,2,3……M-1；
所述比例因子β的取值为1000。
所述计算每串绝缘子温度梯度分布曲线和平均值曲线的相关系数的具体方法为，
Figure PCTCN2020142016-appb-000009
其中，Cov(X,Y)为变量X与变量Y的协方差，Var[X]为X的方差，Var[Y]为Y的方差，即：
Figure PCTCN2020142016-appb-000010
式中，x i为自变量X的标志值，i＝1,2…n；
Figure PCTCN2020142016-appb-000011
为自变量X的平均值；
y i为自变量Y的标志值，i＝1,2…n；
Figure PCTCN2020142016-appb-000012
为自变量Y的平均值；
在计算所述温度梯度分布曲线的相关系数时，自变量X和自变量Y从温度梯度分布曲线中取值；在计算所述平均值曲线的相关系数时，自变量X和自变量Y从平均值曲线中取值。
所述对上述形成的温度梯度分布曲线、待诊断瓷质绝缘子串温度梯度分布矩阵以及散点图进行综合分析判别包括铁帽温差阈值法判别及瓷质绝缘子相关系数法判别。
所述铁帽温差阈值法判别过程为，根据各个绝缘子串对应的温度梯度分布曲线得到各个绝缘子串中各片绝缘子的温差绝对值，按照DL/T 664-2016标准筛查所有绝缘子串，看是否出现任一片绝缘子的温差绝对值大于1K的低零值绝缘子。
所述瓷质绝缘子相关系数法判别过程为，
绝缘子串温度值梯度分布曲线出现局部突变，判断该突变位置对应的绝缘子为劣化绝缘子；
绝缘子串温度值梯度分布曲线无局部突变，则判断该绝缘子串为正常绝缘子；
对于非末片绝缘子片温差绝对值介于0.3K和1K之间的绝缘子串，计算相关系数，若相关系数形成强相关系数簇和弱相关系数簇，且两簇之间最小距离不小于0.4，则判别该串存在劣化；
对于非末片绝缘子片温差绝对值小于0.3K的绝缘子串，计算相关系数，若相关系数整体分散性集中且相关系数大于0.8，形成强相关系数簇，判断该绝缘子串无劣化绝缘子。
如图2所示，一种瓷质绝缘子串红外零值诊断系统，包括：
红外热像图谱采集模块，用于采集待诊断瓷质绝缘子串的红外热像图谱；
红外热像图谱预处理模块，用于对采集的待诊断瓷质绝缘子串红外热像图谱进行预处理，提取待诊断瓷质绝缘子串红外热像图谱中每片绝缘子的铁帽温度；
温度梯度值计算模块，用于计算待诊断瓷质绝缘子串中每片绝缘子温度梯度值；
曲线绘制模块，用于绘制温度梯度分布曲线，以及平均值曲线；
相关系数计算模块，用于分别计算每串绝缘子温度梯度分布曲线和平均值曲线的相关系数；
展示模块，用于展示温度梯度分布曲线、平均值曲线以及相关系数散点图；
分析判别模块，用于对上述形成的温度梯度分布曲线、待诊断瓷质绝缘子串温度梯度分布矩阵以及散点图进行综合分析判别，完成待诊断瓷质绝缘子串的检测。
在另一种优选的实施例中，上述实施例提供的瓷质绝缘子串红外零值诊断系统包括：处理器，其中，所述处理器用于执行存储在存储器中的以下程序模块：红外热像图谱采集模块，用于采集待诊断瓷质绝缘子串的红外热像图谱；红外热像图谱预处理模块，用于对采集的待诊断瓷质绝缘子串红外热像图谱进行预处理，提取待诊断瓷质绝缘子串红外热像图谱中每片绝缘子的铁帽温度；温度梯度值计算模块，用于计算待诊断瓷质绝缘子串中每片绝缘子温度梯度值；曲线绘制模块，用于绘制温度梯度分布曲线，以及平均值曲线；相关系数计算模块，用于分别计算每串绝缘子温度梯度分布曲线和平均值曲线的相关系数；展示模块，用于展示温度梯度分布曲线、平均值曲线以及相关系数散点图；分析判别模块，用于对上述形成的温度梯度分布曲线、待诊断瓷质绝缘子串温度梯度分布矩阵以及散点图进行综合分析判别，完成待诊断瓷质绝缘子串的检测。
实施例：
某500kV变电站绝缘子串应用基于红外热像的盘形悬式瓷绝缘子红外检测 方法开展检测，每串绝缘子含28片同型号绝缘子。以下为诊断过程：
采集待诊断绝缘子串的红外热像图谱；如图3为正常绝缘子串温度分布曲线图，如图4为正常绝缘子串温度梯度分布图；
按照DL/T 664-2016标准筛查所有绝缘子串，看是否出现温差绝对值大于1K的低零值绝缘子；对于采集的绝缘子串红外图谱，可先通过背景消除、图像去噪及增强等算法进行预处理。提取待诊断绝缘子串红外热像图谱中每片绝缘子的铁帽温度；
计算串中第n片绝缘子温度梯度值，形成所有待测绝缘子串温度梯度分布矩阵，并绘制温度梯度分布曲线图(如图5)；
分别计算每串绝缘子温度梯度分布曲线和平均值曲线的相关系数，并通过散点图进行展示(如图6)；
图5中，有3串绝缘子(第5串、第21串、第32串)温度梯度曲线出现了较大突变，判断为劣化绝缘子；
图6中，有3串绝缘子(第5串、第21串、第32串)相关系数较小，判断为劣化绝缘子。
本文将铁帽温差值与温差梯度相关系数相结合进行综合研判，为进一步提高绝缘子红外零值诊断的准确率，
相关系数是研究变量之间线性相关程度的统计量，可用于描述两个事件的相随共现或者相随共变的情况。相关系数越大，表示变量之间相关联程度越高；相关系数越小，则表示变量之间的相关联程度越低。相关系数取值范围为[-1,1]；若相关系数为0，表示两者不相关。相关系数分析方法广泛应用于理学、工程学、经济学、统计学、医学等多学科领域。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包 含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
此外，应当理解，虽然本说明书按照实施方式加以描述，但并非每个实施方式仅包含一个独立的技术方案，说明书的这种叙述方式仅仅是为清楚起见，本领域技术人员应当将说明书作为一个整体，各实施例中的技术方案也可以经适当组合，形成本领域技术人员可以理解的其他实施方式。

Claims (11)

  1. 一种瓷质绝缘子串红外零值诊断方法，其特征在于，包括以下具体步骤：
    采集待诊断瓷质绝缘子串的红外热像图谱；
    提取待诊断瓷质绝缘子串红外热像图谱中每片绝缘子的铁帽温度；
    根据每片绝缘子的铁帽温度计算待诊断瓷质绝缘子串中每片绝缘子温度梯度值，绘制温度梯度分布曲线和平均值曲线，并形成所有待诊断瓷质绝缘子串温度梯度分布矩阵；
    分别计算每串绝缘子温度梯度分布曲线和平均值曲线的相关系数，并通过散点图进行展示；
    对上述得到的温度梯度分布曲线、待诊断瓷质绝缘子串温度梯度分布矩阵以及散点图进行综合分析判别，完成待诊断瓷质绝缘子串的红外零值诊断。
  2. 根据权利要求1所述的一种瓷质绝缘子串红外零值诊断方法，其特征在于，所述提取待诊断瓷质绝缘子串红外热像图谱中每片绝缘子的铁帽温度前还包括对采集的待诊断瓷质绝缘子串红外热像图谱进行背景消除、图像去噪及图像增强的预处理步骤。
  3. 根据权利要求1所述的一种瓷质绝缘子串红外零值诊断方法，其特征在于，所述计算待诊断瓷质绝缘子串中每片绝缘子温度梯度值具体方法为，
    给待诊断瓷质绝缘子串中的每片绝缘子进行编号；第n片绝缘子温度梯度值的计算公式如下：
    Figure PCTCN2020142016-appb-100001
    式中，β为比例因子，
    Figure PCTCN2020142016-appb-100002
    为两片相邻绝缘子之间的温度变化梯度，T n+1为第n+1片绝缘子铁帽温度，T n为第n片绝缘子铁帽温度，待诊断瓷质绝缘子串的绝缘子片数量为M，n＝1,2,3……M-1。
  4. 根据权利要求3所述的一种瓷质绝缘子串红外零值诊断方法，其特征在 于，给每片所述绝缘子编号的方法为，从导线侧开始编号，给待诊断瓷质绝缘子串中的每片绝缘子进行编号，靠近导线侧的第一片绝缘子的位置编号为1，其它绝缘子依次编号。
  5. 根据权利要求3所述的一种瓷质绝缘子串红外零值诊断方法，其特征在于，所述比例因子β的取值为1000。
  6. 根据权利要求1所述的一种瓷质绝缘子串红外零值诊断方法，其特征在于，所述计算每串绝缘子温度梯度分布曲线和平均值曲线的相关系数的具体方法为，
    Figure PCTCN2020142016-appb-100003
    其中，Cov(X,Y)为变量X与变量Y的协方差，Var[X]为X的方差，Var[Y]为Y的方差，即：
    Figure PCTCN2020142016-appb-100004
    式中，x i为自变量X的标志值，i＝1,2…n；
    Figure PCTCN2020142016-appb-100005
    为自变量X的平均值；
    y i为自变量Y的标志值，i＝1,2…n；
    Figure PCTCN2020142016-appb-100006
    为自变量Y的平均值；
    在计算所述温度梯度分布曲线的相关系数时，自变量X和自变量Y从温度梯度分布曲线中取值；在计算所述平均值曲线的相关系数时，自变量X和自变量Y从平均值曲线中取值。
  7. 根据权利要求1所述的一种瓷质绝缘子串红外零值诊断方法，其特征在于，所述综合分析判别，包括：铁帽温差阈值法判别及瓷质绝缘子相关系数法判别。
  8. 根据权利要求7所述的一种瓷质绝缘子串红外零值诊断方法，其特征在于，所述铁帽温差阈值法判别过程为：根据各个绝缘子串对应的所述温度梯度分布曲线得到各个绝缘子串中各片绝缘子的温差绝对值，筛查所有绝缘子串，看是否出现任一片所述绝缘子的温差绝对值大于阈值的低零值绝缘子。
  9. 根据权利要求8所述的一种瓷质绝缘子串红外零值诊断方法，其特征在于，所述筛查所有绝缘子串按照DL/T 664-2016标准进行，所述温差绝对值阈值大小按照DL/T 664-2016标准设定为1K。
  10. 根据权利要求7所述的一种瓷质绝缘子串红外零值诊断方法，其特征在于，所述瓷质绝缘子相关系数法判别过程为，
    绝缘子串温度值梯度分布曲线出现局部突变，判断该突变位置对应的绝缘子为劣化绝缘子；
    绝缘子串温度值梯度分布曲线无局部突变，则判断该绝缘子串为正常绝缘子；
    对于非末片绝缘子片温差绝对值介于0.3K和1K之间的绝缘子串，计算相关系数，若相关系数形成强相关系数簇和弱相关系数簇，且两簇之间最小距离不小于0.4，则判别该绝缘子串存在劣化；
    对于非末片绝缘子片温差绝对值小于0.3K的绝缘子串，计算相关系数，若相关系数整体分散性集中且相关系数大于0.8，形成强相关系数簇，判断该绝缘子串无劣化绝缘子。
  11. 一种瓷质绝缘子串红外零值诊断系统，其特征在于，包括：
    红外热像图谱采集模块，用于采集待诊断瓷质绝缘子串的红外热像图谱；
    红外热像图谱预处理模块，用于对采集的待诊断瓷质绝缘子串红外热像图谱进行预处理，提取待诊断瓷质绝缘子串红外热像图谱中每片绝缘子的铁帽温度；
    温度梯度值计算模块，用于计算待诊断瓷质绝缘子串中每片绝缘子温度梯度值；
    曲线绘制模块，用于绘制温度梯度分布曲线，以及平均值曲线；
    相关系数计算模块，用于分别计算每串绝缘子温度梯度分布曲线和平均值曲线的相关系数；
    展示模块，用于展示温度梯度分布曲线、平均值曲线以及相关系数散点图；
    分析判别模块，用于对上述得到的温度梯度分布曲线、待诊断瓷质绝缘子串温度梯度分布矩阵以及散点图进行综合分析判别，完成待诊断瓷质绝缘子串的检测。
PCT/CN2020/142016 2020-03-26 2020-12-31 一种瓷质绝缘子串红外零值诊断方法及系统 WO2021190056A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/276,480 US11397208B2 (en) 2020-03-26 2020-12-31 Infrared zero value diagnosis method and system for porcelain insulator string

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010225404.6A CN111381134B (zh) 2020-03-26 2020-03-26 一种瓷质绝缘子串红外零值诊断方法及系统
CN202010225404.6 2020-03-26

Publications (1)

Publication Number Publication Date
WO2021190056A1 true WO2021190056A1 (zh) 2021-09-30

Family

ID=71215642

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/142016 WO2021190056A1 (zh) 2020-03-26 2020-12-31 一种瓷质绝缘子串红外零值诊断方法及系统

Country Status (3)

Country Link
US (1) US11397208B2 (zh)
CN (1) CN111381134B (zh)
WO (1) WO2021190056A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115063581A (zh) * 2022-05-31 2022-09-16 中国科学院沈阳自动化研究所 一种变电站环境下绝缘子串局部过曝图像的判断方法
CN115825667A (zh) * 2022-12-06 2023-03-21 广州科易光电技术有限公司 绝缘子串检测方法、电子设备及存储介质
CN116596920A (zh) * 2023-07-12 2023-08-15 国网江西省电力有限公司电力科学研究院 一种长串瓷绝缘子无人机实时测零方法及系统

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111381134B (zh) * 2020-03-26 2021-07-16 国网湖北省电力有限公司电力科学研究院 一种瓷质绝缘子串红外零值诊断方法及系统
CN112699897B (zh) * 2020-12-04 2024-04-05 国网湖北省电力有限公司电力科学研究院 一种特高压瓷质绝缘子串铁帽温度曲线拼接方法及系统
CN113884500A (zh) * 2021-10-12 2022-01-04 国家电网有限公司 基于紫外成像的瓷绝缘子缺陷检测方法
CN114241727A (zh) * 2021-11-26 2022-03-25 国网新疆电力有限公司巴州供电公司 变电设备智能诊断预警系统、方法及装置
CN114724042B (zh) * 2022-06-09 2022-09-02 国网江西省电力有限公司电力科学研究院 一种输电线路中零值绝缘子自动检测方法
CN115421006A (zh) * 2022-08-17 2022-12-02 广州科易光电技术有限公司 绝缘子串缺陷检测方法、设备终端及存储介质

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006012799A (ja) * 2004-05-27 2006-01-12 Central Res Inst Of Electric Power Ind がいしにおいて生じる漏れ電流の推定装置および方法
CN101487866A (zh) * 2008-11-06 2009-07-22 姚建刚 基于红外热像交流输电线路瓷质零值绝缘子在线检测方法
CN103792238A (zh) * 2014-02-07 2014-05-14 国家电网公司 一种瓷质悬式绝缘子缺陷诊断方法
CN104267063A (zh) * 2014-10-10 2015-01-07 国家电网公司 一种基于红外热像的低值绝缘子检测方法
CN106920240A (zh) * 2017-03-09 2017-07-04 国家电网公司 一种基于红外图像的绝缘子识别和故障诊断方法
CN107247059A (zh) * 2017-06-09 2017-10-13 华北电力大学（保定） 基于空气热纹影分布的绝缘子故障检测装置及其方法
CN107767374A (zh) * 2017-10-24 2018-03-06 天津大学 一种gis盆式绝缘子内部导体局部过热智能诊断方法
CN108181556A (zh) * 2017-12-18 2018-06-19 国网浙江省电力有限公司检修分公司 基于铁帽温差时间序列分析的瓷质绝缘子零值检测方法
CN111381134A (zh) * 2020-03-26 2020-07-07 国网湖北省电力有限公司电力科学研究院 一种瓷质绝缘子串红外零值诊断方法及系统

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH07260871A (ja) * 1994-03-25 1995-10-13 Tokyo Electric Power Co Inc:The 冠雪碍子連の絶縁耐力監視方法及びその装置
DE4419750C1 (de) * 1994-06-06 1995-06-22 Siemens Ag Prooftest für keramische Bauteile
US6542849B2 (en) * 2001-01-19 2003-04-01 The University Of Chicago Method for determining defect depth using thermal imaging
US8552382B2 (en) * 2008-08-14 2013-10-08 The Boeing Company Thermal effect measurement with mid-infrared spectroscopy
JP6448488B2 (ja) * 2014-08-28 2019-01-09 日本碍子株式会社 耐熱衝撃性試験方法、及び耐熱衝撃性試験装置
CN104361216B (zh) * 2014-10-29 2017-06-23 国网河南省电力公司电力科学研究院 一种基于变权层次分析法的绝缘子污闪预警方法
US9645012B2 (en) * 2015-08-17 2017-05-09 The Boeing Company Rapid automated infrared thermography for inspecting large composite structures
EP3255421B1 (en) * 2016-06-10 2020-01-01 coatmaster AG Device for the contactless and non-destructive testing of a surface by measuring its infrared radiation
CN109387753A (zh) * 2018-10-08 2019-02-26 国网福建省电力有限公司 一种多元化的复合绝缘子劣化等级划分方法
CN110096737B (zh) * 2019-03-21 2023-04-07 国网内蒙古东部电力有限公司电力科学研究院 绝缘子寿命预测方法、装置、计算机装置及存储介质

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006012799A (ja) * 2004-05-27 2006-01-12 Central Res Inst Of Electric Power Ind がいしにおいて生じる漏れ電流の推定装置および方法
CN101487866A (zh) * 2008-11-06 2009-07-22 姚建刚 基于红外热像交流输电线路瓷质零值绝缘子在线检测方法
CN103792238A (zh) * 2014-02-07 2014-05-14 国家电网公司 一种瓷质悬式绝缘子缺陷诊断方法
CN104267063A (zh) * 2014-10-10 2015-01-07 国家电网公司 一种基于红外热像的低值绝缘子检测方法
CN106920240A (zh) * 2017-03-09 2017-07-04 国家电网公司 一种基于红外图像的绝缘子识别和故障诊断方法
CN107247059A (zh) * 2017-06-09 2017-10-13 华北电力大学（保定） 基于空气热纹影分布的绝缘子故障检测装置及其方法
CN107767374A (zh) * 2017-10-24 2018-03-06 天津大学 一种gis盆式绝缘子内部导体局部过热智能诊断方法
CN108181556A (zh) * 2017-12-18 2018-06-19 国网浙江省电力有限公司检修分公司 基于铁帽温差时间序列分析的瓷质绝缘子零值检测方法
CN111381134A (zh) * 2020-03-26 2020-07-07 国网湖北省电力有限公司电力科学研究院 一种瓷质绝缘子串红外零值诊断方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ZHOU YOUWEI, YAO JIANGANG, WANG XIN, LI KAIDI, LIU ZHENGTING, LU YIPENG YIN, JUNGANG: "Infrared Image Detection for Faulty Insulators Based on Time Series Model", INSULATORS AND SURGE ARRESTERS, no. 1, 25 February 2020 (2020-02-25), pages 149 - 155, XP055852379, ISSN: 1003-8337, DOI: 10.16188/j.isa.1003-8337.2020.01.025 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115063581A (zh) * 2022-05-31 2022-09-16 中国科学院沈阳自动化研究所 一种变电站环境下绝缘子串局部过曝图像的判断方法
CN115825667A (zh) * 2022-12-06 2023-03-21 广州科易光电技术有限公司 绝缘子串检测方法、电子设备及存储介质
CN115825667B (zh) * 2022-12-06 2023-10-13 广州科易光电技术有限公司 绝缘子串检测方法、电子设备及存储介质
CN116596920A (zh) * 2023-07-12 2023-08-15 国网江西省电力有限公司电力科学研究院 一种长串瓷绝缘子无人机实时测零方法及系统
CN116596920B (zh) * 2023-07-12 2023-11-07 国网江西省电力有限公司电力科学研究院 一种长串瓷绝缘子无人机实时测零方法及系统

Also Published As

Publication number Publication date
CN111381134B (zh) 2021-07-16
US11397208B2 (en) 2022-07-26
CN111381134A (zh) 2020-07-07
US20220113343A1 (en) 2022-04-14

Similar Documents

Publication Publication Date Title
WO2021190056A1 (zh) 一种瓷质绝缘子串红外零值诊断方法及系统
CN105004972B (zh) 基于日盲紫外成像图像特征的瓷绝缘子绝缘状态评估方法
CN109660206B (zh) 一种基于Wasserstein GAN的光伏阵列故障诊断方法
CN114283117A (zh) 一种基于改进YOLOv3卷积神经网络的绝缘子缺陷检测方法
CN112200178B (zh) 基于人工智能的变电站绝缘子红外图像检测方法
CN111798412A (zh) 一种基于红外图像的变电设备缺陷智能诊断方法及系统
CN106326808A (zh) 基于无人机图像的检测输电线路杆塔鸟窝的方法
CN113592822A (zh) 一种电力巡检图像的绝缘子缺陷定位方法
CN113449769A (zh) 输电线路覆冰识别模型训练方法、识别方法及存储介质
CN105528790A (zh) 一种输电线路小型部件识别方法
CN115236451A (zh) 一种配电网架空线路故障监测装置及方法
Zhang et al. Intelligent detection technology of infrared image of substation equipment based on deep learning algorithm
CN114034997A (zh) 一种基于多参量的绝缘子劣化程度预测方法及系统
CN108573233B (zh) 一种基于图像处理技术的电网陶瓷绝缘子识别方法
CN115902541A (zh) 一种输电线路绝缘子放电及缺陷的诊断方法及系统
CN116385950A (zh) 一种小样本条件下电力线路隐患目标检测方法
CN116089843A (zh) 一种基于数据聚类的新能源结算数据异常检测与预警方法
CN112884720B (zh) 一种配电线路污闪绝缘子检测方法及系统
Hu et al. A detecting algorithm for occlusion on the surface of photovoltaic modules based on improved YOLOv5
Jin et al. Pollution state detection of insulators based on multisource imaging and information fusion
CN110826601B (zh) 基于改进的支持向量机算法的林火预测方法
Yang et al. Insulator UV image fault detection based on deep learning
CN117475361A (zh) 基于miniImageNet数据集辅助训练小样本学习输电线路缺陷识别方法
Qi et al. Efficient real-time detection of electrical equipment images using a lightweight detector model
CN109272209A (zh) 基于多维数据的输电线路通道隐患分析方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20926547

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20926547

Country of ref document: EP

Kind code of ref document: A1