CN-121978577-A - Pulse insulator leakage fault diagnosis system and method

CN121978577ACN 121978577 ACN121978577 ACN 121978577ACN-121978577-A

Abstract

The application relates to the technical field of leakage detection, in particular to a pulse insulator leakage fault diagnosis system and method, which specifically comprise the steps of collecting insulator leakage current data and humidity data of an environment where an insulator is positioned, and constructing an environmental humidity influence coefficient according to humidity change and the characteristics of the insulator current data change caused by precipitation; the method comprises the steps of constructing a leakage characteristic coefficient according to the leakage current change characteristic generated when the insulator really has defects, detecting and maintaining the marked insulator based on the environmental humidity influence coefficient and the suspected defect insulator mark of the leakage characteristic coefficient, solving the problem that the environmental influence is similar to the leakage current of the leakage fault caused by the defects of the insulator in the traditional insulator leakage fault diagnosis process, so that the actual leakage condition of the insulator cannot be judged, and improving the insulator fault diagnosis accuracy.

Inventors

SHI GUOSONG
LIU YU
WANG HUIXIAN
MA KAIQIANG
YOU HUAJING

Assignees

国网河南省电力公司南阳供电公司
山西西电博宇电力科技有限公司

Dates

Publication Date: 20260505
Application Date: 20260126

Claims (10)

1. The pulse insulator leakage fault diagnosis method is characterized by comprising the following steps of: Collecting current data of insulators at all moments and humidity data of the environment; constructing an environmental humidity influence coefficient of the insulators in each period based on the fluctuation intensity, the humidity change trend and the humidity maximum value of the current data of the insulators in each period; constructing the leakage characteristic coefficient of the insulator in each period based on the current fluctuation speed, the current distribution range and the current fluctuation duration in each period; Constructing a defect induced leakage coefficient of the insulator at each period based on the environmental humidity influence coefficient and the leakage characteristic coefficient; and marking suspected defective insulators based on the defect induced leakage coefficients, and detecting and maintaining marked insulators.
2. The method for diagnosing a leakage fault of a pulse insulator as claimed in claim 1, wherein the process of obtaining the environmental humidity influence coefficient is as follows: And fitting all current data in each time period through a curve fitting algorithm, obtaining the distribution confusion degree of slopes at all sampling moments in a fitting curve, calculating the slope of a fitting straight line of all humidity data time sequence in each time period, and determining the environmental humidity influence coefficient of each time period based on the confusion degree, the slope of the fitting straight line and the maximum value of the humidity data in each time period.
3. The method for diagnosing a leakage fault of a pulse insulator as claimed in claim 2, wherein the degree of disorder of the distribution of the slopes is a standard deviation of the slopes at all sampling moments in the fitted curve.
4. The method for diagnosing a leakage fault of a pulse insulator as claimed in claim 2, wherein the environmental humidity influence coefficient is a forward fusion result of the degree of confusion, the slope of the fitted straight line, and the maximum value of humidity data for each period.
5. The method for diagnosing a leakage fault of a pulse insulator as claimed in claim 1, wherein the obtaining process of the leakage characteristic coefficient is as follows: Clustering all current data in each time period through a clustering algorithm to obtain the total number of elements in clusters with the largest element mean value in the clusters; acquiring the maximum inflection point in the current data of each period, and calculating the gradient speed value of each period by combining the current data in the cluster with the minimum element mean value in the cluster; And constructing a leakage characteristic coefficient under each period based on the gradient speed value, the current data maximum value difference and the total number of elements in the cluster in each period, wherein the leakage characteristic coefficient respectively forms a positive correlation with the gradient speed value, the maximum value difference and the total number of elements in the cluster.
6. The method for diagnosing a leakage fault of a pulse insulator as claimed in claim 5, wherein the step-up speed value is obtained by: and in the cluster with the minimum element mean value in the cluster, acquiring a current data point with the minimum time interval with the maximum inflection point, and recording the ratio of the current difference between the maximum inflection point and the current data point to the time difference as a gradient speed value.
7. The method for diagnosing a leakage fault of a pulse insulator as claimed in claim 5, wherein the current data maximum value difference is a ratio of a maximum value to a minimum value in the current data of each period.
8. The method for diagnosing a leakage fault of a pulse insulator as claimed in claim 1, wherein the defect induced leakage coefficient is a normalized value of a ratio of the leakage characteristic coefficient to the ambient humidity influence coefficient.
9. The method for diagnosing a leakage fault of a pulse insulator according to claim 1, wherein the method for marking the suspected defective insulator comprises the following steps: And if the defect induced leakage coefficient of the insulator at each moment is greater than or equal to a preset segmentation threshold value, marking the insulator as a suspected defect insulator.
10. A pulsed insulator leakage fault diagnosis system comprising a memory, a processor and a computer program stored in said memory and running on said processor, characterized in that said processor implements the steps of the method according to any one of claims 1-9 when said computer program is executed.

Description

Pulse insulator leakage fault diagnosis system and method Technical Field The application relates to the technical field of leakage detection, in particular to a pulse insulator leakage fault diagnosis system and method. Background With the development of sensor technology and communication technology, a great deal of theoretical research and monitoring equipment has been developed in the aspect of state monitoring of insulators. Because the state of the insulator can be reflected by the leakage current, the leakage current detection system accurately extracts useful characteristic signals by detecting the leakage current sensor connected with the insulator string in series, and transmits the characteristic signals of all insulators in an area to the insulator monitoring center and the control center through the communication technology adopted in the Internet of things, and the actual state of the insulator is obtained by processing the technologies of big data, data anomaly detection and the like, and corresponding control and decision are performed. In the actual measurement process, the existing insulator leakage fault diagnosis method mainly comprises the steps of measuring leakage current data of an insulator, judging and analyzing the current data by adopting an anomaly detection algorithm, so as to judge whether the insulator generates leakage current due to defects, and if the leakage condition caused by the defects of the insulator occurs, rapidly replacing or repairing the insulator with the defects by related operators. However, when the humidity in the environment where the insulator is located is higher, water vapor in the air condenses or adsorbs on the surface of the insulator to form a continuous or discontinuous water film, if the surface of the insulator has pollution (salt, dust and industrial pollutants), the water film can dissolve the electrolytes to form a conductive electrolyte solution, and finally a continuous conductive path is formed, so that the condition of leakage current on the surface of the insulator can be caused. The electric leakage condition of the insulator is highly influenced by environmental change, after the electric leakage condition occurs, the electric leakage is stopped after the surface of the insulator is gradually dried along with the reduction of the environmental humidity, so that compared with the condition that the electric leakage is caused by the defect of the insulator, the electric leakage condition caused by the environmental influence has lighter influence on the power equipment. However, when the leakage condition occurs, whether the leakage condition is caused by environmental influence or defects of the insulator itself, the measurement result when the leakage current of the insulator is measured is similar, the insulator is difficult to distinguish by adopting the traditional technical means, and finally, errors are generated when the actual leakage condition of the insulator is judged. Disclosure of Invention In order to solve the technical problems, the application aims to provide a pulse insulator leakage fault diagnosis system and a pulse insulator leakage fault diagnosis method, and the adopted technical scheme is as follows: in a first aspect, an embodiment of the present application provides a method for diagnosing a leakage fault of a pulse insulator, including the steps of: Collecting current data of insulators at all moments and humidity data of the environment; constructing an environmental humidity influence coefficient of the insulators in each period based on the fluctuation intensity, the humidity change trend and the humidity maximum value of the current data of the insulators in each period; constructing the leakage characteristic coefficient of the insulator in each period based on the current fluctuation speed, the current distribution range and the current fluctuation duration in each period; Constructing a defect induced leakage coefficient of the insulator at each period based on the environmental humidity influence coefficient and the leakage characteristic coefficient; and marking suspected defective insulators based on the defect induced leakage coefficients, and detecting and maintaining marked insulators. In one embodiment, the process of obtaining the environmental humidity influence coefficient is: And fitting all current data in each time period through a curve fitting algorithm, obtaining the distribution confusion degree of slopes at all sampling moments in a fitting curve, calculating the slope of a fitting straight line of all humidity data time sequence in each time period, and determining the environmental humidity influence coefficient of each time period based on the confusion degree, the slope of the fitting straight line and the maximum value of the humidity data in each time period. In one embodiment, the degree of confusion of the slope distribution is the standard deviation of the slope at all samplin