CN-121995133-A - Operation state monitoring method of lightning arrester for high-voltage cable terminal tower of power grid

CN121995133ACN 121995133 ACN121995133 ACN 121995133ACN-121995133-A

Abstract

The invention relates to an operation state monitoring method of a lightning arrester for a high-voltage cable terminal tower of a power grid, which comprises the steps of firstly collecting operation data of the lightning arrester in real time, preprocessing the collected data, carrying out time-space synchronous calibration, correcting the influence of space distribution interference and electromagnetic interference on the data based on a cable coupling coefficient and an inter-phase coupling coefficient, thereby establishing a correlation analysis model, then generating a personalized early warning threshold value by utilizing a dynamic threshold algorithm based on historical operation data and operation age of equipment, carrying out abnormal judgment on the preprocessed data and the time-space synchronous calibrated data through the early warning threshold value, extracting abnormal constant values, carrying out coupling analysis on a lightning arrester leakage current signal and a cable circulation signal in the extracted data based on the correlation analysis model, and outputting and uploading a monitoring report.

Inventors

XU HONGXUN
LIU HOULIN
LIU XUN
WANG LEXING
LIU MINJIE
SONG XIAOBO
SHI WENLONG
WANG LIJUN
ZHU LEI

Assignees

国网河南省电力公司商丘供电公司

Dates

Publication Date: 20260508
Application Date: 20251208

Claims (5)

1. The method for monitoring the operation state of the lightning arrester for the high-voltage cable terminal tower of the power grid is characterized by comprising the following steps of: The method comprises the steps of 1, acquiring operation data of a lightning arrester in real time through a data acquisition component, namely acquiring full current and resistive current signals of the lightning arrester by utilizing a leakage current detection unit, and acquiring ring network current signals of a three-phase grounding wire of a cable terminal by utilizing a sheath grounding ring current sensor; Step 2, preprocessing and time-space synchronous calibration are carried out on the data acquired in the step 1, the influence of space distribution interference and electromagnetic interference on the data is corrected based on the cable coupling coefficient and the inter-phase coupling coefficient, and then a correlation analysis model between the leakage current of the lightning arrester and the cable circulation is established; Step 3, based on the historical operation data and the operation age of the equipment, taking the natural aging rule of the material into consideration, correlating real-time load conditions such as load current, environment temperature and humidity and the like, generating a personalized early warning threshold value by using a dynamic threshold value algorithm, then carrying out abnormal judgment on the preprocessed and space-time synchronous calibrated data through the early warning threshold value, triggering grading early warning when the data exceeds the dynamic threshold value range, and extracting and storing and backing up the partial data; Step 4, coupling analysis is carried out on the lightning arrester leakage current signal and the cable circulation signal in the extracted data based on the association analysis model, then association fault risks and fault positions of circulation abnormality caused by poor grounding, stress overload of the lightning arrester and the like are identified through a preset fault feature mapping library, and finally, a monitoring report is output according to the identification analysis result; And 5, classifying and marking the monitoring report according to the early warning grade, and uploading the monitoring report to an operation and maintenance management platform in a wireless communication mode after marking is completed, so that visual display, trend analysis and early warning pushing of the state of the lightning arrester are realized.
2. The method for monitoring the operating state of a lightning arrester for a high-voltage cable terminal tower of a power grid as set forth in claim 1, wherein the leakage current detection unit in the step 1 comprises a rectification module, a low-pass filter circuit and a current amplifying circuit, and the sheath grounding loop sensor capable of outputting a full current signal and a resistive current signal in a separable manner adopts an open-close structure to adapt to the field installation requirement of the high-voltage cable terminal.
3. The method for monitoring the operation state of a lightning arrester for a high-voltage cable terminal tower of a power grid according to claim 1, wherein the fault feature mapping library in the step 4 is capable of realizing accurate positioning of related faults by extracting amplitude deviation, phase difference and change trend features of leakage current of the lightning arrester and cable circulation.
4. The method for monitoring the operation state of the lightning arrester for the high-voltage cable terminal tower of the power grid is characterized in that the data preprocessing operation in the step 2 is data cleaning, filtering, normalization and fusion processing, wherein abnormal values and empty values are removed through data cleaning, the influence of electromagnetic interference and impulse noise on data is removed through data filtering, incoordination caused by different dimensions and sizes among data features is eliminated through data normalization, and multi-source data fusion is realized through a feature fusion algorithm based on an attention mechanism.
5. The method for monitoring the operation state of the lightning arrester for the high-voltage cable terminal tower of the power grid according to claim 1, wherein the dynamic threshold algorithm in the step 3 is used for timely adjusting an early warning threshold interval by fitting a mapping relation between the operation age, the load intensity and normal operation parameters of equipment through a deep learning model.

Description

Operation state monitoring method of lightning arrester for high-voltage cable terminal tower of power grid Technical Field The invention belongs to the technical field of online monitoring of power transmission and transformation of a power grid, and particularly relates to a method for monitoring the running state of a lightning arrester for a high-voltage cable terminal tower of the power grid. Background The high-voltage cable terminal tower is a key facility for converting an overhead line into a cable laying, and mainly comprises a cable terminal, a lightning arrester and a cable joint box, wherein the cable terminal is used for connecting a cable with the overhead line to realize connection of power transmission, the lightning arrester bears the heavy duty of protecting electric equipment from being damaged by high transient overvoltage, however, the existing lightning arrester monitoring method has the defects that 1, the lightning arrester is detected to rely on power failure for maintenance, has larger limitation, cannot be accurately maintained according to the actual state of the equipment, easily causes over maintenance or insufficient maintenance, increases operation and maintenance cost and is difficult to prevent sudden faults, 2, a fixed early warning threshold is adopted, the equipment characteristics under different operation years and under load conditions are difficult to adapt, the false alarm rate is higher, and 3, the fault pre-judging capability is insufficient due to the fact that a unified platform is lack of coupling analysis of parameters such as leakage current of the lightning arrester, circulation of the cable, the temperature of the joint box and the like. Disclosure of Invention The invention aims to overcome the defects of the prior art, and provides a method for monitoring the operation state of a lightning arrester for a high-voltage cable terminal tower of a power grid, which has the advantages of accurate early warning and capability of realizing multi-dimensional monitoring. The invention discloses a method for monitoring the operation state of a lightning arrester for a high-voltage cable terminal tower of a power grid, which comprises the following steps of: The method comprises the steps of 1, acquiring operation data of a lightning arrester in real time through a data acquisition component, namely acquiring full current and resistive current signals of the lightning arrester by utilizing a leakage current detection unit, and acquiring ring network current signals of a three-phase grounding wire of a cable terminal by utilizing a sheath grounding ring current sensor; Step 2, preprocessing and time-space synchronous calibration are carried out on the data acquired in the step 1, the influence of space distribution interference and electromagnetic interference on the data is corrected based on the cable coupling coefficient and the inter-phase coupling coefficient, and then a correlation analysis model between the leakage current of the lightning arrester and the cable circulation is established; Step 3, based on the historical operation data and the operation age of the equipment, taking the natural aging rule of the material into consideration, correlating real-time load conditions such as load current, environment temperature and humidity and the like, generating a personalized early warning threshold value by using a dynamic threshold value algorithm, then carrying out abnormal judgment on the preprocessed and space-time synchronous calibrated data through the early warning threshold value, triggering grading early warning when the data exceeds the dynamic threshold value range, and extracting and storing and backing up the partial data; Step 4, coupling analysis is carried out on the lightning arrester leakage current signal and the cable circulation signal in the extracted data based on the association analysis model, then association fault risks and fault positions of circulation abnormality caused by poor grounding, stress overload of the lightning arrester and the like are identified through a preset fault feature mapping library, and finally, a monitoring report is output according to the identification analysis result; And 5, classifying and marking the monitoring report according to the early warning grade, and uploading the monitoring report to an operation and maintenance management platform in a wireless communication mode after marking is completed, so that visual display, trend analysis and early warning pushing of the state of the lightning arrester are realized. Furthermore, the leakage current detection unit in the step 1 comprises a rectification module, a low-pass filter circuit and a current amplifying circuit, and the protective layer grounding loop sensor capable of outputting the full current signal and the resistive current signal in a separable way adopts an open-close structure to adapt to the field installation requirement of the high-vo