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

Abstract

The invention relates to a method for monitoring the running state of a lightning arrester for a power grid high-voltage cable terminal tower, which comprises the following steps of: firstly, collecting the running data of the lightning arrester in real time, preprocessing the collected data and carrying out time-space synchronous calibration on the collected data, and then calculating the running state of the lightning arrester based on a cable coupling coefficient and an interphase coupling coefficient; the method comprises the following steps of: firstly, correcting the influence of spatial distribution interference and electromagnetic interference on data according to the pre-processed data, so as to establish a correlation analysis model, then, generating a personalized early warning threshold value by utilizing a dynamic threshold value algorithm based on historical operation data and operation age limit of equipment, and carrying out abnormity judgment on the data subjected to pre-processing and time-space synchronization calibration through the early warning threshold value. And finally, based on a correlation analysis model, carrying out coupling analysis on a lightning arrester leakage current signal and a cable circulation current signal in the extracted data, and outputting and uploading a monitoring report. The method has the advantages of being accurate in early warning and capable of achieving multi-dimensional monitoring.

Description

Technical Field

[0001] This invention belongs to the field of online monitoring technology for power grid transmission and transformation, and specifically relates to a method for monitoring the operating status of surge arresters used in high-voltage cable terminal towers of power grids. Background Technology

[0002] High-voltage cable terminal towers are key facilities for converting overhead lines into cable laying, mainly housing cable terminals, surge arresters, and cable junction boxes. Cable terminals connect cables to overhead lines, enabling power transmission. Surge arresters are crucial for protecting electrical equipment from high transient overvoltages. However, existing surge arrester monitoring methods have several shortcomings: 1. Surge arrester detection relies on power outages for maintenance, which has significant limitations and cannot accurately assess the actual condition of the equipment, leading to over- or under-maintenance, increased operating costs, and difficulty in preventing sudden failures; 2. Using fixed warning thresholds makes it difficult to adapt to equipment characteristics under different operating years and load conditions, resulting in a high false alarm rate; 3. The lack of a unified platform for coupled analysis of parameters such as surge arrester leakage current, cable circulating current, and junction box temperature leads to insufficient fault prediction capabilities. Therefore, to solve these problems, it is necessary to develop a method for monitoring the operational status of surge arresters used in high-voltage cable terminal towers that provides accurate early warnings and enables multi-dimensional monitoring. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method for monitoring the operating status of surge arresters used in high-voltage cable terminal towers of power grids that provides accurate early warning and enables multi-dimensional monitoring.

[0004] The objective of this invention is achieved as follows: A method for monitoring the operational status of surge arresters used in high-voltage cable terminal towers of power grids, comprising the following steps: Step 1: Real-time acquisition of surge arrester operating data is performed using data acquisition components. Specifically, leakage current detection unit is used to acquire the total current and resistive current signals of the surge arrester, and sheath grounding loop current sensor is used to acquire the loop current signal of the three-phase grounding wire at the cable terminal. Step 2: Preprocess and perform spatiotemporal synchronization calibration on the data collected in Step 1, and correct the impact of spatial distribution interference and electromagnetic interference on the data based on the cable coupling coefficient and phase coupling coefficient. Then, establish a correlation analysis model between the surge arrester leakage current and the cable circulating current. Step 3: Based on the equipment's historical operating data and years of operation, considering the natural aging of materials, and in conjunction with real-time load conditions such as load current and ambient temperature and humidity, a personalized early warning threshold is generated using a dynamic threshold algorithm. Then, the pre-processed and spatiotemporally synchronized data is judged for anomalies using this early warning threshold. When the data exceeds the dynamic threshold range, a graded early warning is triggered, and the data is extracted and stored for backup. Step 4: Based on the correlation analysis model, perform coupled analysis on the surge arrester leakage current signal and cable circulating current signal in the extracted data. Then, through the preset fault feature mapping library, identify the associated fault risks and fault locations such as abnormal circulating current caused by poor grounding and surge arrester overload. Finally, output a monitoring report based on the identification and analysis results. Step 5: Classify and label the monitoring reports according to the warning level, and upload the monitoring reports to the operation and maintenance management platform via wireless communication after labeling, so as to realize the visualization, trend analysis and warning push of the surge arrester status.

[0005] Furthermore, the leakage current detection unit in step 1 includes a rectifier module, a low-pass filter circuit, and a current amplifier circuit. It can output a full current signal and a resistive current signal separately. The sheath grounding circulating current sensor adopts an open and closed structure to adapt to the on-site installation requirements of high-voltage cable terminals.

[0006] Furthermore, in step 4, the fault feature mapping library can extract the amplitude deviation, phase difference, and trend characteristics of the surge arrester leakage current and cable circulating current, thereby achieving accurate location of related faults.

[0007] Furthermore, the data preprocessing operations in step 2 include data cleaning, filtering, normalization, and fusion processing. Data cleaning removes outliers and null values, data filtering removes the influence of electromagnetic interference and impulse noise on the data, data normalization eliminates the incommensurability between data features due to differences in dimensions and sizes, and data fusion uses a feature fusion algorithm based on an attention mechanism to achieve multi-source data fusion.

[0008] Furthermore, in step 3, the dynamic threshold algorithm uses a deep learning model to fit the mapping relationship between the equipment's operating years, load intensity, and normal operating parameters, and adjusts the warning threshold range in a timely manner.

[0009] The beneficial effects of the present invention are as follows: The present invention collects the operating data of the surge arrester in real time, preprocesses and calibrates the collected data in a time and space, and then corrects the influence of spatial distribution interference and electromagnetic interference on the data based on the cable coupling coefficient and the phase coupling coefficient. This method can increase the consistency of the data. This invention establishes a correlation analysis model and performs coupled analysis on the surge arrester leakage current signal and cable circulating current signal in the extracted data. This allows for the comprehensive identification of correlated faults through multi-physical coupling analysis, thereby overcoming the limitations of single monitoring. This invention, based on historical operating data and years of operation of equipment, considering the natural aging law of materials, and relating to real-time load conditions such as load current, ambient temperature and humidity, uses a deep learning model to fit the mapping relationship between the years of operation of equipment, load intensity and normal operating parameters, and generates personalized dynamic early warning thresholds. This solves the problem that existing fixed early warning thresholds are difficult to adapt to the characteristics of equipment under different years of operation and load conditions, resulting in a high false alarm rate. This invention enables the visualization, trend analysis, and early warning push of surge arrester status through the output and upload of monitoring reports; in general, this invention has the advantages of accurate early warning and the ability to achieve multi-dimensional monitoring. Detailed Implementation

[0010] The present invention will now be further described.

[0011] Example: A method for monitoring the operational status of surge arresters used in high-voltage cable terminal towers of power grids, comprising the following steps: Step 1: Real-time acquisition of surge arrester operating data is performed using data acquisition components. Specifically, the leakage current detection unit acquires the total current and resistive current signals of the surge arrester, and the sheath grounding circulating current sensor acquires the ring network current signal of the three-phase grounding wire of the cable terminal. The leakage current detection unit includes a rectifier module, a low-pass filter circuit, and a current amplification circuit, and can separately output the total current signal and the resistive current signal. The sheath grounding circulating current sensor adopts an open and closed structure to adapt to the on-site installation requirements of high-voltage cable terminals. Step 2: Preprocess and perform spatiotemporal synchronization calibration on the data collected in Step 1. Based on the cable coupling coefficient and phase-to-phase coupling coefficient, correct the impact of spatial distribution interference and electromagnetic interference on the data. Then, establish a correlation analysis model between the surge arrester leakage current and the cable circulating current. The data preprocessing operation includes data cleaning, filtering, normalization, and fusion processing. Data cleaning removes outliers and null values, data filtering removes the impact of electromagnetic interference and impulse noise on the data, data normalization eliminates the incommensurability between data features due to differences in dimensions and sizes, and data fusion uses a feature fusion algorithm based on an attention mechanism to achieve multi-source data fusion. Step 3: Based on the equipment's historical operating data and years of service, considering the natural aging process of materials, and in conjunction with real-time load conditions such as load current and ambient temperature and humidity, a personalized early warning threshold is generated using a dynamic threshold algorithm. Then, this early warning threshold is used to judge anomalies in the pre-processed and spatiotemporally synchronized data. When the data exceeds the dynamic threshold range, a tiered early warning is triggered, and this portion of data is extracted and backed up. The dynamic threshold algorithm uses a deep learning model to fit the mapping relationship between the equipment's years of service, load intensity, and normal operating parameters, adjusting the early warning threshold range in a timely manner. Step 4: Based on the correlation analysis model, couple the surge arrester leakage current signal and cable circulating current signal in the extracted data. Then, through the preset fault feature mapping library, analyze the amplitude deviation, phase difference and trend characteristics of the extracted surge arrester leakage current and cable circulating current to identify associated fault risks and fault locations such as abnormal circulating current caused by poor grounding and surge arrester overload. Finally, output a monitoring report based on the identification and analysis results. Step 5: Classify and label the monitoring reports according to the warning level, and upload the monitoring reports to the operation and maintenance management platform via wireless communication after labeling, so as to realize the visualization, trend analysis and warning push of the surge arrester status.

[0012] In use, this invention first acquires real-time operational data of the surge arrester using a data acquisition component. This process involves using a leakage current detection unit to acquire the total current and resistive current signals of the surge arrester, and using a sheath grounding circulating current sensor to acquire the ring network current signal of the three-phase grounding wire at the cable terminal. The leakage current detection unit includes a rectifier module, a low-pass filter circuit, and a current amplification circuit. Then, the acquired data undergoes preprocessing and spatiotemporal synchronization calibration. Based on the cable coupling coefficient and inter-phase coupling coefficient, the influence of spatial distribution interference and electromagnetic interference on the data is corrected. Finally, a correlation analysis model between the surge arrester leakage current and the cable circulating current is established. During this process, data preprocessing operations include data cleaning and filtering. The data processing involves normalization and fusion. Data cleaning removes outliers and null values; data filtering eliminates electromagnetic interference and impulse noise; data normalization eliminates incommensurability caused by differences in units and dimensions between data features; and data fusion uses an attention-based feature fusion algorithm to fuse multi-source data. Next, based on historical equipment operating data and years of operation, considering the natural aging of materials, and relating to real-time load conditions such as load current and ambient temperature and humidity, a dynamic threshold algorithm generates personalized early warning thresholds. These thresholds are then used to identify anomalies in the pre-processed and spatiotemporally synchronized data. When data exceeds the dynamic threshold range, a tiered early warning is triggered, and the affected data is processed accordingly. The data is extracted and stored for backup. The dynamic threshold algorithm uses a deep learning model to fit the mapping relationship between the equipment's operating years, load intensity, and normal operating parameters, adjusting the warning threshold range in a timely manner. Finally, based on a correlation analysis model, the surge arrester leakage current signal and cable circulating current signal in the extracted data are coupled and analyzed. Then, using a pre-set fault feature mapping library, the amplitude deviation, phase difference, and trend characteristics of the extracted surge arrester leakage current and cable circulating current are analyzed to identify associated fault risks and fault locations, such as abnormal circulating current caused by poor grounding and surge arrester overload. Finally, a monitoring report is output based on the identification and analysis results. After completing the above operations, the monitoring reports are classified according to the warning level. After marking, the monitoring report is uploaded to the operation and maintenance management platform via wireless communication, thereby realizing the visualization, trend analysis, and early warning push of the surge arrester status. This invention increases data consistency by collecting, preprocessing, and calibrating the surge arrester's operating data in real time. By establishing a correlation analysis model and performing coupled analysis on the surge arrester leakage current signal and cable circulating current signal in the extracted data, multi-physical coupling analysis can be used to achieve comprehensive identification of related faults, thereby solving the limitations of single monitoring. By setting dynamic early warning thresholds, the problem of existing fixed early warning thresholds being difficult to adapt to the characteristics of equipment under different operating years and load conditions, resulting in a high false alarm rate can be solved.By outputting and uploading monitoring reports, the status of surge arresters can be visualized, trends analyzed, and early warnings pushed out. Overall, this invention has the advantages of accurate early warning and the ability to achieve multi-dimensional monitoring.

[0013] The above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of the claims of the present invention.

Claims

1. A method for monitoring the operational status of surge arresters used in high-voltage cable terminal towers of power grids, characterized in that, Includes the following steps: Step 1: Real-time acquisition of surge arrester operating data is performed using data acquisition components. Specifically, leakage current detection unit is used to acquire the total current and resistive current signals of the surge arrester, and sheath grounding loop current sensor is used to acquire the loop current signal of the three-phase grounding wire at the cable terminal. Step 2: Preprocess and perform spatiotemporal synchronization calibration on the data collected in Step 1, and correct the impact of spatial distribution interference and electromagnetic interference on the data based on the cable coupling coefficient and phase coupling coefficient. Then, establish a correlation analysis model between the surge arrester leakage current and the cable circulating current. Step 3: Based on the equipment's historical operating data and years of operation, considering the natural aging of materials, and in conjunction with real-time load conditions such as load current and ambient temperature and humidity, a personalized early warning threshold is generated using a dynamic threshold algorithm. Then, the pre-processed and spatiotemporally synchronized data is judged for anomalies using this early warning threshold. When the data exceeds the dynamic threshold range, a graded early warning is triggered, and the data is extracted and stored for backup. Step 4: Based on the correlation analysis model, perform coupled analysis on the surge arrester leakage current signal and cable circulating current signal in the extracted data. Then, through the preset fault feature mapping library, identify the associated fault risks and fault locations such as abnormal circulating current caused by poor grounding and surge arrester overload. Finally, output a monitoring report based on the identification and analysis results. Step 5: Classify and label the monitoring reports according to the warning level, and upload the monitoring reports to the operation and maintenance management platform via wireless communication after labeling, so as to realize the visualization, trend analysis and warning push of the surge arrester status.

2. The method for monitoring the operating status of surge arresters for high-voltage cable terminal towers in power grids as described in claim 1, characterized in that: The leakage current detection unit in step 1 includes a rectifier module, a low-pass filter circuit, and a current amplifier circuit. It can output a full current signal and a resistive current signal separately. The sheath grounding circulating current sensor adopts an open and close structure to adapt to the on-site installation requirements of high-voltage cable terminals.

3. The method for monitoring the operating status of surge arresters for high-voltage cable terminal towers in power grids as described in claim 1, characterized in that: In step 4, the fault feature mapping library can extract the amplitude deviation, phase difference, and trend characteristics of the surge arrester leakage current and cable circulating current, thereby achieving accurate location of related faults.

4. The method for monitoring the operating status of surge arresters for high-voltage cable terminal towers in power grids as described in claim 1, characterized in that: The data preprocessing operations in step 2 include data cleaning, filtering, normalization, and fusion. Data cleaning removes outliers and null values, data filtering removes the influence of electromagnetic interference and impulse noise on the data, data normalization eliminates the incommensurability between data features due to differences in dimensions and sizes, and data fusion uses a feature fusion algorithm based on an attention mechanism to achieve multi-source data fusion.

5. The method for monitoring the operating status of surge arresters for high-voltage cable terminal towers in power grids as described in claim 1, characterized in that: In step 3, the dynamic threshold algorithm uses a deep learning model to fit the mapping relationship between the equipment's operating years, load intensity, and normal operating parameters, and adjusts the warning threshold range in a timely manner.