WO2023284127A1

WO2023284127A1 - Vibration-signal-based online monitoring system for gil defects, and method

Info

Publication number: WO2023284127A1
Application number: PCT/CN2021/120820
Authority: WO
Inventors: 徐惠; 张静; 李梦齐; 杨旭; 刘梦娜; 胡长猛; 程林; 黄立才
Original assignee: 国网电力科学研究院武汉南瑞有限责任公司; 国网电力科学研究院有限公司; 国网山西省电力公司
Priority date: 2021-07-15
Filing date: 2021-09-27
Publication date: 2023-01-19
Also published as: CN113607271A; LU503633B1

Abstract

A vibration-signal-based online monitoring system for GIL defects, and a method. The monitoring system comprises a vibration signal collection module (1), a vibration signal feature extraction module (2), a device defect identification module (3) and a data storage display module (4), wherein the vibration signal collection module (1) is used for collecting a GIL housing vibration signal; the vibration signal feature extraction module (2) is used for extracting feature parameters of a vibration signal in three aspects, i.e. a time domain and/or a frequency domain and/or a time-frequency domain; and the device defect identification module (3) is used for identifying whether there is a defect in a GIL, identifying a defect type, and storing feature parameters of the vibration signal that cannot be identified and a corresponding device state in the data storage display module (4). By means of the system, not only can online monitoring and live detection be performed on the state of a GIL during the running process without a power failure, the running state of the GIL can also be analyzed and an alarm can also be given in real time, and database updating can also be performed according to a newly added defect type during the running process of the GIL, thereby improving the accuracy of GIL defect identification.

Description

A system and method for on-line monitoring of GIL defects based on vibration signals

technical field

The invention belongs to the technical field of electrician detection, in particular to the defect detection technology of a gas-insulated metal-enclosed transmission line (GIL).

Background technique

Gas-insulated metal-enclosed transmission line (GIL) is a kind of high-voltage, high-current power transmission equipment that is insulated by SF6 or SF6/N2 mixed gas, and the shell and conductor are coaxially arranged. It has the advantages of large transmission capacity, small footprint, flexible layout, high reliability, maintenance-free, long life, and small interaction with the environment. The use of GIL can solve the problem of erecting transmission lines in special meteorological environments or special locations. Through reasonable planning and design, not only can the system cost be greatly reduced, but also the reliability of the system can be improved.

GIL adopts a fully sealed design, and has a large air chamber and long pipeline. When discharge, mechanical or overheating defects occur during operation, existing methods are difficult to accurately locate the fault point. In order to reduce the probability of GIL serious faults and improve the repair efficiency after faults occur, it is necessary to accurately and quickly identify, locate and warn GIL defects.

At present, for GIL fault diagnosis technology, the research mainly focuses on the detection technology of UHF and ultrasonic discharge signals, and there are few researches on GIL vibration technology and mechanical defects. At the same time, the post-event positioning of GIL breakdown faults is mainly carried out, and there is a lack of research on online monitoring and pre-fault early warning technologies.

Contents of the invention

The purpose of the present invention is to provide a GIL defect online monitoring system and method based on vibration signals, realize the online monitoring of GIL operating status, and judge in real time whether there are mechanical or discharge defects in GIL, realize early identification and early warning of faults, and reduce GIL The probability of equipment failure occurs, and the type of equipment defect is identified and judged, and the location of the possible defect is given, thereby reducing troubleshooting events and improving repair efficiency after a failure occurs.

To achieve this goal, the GIL defect online monitoring system based on vibration signals designed by the present invention includes a vibration signal acquisition module, a vibration signal feature extraction module, an equipment defect identification module and a data storage display module; the vibration signal acquisition unit is used for Collect the vibration signal of the GIL shell, and transmit the vibration signal to the vibration signal feature extraction module; the vibration signal feature extraction module is used to extract the characteristic parameters of the vibration signal in the time domain, frequency domain and time-frequency domain, and transmit the characteristic parameters of the vibration signal to the device defect identification module; the device defect recognition module normalizes the characteristic parameters of the vibration signal, and then uses the maximum correlation minimum redundancy algorithm to analyze the redundancy between each characteristic parameter and the correlation between the characteristic parameters and various types of vibration signal characteristic maps in the data storage and display module, and prioritize the characteristic parameters according to the weight of the characteristic parameters, and finally use the defect recognition algorithm to analyze the equipment status represented by each characteristic parameter, Comprehensively assessing whether the GIL has defects based on the equipment status and obtaining equipment defect type and defect level data, the equipment defect identification module transmits the characteristic parameters of the vibration signal, equipment status, equipment defect type and level data to the data storage and display module ; If the equipment defect level reaches the failure level, the equipment defect identification module generates an alarm signal; the data storage and display module is used to store and display the characteristic parameters, equipment status, equipment defect type and level data of the vibration signal.

A method for online monitoring and diagnosis of GIL defects based on vibration signals, comprising the steps of:

Step 1, vibration signal collection: the vibration signal collection unit collects the vibration signal of the GIL shell, and transmits the vibration signal to the vibration signal feature extraction module;

Step 2, vibration signal feature extraction: the vibration signal feature extraction module extracts the characteristic parameters of the vibration signal of the GIL shell in the time domain, frequency domain and time-frequency domain, and transmits the vibration signal characteristic parameters to the equipment defect identification module ;

Step 3, GIL equipment status diagnosis: the equipment defect identification module normalizes the characteristic parameters of the vibration signal, and then uses the maximum correlation minimum redundancy algorithm to analyze the redundancy between the characteristic parameters and the characteristic parameters and data storage display The correlation between various vibration signal characteristic maps in the module, and the characteristic parameters are optimized and sorted according to the weight of the characteristic parameters. Finally, the defect recognition algorithm is used to analyze the equipment status represented by each characteristic parameter, and the comprehensive equipment status is used to evaluate whether the GIL exists. Defects and obtain equipment defect type and defect level data, the equipment defect identification module transmits the characteristic parameters of the vibration signal, equipment status, equipment defect type and level data to the data storage display module; if the equipment defect level reaches the fault level, Then the equipment defect identification module generates an alarm signal.

The beneficial effects of the present invention are:

1. The present invention can realize the defect analysis of the equipment by collecting and analyzing the vibration signal of the GIL shell, and realize the online monitoring and electrification detection of the state of the GIL during operation without power failure;

2. The present invention can analyze the running state of GIL in real time and give an alarm in real time, and update the database according to the newly added defect types in the running process of GIL, so as to improve the accuracy of GIL defect recognition;

3. The present invention identifies and judges the type of equipment defect, and gives the location where the defect may occur, thereby reducing troubleshooting events and improving repair efficiency after a fault occurs.

Description of drawings

Fig. 1 is a schematic diagram of the system structure of the present invention;

Fig. 2 is method flowchart of the present invention;

Among them, 1-vibration signal acquisition module, 2-vibration signal feature extraction module, 3-equipment defect identification module, 4-data storage display module, 5-equipment defect alarm module, 11-vibration sensor and 12-acquisition card.

detailed description

Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

A kind of GIL defective online monitoring system based on vibration signal, as shown in Figure 1, it comprises vibration signal acquisition module 1, vibration signal feature extraction module 2, equipment defect recognition module 3 and data storage display module 4; Described vibration signal acquisition Unit 1 is used to collect the vibration signal of the GIL shell, and transmits the vibration signal to the vibration signal feature extraction module 2; the vibration signal feature extraction module 2 is used to extract the vibration signal in the time domain, frequency domain and time-frequency domain characteristic parameters of each aspect, and transmit the vibration signal characteristic parameters to the equipment defect identification module 3; the equipment defect identification module 3 normalizes the vibration signal characteristic parameters, and then uses the maximum correlation minimum redundancy algorithm to analyze each The redundancy between the characteristic parameters and the correlation between the characteristic parameters and the various types of vibration signal characteristic maps in the data storage display module 4, and according to the weight of the characteristic parameters, the characteristic parameters are optimally sorted to obtain the characteristic parameter sorting results, Finally, the defect identification algorithm is used to analyze the redundancy, the correlation between the characteristic maps and the ranking results of the characteristic parameters, evaluate the equipment status represented by each characteristic parameter, and comprehensively evaluate whether the GIL has a defect based on the equipment status And obtain equipment defect type and defect level data, described equipment defect identification module 3 transmits the characteristic parameter of vibration signal, equipment state, equipment defect type and level data to described data storage display module 4; If equipment defect level reaches failure level , then the equipment defect identification module 3 generates an alarm signal; the data storage display module 4 is used to store and display the characteristic parameters, equipment status, equipment defect type and level data of the vibration signal.

In the above technical solution, the characteristic parameter weights are determined according to the results of defect simulation tests, and can be adjusted and updated according to the results of on-site fault detection.

An on-line monitoring system for GIL defects based on vibration signals, as shown in FIG. 1 , also includes an equipment defect alarm module 5 configured to issue the alarm signal generated by the equipment defect identification module 3 .

In the above technical solution, if the equipment defect identification module 3 cannot identify the characteristic parameters of the vibration signal, the staff will determine the equipment status through tests and on-site inspections, and the equipment defect identification module 3 will receive the equipment status and will not be able to The identified characteristic parameters of the vibration signal and the corresponding equipment status are stored in the data storage display module 4 .

In the above technical solution, the vibration signal collection unit 1 includes a plurality of vibration sensors 11 and a collection card 12, the vibration sensors 11 are used to collect the vibration signal of the GIL shell, and the collection card 12 is used to receive the vibration of the vibration sensor 11 signal and transmit the vibration signal to the vibration signal feature extraction module 2.

In the above technical solution, the characteristic parameters of the vibration signal include any of the following parameters or any combination thereof: amplitude, frequency characteristics, attenuation characteristics, pulse characteristics, and marginal spectrum distribution characteristics of the vibration signal.

In the above technical solution, the vibration sensor 11 can be fixed on the GIL shell by sticking or strapping, the base material of the vibration sensor 11 is determined by the GIL shell material, and the base curvature of the vibration sensor 11 is determined by the GIL The shell radius is determined to ensure that the base of the vibration sensor 11 matches the radius of the GIL shell, and the vibration sensor 11 can be firmly fixed on the surface of the GIL; the size and surface of the vibration sensor (11) are adjusted according to the GIL shell, so The detection frequency range of the vibration sensor 11 is 0-15kHz, and the measurement sensitivity is not lower than 0.00001g.

A kind of GIL defects online monitoring diagnosis method based on vibration signal, as shown in Figure 2, it comprises the following steps:

Step 1, the vibration signal acquisition unit 1 collects the vibration signal of the GIL shell, and transmits the vibration signal to the vibration signal feature extraction module 2;

Step 2, the vibration signal feature extraction module 2 extracts the characteristic parameters of the GIL shell vibration signal in the time domain, frequency domain and time-frequency domain, and transmits the vibration signal characteristic parameters to the equipment defect identification module 3;

Step 3, the equipment defect identification module 3 normalizes the characteristic parameters of the vibration signal, and then uses the maximum correlation minimum redundancy algorithm to analyze the redundancy between the characteristic parameters and the characteristic parameters and the data stored in the display module 4. According to the correlation between the characteristic maps of similar vibration signals, the characteristic parameters are optimized and sorted according to the weight of the characteristic parameters. Finally, the defect identification algorithm is used to analyze the equipment status represented by each characteristic parameter, and the equipment status is comprehensively evaluated to determine whether the GIL has defects and obtain Equipment defect type and defect level data, the device defect identification module 3 transmits the characteristic parameters, equipment status, equipment defect type and level data of the vibration signal to the data storage display module 4; if the equipment defect level reaches the failure level, then The device defect identification module 3 generates an alarm signal;

Step 4: The equipment defect alarm module 5 is used to issue the alarm signal generated by the equipment defect identification module 3 to remind the operation and maintenance personnel to pay attention to the equipment status; if the equipment defect identification module 3 cannot identify the characteristic parameters of the vibration signal, the staff will pass The equipment status is determined by means of testing and on-site inspection and investigation. The equipment defect identification module 3 receives the equipment status, and stores the unidentifiable vibration signal characteristic parameters and corresponding equipment status into the data storage display module 4 to add GIL vibration defects. feature map.

In the above technical solution, the defect identification algorithm is a BP neural network algorithm or a support vector machine algorithm.

Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowcharts and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

The content not described in detail in this specification belongs to the prior art known to those skilled in the art.

Claims

A GIL defect online monitoring system based on vibration signals, characterized in that it includes a vibration signal acquisition module (1), a vibration signal feature extraction module (2), an equipment defect identification module (3) and a data storage display module (4) ;

The vibration signal collection unit (1) is used to collect the vibration signal of the GIL shell, and transmit the vibration signal to the vibration signal feature extraction module (2);

The vibration signal feature extraction module (2) is used to extract the characteristic parameters of the vibration signal in the time domain and/or the frequency domain and/or the time-frequency domain, and transmit the vibration signal characteristic parameters to the equipment defect identification module (3);

The equipment defect identification module (3) uses the maximum correlation minimum redundancy algorithm to analyze the redundancy between the characteristic parameters and the correlation between the characteristic parameters and the various types of vibration signal characteristic maps in the data storage display module (4) The feature parameters are optimized and sorted according to the weight of the feature parameters to obtain the feature parameter sorting results, and finally the defect identification algorithm is used to analyze the redundancy, the correlation between the feature maps and the feature parameter sorting results , evaluate the equipment state represented by each characteristic parameter, comprehensively describe the equipment state to evaluate whether there is a defect in the GIL and obtain the equipment defect type and defect level data, and the equipment defect identification module (3) combines the characteristic parameters of the vibration signal, the equipment state, the equipment Defect type and level data are transmitted to the data storage display module (4); if the equipment defect level reaches the fault level, the equipment defect identification module (3) generates an alarm signal;

The data storage and display module (4) is used for storing and displaying the characteristic parameters, equipment status, equipment defect type and level data of the vibration signal.
Based on the GIL defect online monitoring system based on vibration signals according to claim 1, it is characterized in that: the equipment defect identification module (3) first normalizes the vibration signal characteristic parameters output by the vibration signal feature extraction module (2) The normalized processing obtains the characteristic parameters of the vibration signal, and then performs the subsequent maximum correlation minimum redundancy algorithm analysis.
Based on the GIL defect online monitoring system based on vibration signals according to claim 1, it is characterized in that: it also includes an equipment defect alarm module (5), and the equipment defect alarm module (5) is used to issue the equipment defect identification module (3) Generated alarm signal.
Based on the GIL defect online monitoring system based on vibration signals according to claim 1, it is characterized in that: if the equipment defect identification module (3) cannot identify the vibration signal characteristic parameters, then the equipment defect identification module (3) receives the equipment state, and store unidentifiable vibration signal characteristic parameters and corresponding device states into the data storage display module (4).
Based on the GIL defect online monitoring system based on vibration signal according to claim 1, it is characterized in that:

The vibration signal collection unit (1) includes a plurality of vibration sensors (11) and a collection card (12), the vibration sensors (11) are used to collect vibration signals of the GIL housing, and the collection card (12) is used to receive The vibration signal of the vibration sensor (11) is transmitted to the vibration signal feature extraction module (2).
Based on the GIL defect online monitoring system based on vibration signal according to claim 1, it is characterized in that:

The characteristic parameters of the vibration signal include any of the following parameters or any combination thereof: amplitude, frequency characteristics, attenuation characteristics, pulse characteristics, and marginal spectrum distribution characteristics of the vibration signal.
Based on the GIL defect online monitoring system based on vibration signals according to claim 5, it is characterized in that: the vibration sensor (11) can be fixed on the GIL shell by pasting or strapping, and the vibration sensor (11) The base material is determined by the GIL shell material, and the base curvature of the vibration sensor (11) is determined by the GIL shell radius; the size and surface of the vibration sensor (11) are adjusted according to the GIL shell, and the vibration sensor (11) The detection frequency range is 0~15kHz, and the measurement sensitivity is not less than 0.00001g.
A kind of GIL defects online monitoring diagnosis method based on vibration signal is characterized in that: it comprises the steps:

Step 1, collecting the vibration signal of the GIL shell, and transmitting the vibration signal to the vibration signal feature extraction module (2);

Step 2, extracting the characteristic parameters of the vibration signal of the GIL shell in the time domain and/or the frequency domain and/or the time-frequency domain, and transmitting the vibration signal characteristic parameters to the equipment defect identification module (3);

Step 3, normalize the characteristic parameters of the vibration signal, and then use the maximum correlation minimum redundancy algorithm to analyze the redundancy between the characteristic parameters and the characteristic spectra of various vibration signals in the characteristic parameters and data storage display module (4) According to the correlation between the characteristic parameters, the characteristic parameters are optimized and sorted according to the weight of the characteristic parameters. Finally, the defect identification algorithm is used to analyze the equipment status represented by each characteristic parameter, and the equipment status is integrated to evaluate whether there is a defect in the GIL and obtain the equipment defect type and defect Level data, the equipment defect identification module (3) transmits the characteristic parameters, equipment status, equipment defect type and level data of the vibration signal to the data storage display module (4); if the equipment defect level reaches the fault level, the The device defect identification module (3) generates an alarm signal.
Based on the GIL defect online monitoring method based on vibration signal according to claim 8, it is characterized in that: it also includes step 4: issue the warning signal that described equipment defect recognition module (3) generates; If described device defect recognition module ( 3) If the characteristic parameters of the vibration signal cannot be identified, the equipment defect identification module (3) receives the equipment status, and stores the unidentifiable vibration signal characteristic parameters and corresponding equipment status into the data storage and display module (4).
The online monitoring method for GIL defects based on vibration signals according to claim 9, characterized in that: the defect identification algorithm is a BP neural network algorithm or a support vector machine algorithm.