CN115524583A - Partial discharge monitoring method, device and medium for GIS - Google Patents
Partial discharge monitoring method, device and medium for GIS Download PDFInfo
- Publication number
- CN115524583A CN115524583A CN202211131400.7A CN202211131400A CN115524583A CN 115524583 A CN115524583 A CN 115524583A CN 202211131400 A CN202211131400 A CN 202211131400A CN 115524583 A CN115524583 A CN 115524583A
- Authority
- CN
- China
- Prior art keywords
- gis
- partial discharge
- current
- amplitude
- grounding
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
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
- G01R31/1227—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
- G01R31/1254—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 gas-insulated power appliances or vacuum gaps
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/0046—Arrangements for measuring currents or voltages or for indicating presence or sign thereof characterised by a specific application or detail not covered by any other subgroup of G01R19/00
- G01R19/0053—Noise discrimination; Analog sampling; Measuring transients
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R19/00—Arrangements for measuring currents or voltages or for indicating presence or sign thereof
- G01R19/0092—Arrangements for measuring currents or voltages or for indicating presence or sign thereof measuring current only
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention discloses a method, a device and a medium for monitoring partial discharge of a GIS (geographic information system). The method comprises the steps of collecting the amplitude and the phase of ground current of a plurality of sampling points which are sequentially arranged on a GIS shell along a specified direction; judging whether the difference between the amplitude values of the grounding currents of any two sampling points exceeds a preset threshold value, if so, normalizing the amplitude value and the phase value of the grounding current of each sampling point, then constructing a characteristic vector, inputting the characteristic vector into a machine learning model trained in advance, obtaining the current local discharge fault position, and outputting the current local discharge fault position and the amplitude value of the grounding current. The invention can realize the on-line monitoring of the local discharge fault position and the amplitude of the grounding current without depending on the technical level of operators, and has high reliability and precision of the detection result.
Description
Technical Field
The invention relates to the technical field of GIS discharge monitoring, in particular to a method, a device and a medium for monitoring partial discharge of a GIS.
Background
The gas insulated totally-enclosed combined electrical appliance (GIS for short) is mainly composed of circuit breaker, isolating switch, grounding switch, mutual inductor, lightning arrester, bus, connecting piece and outgoing line terminal, all of which are packaged in metal shell, wherein the metal shell is grounded, and the metal shell is filled with insulating gas with certain pressure, such as sulfur hexafluoride (SF) 6 ). According to different detection principles and means, the GIS commonly used partial discharge detection method comprises five methods, namely an ultrahigh frequency method, an ultrasonic method, a chemical detection method, an optical detection method and a high-frequency current method. The ultra-high frequency detection method (UHF method) detects internal discharge by measuring electromagnetic waves (the frequency band is 0.3-3 GHz) at an insulation gap, does not change the operation mode of equipment, can effectively inhibit background noise, and has strong anti-interference capability. But it can only know that a fault has occurred, but it cannot accurately locate the point where the fault has occurred and cannot determine the amount of discharge. Ultrasonic detection (AE) is a method of detecting internal discharge by receiving a sound wave vibration signal with a piezoelectric transducer attached to the surface of the GIS case. Sensor andthe electrical circuit of the GIS device has no connection, can be used for live measurement, and can be used for positioning defects. But has the defects of no distinction between the discharge signal and the interference signal, low sensitivity, great influence on the measurement effect when the operation is not proper, and the like. The chemical detection method is used for determining the severity of the discharge defect by analyzing the content of gas component products caused by partial discharge in the GIS, and has the advantages of poor sensitivity, failure positioning, online monitoring and less application. The optical detection method is used for determining internal discharge by detecting photons through a photomultiplier effect, has the problems of poor sensitivity, failure positioning and the like, is effective in monitoring the failure of a known discharge position, and has few application scenes. The high frequency current method (HFCT method) realizes partial discharge detection by mounting a high frequency current sensor on a ground line to detect a high frequency current signal. The high-frequency current method generally uses a Rogowski coil method in which a coil of a conductive wire is wound around a ring-shaped core material in a plurality of turns, and a high-frequency alternating electromagnetic field caused by a high-frequency current passing through the center of the core generates a voltage induced in the coil. The live detection and online monitoring can be realized, but the fault location cannot be realized. In summary, the ultrahigh frequency method, the ultrasonic method and the combined detection method thereof are applied to actual GIS operation and maintenance, wherein only the ultrasonic detection method can realize fault location, but the problems of easy interference from external vibration, high operation requirement, failure of sensor when the sensor is not installed properly and the like exist. Therefore, how to realize online GIS partial discharge monitoring and fault location has no better solution, which becomes a key technical problem to be solved urgently.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the invention can realize the on-line monitoring of the local discharge fault position and the amplitude of the grounding current, does not need to depend on the technical level of operators, and has high reliability and high precision of the detection result.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a partial discharge monitoring method for a GIS comprises the following steps:
s101, collecting the amplitude and the phase of the grounding current of a plurality of sampling points sequentially arranged on a GIS shell along a specified direction;
s102, judging whether the difference of the amplitude values of the grounding currents of any two sampling points exceeds a preset threshold value, if not, jumping to the step S101 to continue monitoring; otherwise, jumping to step S103;
s103, normalizing the amplitude and the phase of the grounding current of each sampling point to construct a characteristic vector;
and S104, inputting the feature vector into a machine learning model trained in advance to obtain a current partial discharge fault position, outputting the current partial discharge fault position and the amplitude of the grounding current, and skipping to the step S101 to continue monitoring.
Optionally, the amplitude and the phase of the ground current of the sampling point in step S101 are acquired by a high-frequency current sensor on the ground line to which the sampling point is connected.
Optionally, the resistance of the ground line is no greater than 4 ohms.
Alternatively, the plurality of sampling points are arranged equidistantly in the specified direction in step S101.
Alternatively, the intervals at which the plurality of sampling points are arranged equidistantly in the specified direction in step S101 are not more than 2 meters.
Optionally, step S104 is preceded by the step of training the machine learning model:
s201, aiming at a monitored GIS, generating local discharge signals artificially, collecting amplitude values and phases of ground currents of a plurality of sampling points which are sequentially arranged on a GIS shell corresponding to each local discharge signal along a specified direction, normalizing the amplitude values and the phases of the ground currents of the sampling points to construct a characteristic vector, generating a label at a position where the local discharge signal is generated, and forming a sample data set by the characteristic vector and the label corresponding to the characteristic vector;
s202, randomly dividing a sample data set into a training data set and a testing data set;
s203, training a machine learning model by adopting a training data set;
s204, aiming at the machine learning model which completes the training of the current round, testing by adopting a test data set to obtain the accuracy;
s205, judging whether the accuracy rate reaches the standard, and if not, skipping to S201 to continue training the machine learning model; otherwise, the network parameters of the machine learning model are saved, and the machine learning model which completes training is obtained.
Optionally, the machine learning model is a BP neural network, the BP neural network includes an input layer, a hidden layer and an output layer, the number of elements in the feature vector is twice the number of sampling points, each element represents the amplitude or phase of the ground current after one sampling point is normalized, the number of neurons in the input layer is the same as the number of elements in the feature vector, the hidden layer is used for connecting the input layer and the output layer, weights of connecting edges are used as network parameters of the BP neural network, and the output layer includes a neuron for outputting a current partial discharge fault location.
In addition, the invention also provides a partial discharge monitoring device for the GIS, which comprises an upper computer, a data acquisition module and a plurality of grounding wires, wherein the grounding wires are respectively and correspondingly connected with a plurality of sampling points which are sequentially arranged on a monitored GIS shell along a specified direction one by one, each grounding wire is connected with a high-frequency current sensor for acquiring the amplitude and the phase of grounding current in series, the output end of the high-frequency current sensor is connected with the upper computer through the data acquisition module, the upper computer comprises a microprocessor and a memory which are mutually connected, and the microprocessor is programmed or configured to execute the partial discharge monitoring method for the GIS.
In addition, the invention also provides a partial discharge monitoring device for the GIS, which comprises a microprocessor and a memory which are connected with each other, wherein the microprocessor is programmed or configured to execute the partial discharge monitoring method for the GIS.
Furthermore, the present invention also provides a computer-readable storage medium having stored therein a computer program for being programmed or configured by a microprocessor to execute the partial discharge monitoring method for a GIS.
Compared with the prior art, the invention mainly has the following advantages:
1. the method comprises the steps of collecting the amplitude and the phase of grounding current of a plurality of sampling points which are sequentially arranged on a GIS shell along a specified direction; the method judges whether the difference of the grounding current amplitudes of any two sampling points exceeds a preset threshold value, so as to judge whether the partial discharge fault occurs, and can reduce the operation frequency of subsequent partial discharge fault position diagnosis, thereby achieving the purposes of reducing the consumption of computing resources and saving energy consumption, and improving the efficiency of partial discharge fault position diagnosis after partial discharge.
2. When a discharge fault in the GIS occurs, a large amount of high-energy free electrons can be generated, and partial electrons can penetrate SF6 gas to be hit on the shell and finally flow to the ground through a connecting wire. The quantity of free electrons generated by discharge can be detected by arranging the grounding wires and the high-frequency current sensors in sequence, electrons flow from the shell to the ground and can be simplified into a current source model, the electrons are transmitted to the ground through the grounding electrode and are related to the distance position of the grounding electrode, and the current passing through the grounding electrode close to the grounding electrode is larger. The method comprises the steps of normalizing the amplitude and the phase of the ground current of each sampling point, constructing a characteristic vector, inputting the characteristic vector into a machine learning model trained in advance, obtaining a current partial discharge fault position, and outputting the current partial discharge fault position and the amplitude of the ground current, on one hand, extracting the characteristic vector by utilizing the relation between a plurality of sampling points and partial discharge fault positions which are sequentially arranged along a specified direction, on the other hand, considering that the amplitude of the ground current directly has a direct proportion relation with the number of high-energy free electrons of the discharge fault in the GIS, so that the amplitude and the partial discharge fault positions of the ground current of different sampling points have a correlation relation, and the phase of the ground current expresses the time for the high-energy free electrons of the discharge fault in the GIS to reach the sampling points, so that the phase of the ground current also has a correlation relation with the partial discharge fault positions, and extracting the characteristic vector by utilizing the triple correlation relation, so that the on-line monitoring of the partial discharge fault positions and the amplitude of the ground current can be realized, the technical level of an operator is not required, and the reliability and the precision of a detection result is high.
Drawings
FIG. 1 is a schematic diagram of a basic process flow of a method according to an embodiment of the present invention.
FIG. 2 is a schematic diagram of a method according to an embodiment of the present invention.
Detailed Description
As shown in fig. 1, the partial discharge monitoring method for the GIS of the present embodiment includes:
s101, collecting the amplitude and the phase of the grounding current of a plurality of sampling points sequentially arranged on a GIS shell along a specified direction;
s102, judging whether the difference of the grounding current amplitudes of any two sampling points exceeds a preset threshold value, if not, skipping to the step S101 to continue monitoring; otherwise, jumping to step S103;
s103, normalizing the amplitude and the phase of the grounding current of each sampling point to construct a characteristic vector;
and S104, inputting the characteristic vector into a pre-trained machine learning model to obtain a current partial discharge fault position, outputting the current partial discharge fault position and the amplitude of the grounding current, and skipping to the step S101 to continue monitoring.
As shown in fig. 2, the working principle of the partial discharge monitoring method for the GIS of the present embodiment is as follows: when the internal discharge fault of the GIS is generated, a large amount of high-energy free electrons can be generated, and partial electrons can penetrate SF6 gas to be hit on a shell and finally flow to the ground through a connecting wire. The quantity of free electrons generated by discharge can be detected by arranging the grounding wires and the high-frequency current sensors in sequence, the electrons flowing from the shell to the ground can be simplified into a current source model, the electrons are transmitted to the ground through the grounding electrode and are related to the position of the grounding electrode at a distance, and the current passing through the grounding electrode at a close distance is larger; the discharge position can be preliminarily judged to be in the middle area of the grounding wire with larger current amplitude by analyzing the current measured by each sensor, the time of the electronic pulse reaching the grounding wire sensor is further calculated by comparing and analyzing the phase, the discharge fault position can be accurately calculated by the path difference, and the detection precision is less than 1/2 of the interval of the grounding wires. In addition, in consideration of the problem that the accuracy of judging the partial discharge fault position directly according to the amplitude and the phase of the ground current is insufficient, in the embodiment, the amplitude and the phase of the ground current of each sampling point are normalized to construct a feature vector, and the feature vector is input into a machine learning model trained in advance to obtain the current partial discharge fault position, so that the partial discharge fault position with the detection accuracy far exceeding 1/2 of the interval of the ground wire can be obtained through the trained machine learning model, and online monitoring and accurate fault positioning can be realized, and the method is low in cost, high in accuracy and easy to realize.
In this embodiment, the amplitude and the phase of the ground current of the sampling point in step S101 are acquired by a high-frequency current sensor on the ground line to which the sampling point is connected. Generally speaking, the discharge detection sensitivity of the high-frequency current sensor is better than 5pC, and the frequency range covers 100kHz to 50MHz. Referring to fig. 2, N +1 sampling points are counted, and are respectively connected to N +1 grounding wires, for example, sampling point 1 (not labeled in the figure) is connected to grounding electrode 1 through grounding wire 1 (not labeled in the figure), the high-frequency current sensor connected in series in grounding wire 1 is denoted as sensor 1, the high-frequency current sensor connected in series in grounding wire 2 is denoted as sensor 2, \8230;, the high-frequency current sensor connected in series in grounding wire N is denoted as sensor N, and the high-frequency current sensor connected in series in grounding wire N +1 is denoted as sensor N +1. Generally, the resistance of the ground line is not greater than 4 ohms.
In order to accurately locate the position of the partial discharge fault, in step S101 of this embodiment, a plurality of sampling points are equidistantly arranged along a specific direction, so that an additional error caused by a difference in distance between the sampling points can be effectively eliminated. The designated direction may be designated as needed, and may be generally arranged along the longitudinal direction of the conductor inside the GIS, for example, in fig. 2, the designated direction is arranged along the longitudinal direction of the conductor inside the GIS. In addition, the conductor may be arranged along the width direction of the conductor inside the GIS as needed, or another direction may be selected as needed.
In this embodiment, the preset threshold in step S102 may be specified according to actual needs.
In this embodiment, the intervals at which the plurality of sampling points are equidistantly arranged in the specified direction in step S101 are not more than 2 meters.
In this embodiment, in step S103, the amplitude and the phase of the ground current of each sampling point are normalized to construct a feature vector, so that both the amplitude and the phase are normalized to be between [0,1 ]. It should be noted that the numerical values are normalized by a known data processing method, and a specific calculation function expression thereof is not described in detail here.
In this embodiment, step S104 further includes a step of training a machine learning model:
s201, aiming at a monitored GIS, generating local discharge signals artificially, acquiring the amplitude and phase of the ground current of a plurality of sampling points sequentially arranged along a specified direction on a GIS shell corresponding to each local discharge signal, normalizing the amplitude and phase of the ground current of each sampling point to construct a characteristic vector, generating a label at a position where the local discharge signal is generated, and forming a sample data set by the characteristic vector and the label corresponding to the characteristic vector;
s202, randomly dividing a sample data set into a training data set and a testing data set;
s203, training a machine learning model by adopting a training data set;
s204, aiming at the machine learning model which completes the training of the current round, testing by adopting a test data set to obtain the accuracy;
it should be noted that the accuracy here may be calculated by using the ratio of the accurate number to the total number of the test samples, may also be calculated by using an error statistic (for example, a standard deviation or a variance) between the labels of the test samples and the predicted partial discharge fault locations, and may also be calculated by using other similar statistics as needed, which may be specifically selected as needed;
s205, judging whether the accuracy rate reaches the standard, and if not, jumping to the step S201 to continue training the machine learning model; otherwise, the network parameters of the machine learning model are stored, and the machine learning model which completes training is obtained.
Through the position generation label of the partial discharge signal in the training, the machine learning model after training is utilized to establish the mapping relation between the amplitude and the phase of the grounding current of a plurality of sampling points and the partial discharge fault position, so that the partial discharge fault position with the detection precision far exceeding 1/2 of the interval of the grounding wire can be obtained, the online monitoring and the accurate fault positioning can be realized, the cost is low, the precision is high, and the realization is easy.
In this embodiment, the machine learning model is a BP neural network, the BP neural network includes an input layer, a hidden layer, and an output layer, the number of elements in the feature vector is twice the number of sampling points, each element represents the amplitude or phase of the ground current after normalization of one sampling point, the number of neurons in the input layer is the same as the number of elements in the feature vector, the hidden layer is used to connect the input layer and the output layer, and the weight of the connecting edge is used as a network parameter of the BP neural network, and the output layer includes one neuron for outputting the current partial discharge fault location.
In addition, this embodiment still provides a partial discharge monitoring devices for GIS, including host computer, data acquisition module and many earth connections, many earth connections respectively with follow a plurality of sampling points that assign direction in proper order on the monitored GIS shell one-to-one connection, each earth connection is gone up and is connected with a high frequency current sensor who is used for gathering the amplitude and the phase place of ground current in series, the output of high frequency current sensor passes through data acquisition module and links to each other with the host computer, the host computer includes interconnect's microprocessor and memory, microprocessor is programmed or configuration in order to carry out aforementioned partial discharge monitoring methods for GIS.
In addition, the present embodiment also provides a partial discharge monitoring device for a GIS, which includes a microprocessor and a memory connected to each other, wherein the microprocessor is programmed or configured to execute the aforementioned partial discharge monitoring method for a GIS.
Furthermore, the present embodiment also provides a computer-readable storage medium, in which a computer program is stored, the computer program being programmed or configured by a microprocessor to execute the aforementioned partial discharge monitoring method for the GIS.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. 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-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and adaptations to those skilled in the art without departing from the principles of the present invention should also be considered as within the scope of the present invention.
Claims (10)
1. A partial discharge monitoring method for a GIS is characterized by comprising the following steps:
s101, collecting the amplitude and the phase of grounding current of a plurality of sampling points sequentially arranged on a GIS shell along a specified direction;
s102, judging whether the difference of the amplitude values of the grounding currents of any two sampling points exceeds a preset threshold value, if not, jumping to the step S101 to continue monitoring; otherwise, jumping to step S103;
s103, normalizing the amplitude and the phase of the grounding current of each sampling point to construct a characteristic vector;
and S104, inputting the characteristic vector into a pre-trained machine learning model to obtain a current partial discharge fault position, outputting the current partial discharge fault position and the amplitude of the grounding current, and skipping to the step S101 to continue monitoring.
2. The partial discharge monitoring method for the GIS according to claim 1, wherein the amplitude and phase of the ground current of the sampling point in step S101 are acquired by a high frequency current sensor on a ground line connected to the sampling point.
3. The partial discharge monitoring method for the GIS as claimed in claim 2, wherein the resistance of the ground line is not more than 4 ohms.
4. The partial discharge monitoring method for the GIS according to claim 1, wherein the plurality of sampling points are equidistantly arranged in a designated direction in step S101.
5. The partial discharge monitoring method for the GIS according to claim 4, wherein the intervals between the plurality of sampling points equidistantly arranged in the designated direction in step S101 are not more than 2 meters.
6. The partial discharge monitoring method for the GIS according to claim 1, wherein step S104 is preceded by the step of training a machine learning model:
s201, aiming at a monitored GIS, generating local discharge signals artificially, collecting amplitude values and phases of ground currents of a plurality of sampling points which are sequentially arranged on a GIS shell corresponding to each local discharge signal along a specified direction, normalizing the amplitude values and the phases of the ground currents of the sampling points to construct a characteristic vector, generating a label at a position where the local discharge signal is generated, and forming a sample data set by the characteristic vector and the label corresponding to the characteristic vector;
s202, randomly dividing a sample data set into a training data set and a testing data set;
s203, training a machine learning model by adopting a training data set;
s204, aiming at the machine learning model which completes the training of the current round, testing by adopting a test data set to obtain the accuracy;
s205, judging whether the accuracy rate reaches the standard, and if not, skipping to S201 to continue training the machine learning model; otherwise, the network parameters of the machine learning model are stored, and the machine learning model which completes training is obtained.
7. The partial discharge monitoring method for the GIS according to claim 6, wherein the machine learning model is a BP neural network, the BP neural network comprises an input layer, a hidden layer and an output layer, the number of elements in the feature vector is twice the number of sampling points, each element represents the amplitude or phase of the ground current after one sampling point is normalized, the number of neurons in the input layer is the same as the number of elements in the feature vector, the hidden layer is used for connecting the input layer and the output layer, the weights of the edges are used as network parameters of the BP neural network, and the output layer comprises one neuron for outputting the current partial discharge fault position.
8. A partial discharge monitoring device for a GIS is characterized by comprising an upper computer, a data acquisition module and a plurality of grounding wires, wherein the grounding wires are respectively connected with a plurality of sampling points which are sequentially arranged on a monitored GIS shell along a specified direction in a one-to-one correspondence manner, a high-frequency current sensor for acquiring the amplitude and the phase of grounding current is connected to each grounding wire in series, the output end of the high-frequency current sensor is connected with the upper computer through the data acquisition module, the upper computer comprises a microprocessor and a memory which are connected with each other, and the microprocessor is programmed or configured to execute the partial discharge monitoring method for the GIS according to any one of claims 1 to 7.
9. A partial discharge monitoring device for GIS comprising a microprocessor and a memory connected to each other, wherein the microprocessor is programmed or configured to perform the partial discharge monitoring method for GIS of any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored, wherein the computer program is used for being programmed or configured by a microprocessor to execute the partial discharge monitoring method for GIS according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211131400.7A CN115524583A (en) | 2022-09-16 | 2022-09-16 | Partial discharge monitoring method, device and medium for GIS |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211131400.7A CN115524583A (en) | 2022-09-16 | 2022-09-16 | Partial discharge monitoring method, device and medium for GIS |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115524583A true CN115524583A (en) | 2022-12-27 |
Family
ID=84698710
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211131400.7A Pending CN115524583A (en) | 2022-09-16 | 2022-09-16 | Partial discharge monitoring method, device and medium for GIS |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115524583A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117970061A (en) * | 2024-04-02 | 2024-05-03 | 山东泰开电力电子有限公司 | High-voltage power capacitor fault early warning method and system |
-
2022
- 2022-09-16 CN CN202211131400.7A patent/CN115524583A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117970061A (en) * | 2024-04-02 | 2024-05-03 | 山东泰开电力电子有限公司 | High-voltage power capacitor fault early warning method and system |
| CN117970061B (en) * | 2024-04-02 | 2024-06-11 | 山东泰开电力电子有限公司 | High-voltage power capacitor fault early warning method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103930789B (en) | Apparatus and method for remote monitoring of partial discharge in electrical apparatus | |
| US9823289B2 (en) | Automated digital earth fault system | |
| JP4157636B2 (en) | Partial discharge diagnostic equipment for gas insulation equipment | |
| Shafiq et al. | Online condition monitoring of MV cable feeders using Rogowski coil sensors for PD measurements | |
| US9046563B2 (en) | Arcing event detection | |
| Pommerenke et al. | Discrimination between internal PD and other pulses using directional coupling sensors on HV cable systems | |
| EP2579056A2 (en) | Novel method for real time tests and diagnosis of the sources of partial discharge in high voltage equipment and installations, which are in service or not in service, and physical system for the practical use of the method | |
| CN102508128A (en) | Switch cabinet local discharge transient-to-ground voltage detection system based on wireless network | |
| KR20140120331A (en) | System for analyzing and locating partial discharges | |
| CN109342883A (en) | A kind of local ageing fault detecting and positioning method for cable | |
| CN108375718B (en) | Evaluation of phase-resolved partial discharges | |
| WO2005121821A1 (en) | A method and a device for determining the location of a partial discharge (pd) | |
| KR101550689B1 (en) | A arc or corona detection system for a distributing board with the acoustic emission sensor and noise removal function | |
| CN108008254A (en) | A kind of Failure Diagnosis of Substation Ground Network method and device | |
| US6418385B1 (en) | Method for determining the location of a partial discharge | |
| CN115524583A (en) | Partial discharge monitoring method, device and medium for GIS | |
| Huecker et al. | UHF partial discharge monitoring and expert system diagnosis | |
| JP2019132823A (en) | Feature amount acquisition device, discharge monitoring system, discharge monitoring device, and method for monitoring discharge | |
| CN107192943A (en) | Fault diagnosis method for switch in the GIS measured based on switching manipulation radiated electric field | |
| Behrmann et al. | State of the Art in GIS PD Diagnostics | |
| CN105842595A (en) | Broadband scanning-type cable partial discharge measurement device | |
| Farag et al. | On-line partial discharge calibration and monitoring for power transformers | |
| KR102377939B1 (en) | Partial discharge monitoring and diagnosis system for distribution board using ultra frequency and high frequency current transformer signal | |
| US11953534B2 (en) | Detection of lightning and related control strategies in electric power systems | |
| KR101843792B1 (en) | Method for deciding partial discharge for power equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |