CN114779010A - Fault traveling wave detection method based on symmetric differential energy operator and neural network - Google Patents
Fault traveling wave detection method based on symmetric differential energy operator and neural network Download PDFInfo
- Publication number
- CN114779010A CN114779010A CN202210429039.XA CN202210429039A CN114779010A CN 114779010 A CN114779010 A CN 114779010A CN 202210429039 A CN202210429039 A CN 202210429039A CN 114779010 A CN114779010 A CN 114779010A
- Authority
- CN
- China
- Prior art keywords
- fault
- mode voltage
- line
- traveling wave
- line mode
- 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
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention discloses a fault traveling wave detection method based on a symmetric differential energy operator and a neural network, which comprises the following steps: acquiring a three-phase voltage traveling wave signal of a fault to be detected through a plurality of sampling points, and performing decoupling transformation on the three-phase voltage traveling wave signal to obtain a line mode voltage component, wherein the line mode voltage component comprises an alpha line mode voltage component and a beta line mode voltage component; carrying out differential calculation on the alpha line mode voltage component or the beta line mode voltage component by using a three-point symmetrical differential energy operator to obtain an energy spectrogram corresponding to the fault to be detected; and inputting the energy spectrogram into a trained line fault diagnosis model to obtain fault information of the fault to be detected. The method can quickly judge the fault branch and the fault type of the line fault, can better solve the problem of difficult downlink wave positioning under the condition of multiple branches, and has better reliability.
Description
Technical Field
The invention relates to the technical field of distribution line fault detection, in particular to a fault traveling wave detection method based on a symmetric differential energy operator and a neural network.
Background
With the rapid development of the smart power grid, the power distribution network plays an increasingly important role in a power system, the power distribution line is used as an important component of the power distribution network, and the fault detection technology of the power distribution network is very important for the safe and stable operation of the power distribution network.
The existing distribution network fault monitoring device generally has the problems that the judgment fault is unreliable, the accurate positioning cannot be realized, and the like 1, and in order to accelerate the distribution automation construction of a smart grid, the fault is quickly positioned after the fault, and the fault is repaired to enable the system to recover to a stable state.
The traditional fault positioning mode cannot meet the requirements of the current power system development, so that the accurate and quick fault positioning method has very important significance for the stable operation of the power distribution system.
Disclosure of Invention
The invention aims to provide a fault traveling wave detection method based on a symmetric differential energy operator and a neural network, and aims to solve the technical problems of inaccurate fault location and low efficiency of a distribution line in the prior art.
The purpose of the invention can be realized by the following technical scheme:
the fault traveling wave detection method based on the symmetric differential energy operator and the neural network comprises the following steps:
acquiring a three-phase voltage traveling wave signal to be detected for a fault through a plurality of sampling points, and performing decoupling transformation on the three-phase voltage traveling wave signal to obtain a line mode voltage component, wherein the line mode voltage component comprises an alpha line mode voltage component and a beta line mode voltage component;
carrying out differential calculation on the alpha line mode voltage component or the beta line mode voltage component by using a three-point symmetrical differential energy operator to obtain an energy spectrogram corresponding to the fault to be detected;
and inputting the energy spectrogram into a trained line fault diagnosis model to obtain fault information of the fault to be detected, wherein the line fault diagnosis model is obtained by training the energy spectrogram obtained by carrying out differential calculation on line mode voltage components of various line faults by using a three-point symmetric differential energy operator.
Optionally, the obtaining of the fault information of the fault to be detected specifically includes:
and obtaining the line branch where the fault to be detected is located and the fault type of the fault to be detected.
Optionally, obtaining the fault information of the fault to be detected further includes:
and performing double-end positioning by using fault traveling wave signals acquired at two ends of the line branch where the fault to be detected is located to obtain the accurate position of the fault to be detected.
Optionally, the decoupling and transforming the three-phase voltage traveling wave signal to obtain the line mode voltage component specifically includes:
and decoupling conversion is carried out on the three-phase voltage traveling wave signals through Kerenbel conversion to obtain line mode voltage components.
Optionally, the α -line mode voltage component is:
Uα＝(UA-UB)/3；
wherein, UαIs a component of the line mode voltage, UAFor A-phase voltage signals, UBIs a B-phase voltage signal. Optionally, the β -line mode voltage component is:
Uβ＝(UA-UC)/3；
wherein, UβIs a beta line mode voltage component, UCIs a C-phase voltage signal.
Optionally, the differential calculation of the α line mode voltage component or the β line mode voltage component by using a three-point symmetric differential energy operator to obtain an energy spectrum corresponding to the fault to be detected specifically includes:
using formulas
Calculating an energy operator corresponding to each sampling point, and obtaining an energy spectrogram corresponding to the fault to be detected according to the energy operator corresponding to each sampling point;
wherein psi [ s (n)]The energy operator corresponding to the nth sampling point is shown, F(s) (n) is an operator introduced in the calculation process, and F(s) (n) is s2(n) -s (n +1) s (n-1); and s (n) is a signal corresponding to the nth sampling point, s (n +1) is a signal corresponding to the (n +1) th sampling point, and s (n-1) is a signal corresponding to the (n-1) th sampling point.
Optionally, the training process of the line fault diagnosis model includes:
simulating various line faults, extracting a plurality of three-phase voltage traveling wave signals when the faults occur, and decoupling and converting the three-phase voltage traveling wave signals to obtain corresponding alpha line mode voltage components and beta line mode voltage components;
carrying out differential calculation on each alpha mode voltage or each beta line mode voltage component by using a three-point symmetrical differential energy operator to obtain a corresponding energy spectrogram and form a training data set;
and training the line fault diagnosis model according to the training data set to obtain the trained line fault diagnosis model.
The invention provides a fault traveling wave detection method based on a symmetric differential energy operator and a neural network, which comprises the following steps: acquiring a three-phase voltage traveling wave signal to be detected for a fault through a plurality of sampling points, and performing decoupling transformation on the three-phase voltage traveling wave signal to obtain a line mode voltage component, wherein the line mode voltage component comprises an alpha line mode voltage component and a beta line mode voltage component; carrying out differential calculation on the alpha line mode voltage component or the beta line mode voltage component by using a three-point symmetrical differential energy operator to obtain an energy spectrogram corresponding to the fault to be detected; and inputting the energy spectrogram into a trained line fault diagnosis model to obtain fault information of the fault to be detected, wherein the line fault diagnosis model is obtained by training the energy spectrogram obtained by carrying out differential calculation on line mode voltage components of various line faults by using a three-point symmetric differential energy operator.
Therefore, the invention has the beneficial effects that:
according to the method, a line mode voltage component is obtained by obtaining a three-phase voltage traveling wave signal of a fault to be detected and performing decoupling transformation, differential calculation is performed on the line mode voltage component by using a three-point symmetrical differential energy operator to obtain a corresponding DEO3S energy spectrogram, and the three-point symmetrical differential energy operator has a better envelope diagram effect compared with a traditional Teager energy operator; the DEO3S energy spectrogram is input into a trained line fault diagnosis model, so that the fault branch and the fault type of the line fault can be quickly judged, the problem of difficult downlink wave positioning under the condition of multiple branches can be better solved, and the reliability is better.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a schematic diagram of a multi-branch circuit structure according to an embodiment of the present invention;
FIG. 3 is a component diagram of a traveling wave line at the line M terminal voltage according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of an energy spectrum of DEOS3 at the M end of the line according to the embodiment of the invention;
fig. 5 is a flow chart diagram of another embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a fault traveling wave detection method based on a symmetric differential energy operator and a neural network, and aims to solve the technical problems of inaccurate fault location and low efficiency of a distribution line in the prior art.
To facilitate an understanding of the invention, the invention will now be described more fully hereinafter with reference to the accompanying drawings. Preferred embodiments of the present invention are shown in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The convolutional neural network is one of representative algorithms for deep learning, has stable learning effect, does not need additional characteristic processing, has excellent performance in the fields of computer vision, medicine, health management and the like, and can be applied to the aspects of identification, judgment and the like of a map.
The three-point symmetrical difference energy operator is widely used in the field of bearing fault location, has a better enveloping diagram effect than the Teager energy operator widely used in the field of wave fault location at present, solves the problem of an end point effect frequently occurring in the Teager energy operator, and is an algorithm with more excellent performance.
Referring to fig. 1, the following embodiments of the method for detecting a traveling fault wave based on a symmetric differential energy operator and a neural network according to the present invention include:
s100: acquiring a three-phase voltage traveling wave signal to be detected for a fault through a plurality of sampling points, and performing decoupling transformation on the three-phase voltage traveling wave signal to obtain a line mode voltage component, wherein the line mode voltage component comprises an alpha line mode voltage component and a beta line mode voltage component;
s200: carrying out differential calculation on the alpha line mode voltage component or the beta line mode voltage component by using a three-point symmetrical differential energy operator to obtain an energy spectrogram corresponding to the fault to be detected;
s300: and inputting the energy spectrogram into a trained line fault diagnosis model to obtain fault information of the fault to be detected, wherein the line fault diagnosis model is obtained by training the energy spectrogram obtained by carrying out differential calculation on line mode voltage components of various line faults by using a three-point symmetric differential energy operator.
In step S100, acquiring a three-phase voltage traveling wave signal of an actual fault to be detected through a plurality of sampling points; in this embodiment, the collected voltage signal is composed of a plurality of sampling points, and in a preferred embodiment, when the sampling rate is 10MHZ, the time interval between every two adjacent sampling points is 0.1 μ s.
Because the three-phase voltage traveling wave signals in the power transmission line are not completely independent, a coupling relation exists between the three-phase voltage traveling wave signals, and the three-phase voltage traveling wave signals are required to be decoupled. In the embodiment, after the three-phase voltage traveling wave signals of the faults to be detected are collected, decoupling transformation is performed on the three-phase voltage traveling wave signals, in the preferred embodiment, the three-phase voltage traveling wave signals of the line faults are subjected to decoupling transformation by adopting Kerenbel transformation, and three independent modulus components of an alpha modulus, a beta modulus and a 0 modulus are obtained through decoupling, wherein the alpha modulus and the beta modulus belong to a line modulus voltage component, and the 0 modulus belongs to a zero modulus voltage component.
The process of the Kelenebel transformation is shown in formula (1):
wherein, UAFor A-phase voltage signal, UBFor B-phase voltage signals, UCIs a C-phase voltage signal; u shapeαIs a component of the line mode voltage, UβIs a beta line mode voltage component, U0A zero mode voltage component.
In step S200, a three-point symmetric difference energy operator is used to perform difference calculation on the α line mode voltage component or the β line mode voltage component, so as to obtain an energy spectrum corresponding to the fault to be detected.
Since the attenuation of the line mode voltage component is slower than that of the zero mode voltage component, in this embodiment, the line mode voltage component is selected for line fault analysis, and the α line mode voltage component or the β line mode voltage component may be selected for line fault analysis.
Specifically, a three-point symmetric difference energy operator can be used for performing difference calculation on the alpha line mode voltage component to obtain a corresponding DEO3S energy spectrogram, and a formula (2) and a formula (3) are used for calculating the DEO3S energy spectrogram corresponding to the fault to be detected:
F(s(n))＝s2(n)-s(n+1)s(n-1)； (2)
wherein ψ [ s (n)) ] represents an energy operator corresponding to the nth sampling point, F (s (n)) represents an operator introduced in the calculation process, s (n) represents a signal corresponding to the nth sampling point, s (n +1) represents a signal corresponding to the (n +1) th sampling point, and s (n-1) represents a signal corresponding to the (n-1) th sampling point.
It can be understood that the collected voltage signal is composed of a plurality of sampling points, and each sampling point corresponds to a sampling time; wherein, s (n) is a signal corresponding to the nth sampling point, and specifically: and when the nth sampling point is used for sampling, the voltage value at a certain moment is acquired.
It is worth to be noted that the formula (2) and the formula (3) are the prior art which is widely applied in the mechanical field and proposed in recent years, and the technical scheme applies the technique in the field of fault traveling wave detection. And (3) calculating the energy value corresponding to each sampling point according to the operator of the formula (2) and (3), and drawing according to the energy value corresponding to each sampling point to obtain a DEO3S energy spectrogram. The DEO3S energy spectrum is closely related to time and can be used to represent the energy fluctuations of the voltage signal over time.
Because the three-point symmetrical difference energy operator is subjected to smoothing processing on the basis of the traditional Teager energy operator, compared with the traditional Teager Energy Operator (TEO), the three-point symmetrical difference energy operator (DEO3S) has a better enveloping diagram effect, solves the problem of an end point effect which often occurs in the Teager energy operator, and is an algorithm with better performance.
In step S300, the energy spectrogram is input into a trained line fault diagnosis model to obtain fault information of the fault to be detected, where the line fault diagnosis model is obtained by training an energy spectrogram obtained by performing differential calculation on line mode voltage components of various line faults by using a three-point symmetric differential energy operator.
In this embodiment, the DEO3S energy spectrogram corresponding to the actual fault signal to be detected is input into the trained line fault diagnosis model for identification, so as to obtain a line fault diagnosis result, and specifically, the line branch where the fault to be detected is located and the fault type thereof can be obtained according to the fault diagnosis result.
In this embodiment, the DEO3S energy spectrogram can indicate the energy fluctuation condition of the voltage signal after the line fault, and the energy spectrum amplitudes corresponding to different fault types are different; and different fault line branches reflect fault traveling waves back and forth at the end points of each line branch, so that the time intervals corresponding to the peaks of the DEO3S energy spectrums are obviously different, and the branch where the line fault exists and the fault type can be determined according to the DEO3S energy spectrums corresponding to the line fault.
It is worth to be noted that after the DEO3S energy spectrogram corresponding to the fault to be detected is obtained, the DEO3S energy spectrogram corresponding to the fault to be detected is input into the trained line fault diagnosis model, and the line fault diagnosis model performs normalization processing on the DEO3S energy spectrogram corresponding to the fault to be detected, performs gray level conversion, and formats the DEO3S energy spectrogram according to the format of the training data set.
The line fault diagnosis model in this embodiment is a convolutional neural network model based on DEO3S and CNN, and the training process of the line fault diagnosis model includes:
simulating various line faults, extracting a plurality of three-phase voltage traveling wave signals when the faults occur, and decoupling and converting the three-phase voltage traveling wave signals to obtain corresponding alpha line mode voltage components and beta line mode voltage components;
carrying out differential calculation on each alpha mode voltage or each beta line mode voltage component by using a three-point symmetrical differential energy operator to obtain a corresponding energy spectrogram and form a training data set;
and training the line fault diagnosis model according to the training data set to obtain the trained line fault diagnosis model.
The Convolutional Neural Network (CNN) is one of the representative algorithms of deep learning, has stable learning effect and does not need additional feature processing, and can be used for identifying and processing the DEO3S energy spectrogram.
Convolutional neural networks are divided into convolutional layers, pooling layers, and fully-connected layers, where convolutional and pooling layers are used for feature extraction of images, and fully-connected layers are used for classification. In this embodiment, the line fault diagnosis model adopts a CNN convolutional neural network model, adopts a basic structure of two convolutional layers, two pooling layers, and two full-link layers, and on this basis, two batch normalization layers (BN layers) are added to perform normalization processing on an input image, thereby improving training speed and generalization capability of the model.
In this embodiment, the DEO3S energy spectrograms corresponding to various line faults are divided into training data sets, and the training data sets are input into the CNN convolutional neural network model for training, so as to obtain a trained CNN convolutional neural network model, which is a line fault diagnosis model based on DEO3S and CNN.
According to the fault traveling wave detection method based on the symmetrical differential energy operator and the neural network, a three-phase voltage traveling wave signal of a fault to be detected is obtained and subjected to decoupling transformation to obtain a line-mode voltage component, the line-mode voltage component is subjected to differential calculation by using the three-point symmetrical differential energy operator to obtain a corresponding DEO3S energy spectrogram, and the three-point symmetrical differential energy operator has a better envelope map effect compared with the traditional Teager energy operator; the DEO3S energy spectrogram is input into a trained line fault diagnosis model, so that the fault branch and the fault type of the line fault can be quickly judged, the problem of difficult downlink wave positioning under the condition of multiple branches can be well solved, and the reliability is good.
Referring to fig. 2, the following is an embodiment of the present invention:
a10 kv power distribution network multi-branch line model shown in figure 2 is established on PSCAD simulation software, a single-phase earth fault occurs at an F1 position 2.5km right of a C point when 0.1ms is set, the ground resistance is 5 omega, the line wave speed is 2.98285 multiplied by 105km/s, the sampling rate is 10MHz, and fault voltage traveling wave forms are detected at an M end (namely a transmitting end of a power distribution line) and at each branch point and the tail end of the line.
Collecting voltage traveling wave signals of each end of the line, decoupling and transforming the three-phase voltage traveling wave signals of the line fault by adopting Kerenbel transformation, and selecting alpha line mode voltage components for fault analysis, wherein the alpha line mode voltage components of the M end are shown in figure 3.
Then, a three-point symmetrical difference energy operator is adopted to perform difference calculation on the alpha line mode voltage component to obtain a DEO3S energy spectrogram shown in fig. 4, the abscissa of fig. 4 is the time interval of every two adjacent sampling points, the ordinate is the energy value corresponding to each sampling point, the energy value of each sampling point can be calculated according to the energy operator, and an image drawn by the energy value of each sampling point is an energy operator envelope.
And inputting the DEO3S energy spectrum diagram of FIG. 4 into a trained line fault diagnosis model based on DEO3S and CNN, so that the line branch where the current fault exists and the type of the fault can be determined.
The line fault diagnosis result is as follows: and judging that the fault branch is in the CE line branch, wherein the fault type is single-phase earth fault.
The fault traveling wave signals collected at the two ends of C, E are adopted to carry out DEO3S double-end positioning, and the positioning result is as follows: the fault distance C point is 2.489km, namely the positioning error is 11 m.
By using the fault traveling wave detection method based on the symmetric differential energy operator and the neural network, the line branch where the line fault is located and the fault type of the line fault can be quickly judged, the problem that the traveling wave is difficult to position under the condition of multiple branches is solved, after the fault branch and the fault type are judged, double-end positioning can be directly carried out by adopting a DEO3S energy spectrum, accurate positioning can also be carried out by adopting other double-end positioning algorithms, and the method has better reliability.
Referring to fig. 5, another embodiment of the method for detecting a traveling fault wave based on a symmetric differential energy operator and a neural network according to the present invention includes:
the method comprises the following steps: firstly, simulating various line faults and extracting voltage traveling wave signals during the faults, decoupling and converting the three-phase voltage traveling wave signals of the line faults by adopting Kernel-Bell conversion, and selecting an alpha line mode voltage component for fault analysis;
step two: differential calculation is carried out on the alpha line mode voltage component by adopting a three-point symmetrical differential energy operator to obtain a corresponding DEO3S energy spectrogram and divide a data set;
step three: inputting the DEO3S energy spectrogram data set into a convolutional neural network for training to obtain a trained line fault diagnosis model based on DEO3S and CNN;
step four: performing the first step and the second step on the three-phase voltage traveling wave signal of the actual fault to be detected to obtain a corresponding DEO3S energy spectrogram;
step five: inputting the DEO3S energy spectrogram corresponding to the actual fault to be detected into a trained line fault diagnosis model based on DEO3S and CNN, and judging the branch where the current fault is located and the fault type through the line fault diagnosis model.
It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above examples are only intended to illustrate the technical solution of the present invention, and not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. The fault traveling wave detection method based on the symmetric differential energy operator and the neural network is characterized by comprising the following steps of:
acquiring a three-phase voltage traveling wave signal of a fault to be detected through a plurality of sampling points, and performing decoupling transformation on the three-phase voltage traveling wave signal to obtain a line mode voltage component, wherein the line mode voltage component comprises an alpha line mode voltage component and a beta line mode voltage component;
carrying out differential calculation on the alpha line mode voltage component or the beta line mode voltage component by using a three-point symmetrical differential energy operator to obtain an energy spectrogram corresponding to the fault to be detected;
and inputting the energy spectrogram into a trained line fault diagnosis model to obtain fault information of the fault to be detected, wherein the line fault diagnosis model is obtained by training the energy spectrogram obtained by carrying out differential calculation on line mode voltage components of various line faults by using a three-point symmetric differential energy operator.
2. The method according to claim 1, wherein obtaining the fault information of the fault to be detected specifically comprises:
and obtaining the line branch where the fault to be detected is located and the fault type of the fault to be detected.
3. The method for detecting traveling wave fault based on symmetric differential energy operator and neural network of claim 2, wherein obtaining the fault information of the fault to be detected further comprises:
and performing double-end positioning by using fault traveling wave signals acquired at two ends of the line branch where the fault to be detected is located to obtain the accurate position of the fault to be detected.
4. The fault traveling wave detection method based on the symmetric differential energy operator and the neural network according to claim 1, wherein the step of performing decoupling transformation on the three-phase voltage traveling wave signal to obtain a line-mode voltage component specifically comprises:
and decoupling conversion is carried out on the three-phase voltage traveling wave signals through Kerenbel conversion to obtain line mode voltage components.
5. The fault traveling wave detection method based on the symmetric differential energy operator and the neural network according to claim 4, wherein the α -line mode voltage component is:
Uα＝(UA-UB)/3；
wherein, UαIs a component of the line mode voltage, UAFor A-phase voltage signals, UBIs a B-phase voltage signal.
6. The fault traveling wave detection method based on the symmetric differential energy operator and the neural network according to claim 5, wherein the β -line mode voltage component is:
Uβ＝(UA-UC)/3；
wherein, UβIs a beta line mode voltage component, UCIs a C-phase voltage signal.
7. The fault traveling wave detection method based on the symmetric differential energy operator and the neural network according to claim 6, wherein the differential calculation of the α -line mode voltage component or the β -line mode voltage component by using the three-point symmetric differential energy operator to obtain the energy spectrogram corresponding to the fault to be detected specifically comprises:
using formulas
Calculating energy operators corresponding to the sampling points, and obtaining energy spectrograms corresponding to the faults to be detected according to the energy operators corresponding to the sampling points;
wherein psi [ s (n)]The energy operator corresponding to the nth sampling point is shown, F(s) (n)) is an operator introduced in the calculation process, and F(s) (n) ═ s2(n) -s (n +1) s (n-1); and s (n) is a signal corresponding to the nth sampling point, s (n +1) is a signal corresponding to the (n +1) th sampling point, and s (n-1) is a signal corresponding to the (n-1) th sampling point.
8. The fault traveling wave detection method based on the symmetric differential energy operator and the neural network as claimed in claim 1, wherein the training process of the line fault diagnosis model comprises:
simulating various line faults, extracting a plurality of three-phase voltage traveling wave signals when the faults occur, and decoupling and converting the three-phase voltage traveling wave signals to obtain corresponding alpha line mode voltage components and beta line mode voltage components;
carrying out differential calculation on each alpha mode voltage or each beta line mode voltage component by using a three-point symmetrical differential energy operator to obtain a corresponding energy spectrogram and form a training data set;
and training the line fault diagnosis model according to the training data set to obtain the trained line fault diagnosis model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210429039.XA CN114779010A (en) | 2022-04-22 | 2022-04-22 | Fault traveling wave detection method based on symmetric differential energy operator and neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210429039.XA CN114779010A (en) | 2022-04-22 | 2022-04-22 | Fault traveling wave detection method based on symmetric differential energy operator and neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114779010A true CN114779010A (en) | 2022-07-22 |
Family
ID=82430863
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210429039.XA Pending CN114779010A (en) | 2022-04-22 | 2022-04-22 | Fault traveling wave detection method based on symmetric differential energy operator and neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114779010A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115963358A (en) * | 2023-03-13 | 2023-04-14 | 昆明理工大学 | Fault location method and system for hybrid three-terminal flexible direct-current transmission line |
-
2022
- 2022-04-22 CN CN202210429039.XA patent/CN114779010A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115963358A (en) * | 2023-03-13 | 2023-04-14 | 昆明理工大学 | Fault location method and system for hybrid three-terminal flexible direct-current transmission line |
| CN115963358B (en) * | 2023-03-13 | 2023-08-04 | 昆明理工大学 | Mixed three-terminal flexible direct current transmission line fault location method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104569694B (en) | Electric signal feature extraction and recognition system oriented to aircraft flying process | |
| CN112952828A (en) | User station area analysis method for low-voltage distribution network | |
| CN107942214A (en) | A kind of feature extracting method of transformer partial discharge signal, device | |
| CN111898644A (en) | Intelligent identification method for health state of aerospace liquid engine under fault-free sample | |
| CN201083800Y (en) | Transformer substation insulated live-wire detector based on dummy instrument technology | |
| CN111426905B (en) | Power distribution network common bus transformation relation abnormity diagnosis method, device and system | |
| CN114779010A (en) | Fault traveling wave detection method based on symmetric differential energy operator and neural network | |
| CN115876473A (en) | Bearing fault diagnosis method based on PWVD and DenseNet | |
| CN216848010U (en) | Cable partial discharge online monitoring device for edge calculation | |
| CN115481657A (en) | Wind generating set communication slip ring fault diagnosis method based on electric signals | |
| CN113027658B (en) | Real-time state evaluation method for water turbine runner and application thereof | |
| CN114354184A (en) | Deep learning-based method and device for establishing health early warning model of main shaft of large-scale rotating equipment | |
| CN117056865B (en) | Method and device for diagnosing operation faults of machine pump equipment based on feature fusion | |
| Wang et al. | An improved generative adversarial network for fault diagnosis of rotating machine in nuclear power plant | |
| CN113191247A (en) | GIS equipment mechanical fault diagnosis method and system | |
| CN116520095A (en) | Fault location method, system and computer readable storage medium | |
| CN116911161A (en) | Data-enhanced deep learning transient voltage stability evaluation method | |
| CN116223009A (en) | Fault diagnosis method, system, device and medium for main circulating pump in converter valve | |
| CN110765908A (en) | Cascade type cancer cell detection system based on deep learning | |
| CN116432077A (en) | Intelligent station secondary system fault positioning method based on optimized BP neural network | |
| CN113408182B (en) | Tool life full-cycle wear diagnosis method, device and storage medium based on multiple wavelet optimal features and neural network | |
| CN110927511B (en) | Power grid fault diagnosis system and method using fault waveform | |
| CN114062995A (en) | Mutual inductor fault diagnosis method, equipment and medium based on electric quantity multi-feature fusion | |
| CN114548153B (en) | Planetary gear box fault diagnosis method based on residual error-capsule network | |
| CN117171544B (en) | Motor vibration fault diagnosis method based on multichannel fusion convolutional neural network |
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 |