CN112881879A - High-voltage cable terminal partial discharge mode identification method, device and equipment - Google Patents
High-voltage cable terminal partial discharge mode identification method, device and equipment Download PDFInfo
- Publication number
- CN112881879A CN112881879A CN202110422803.6A CN202110422803A CN112881879A CN 112881879 A CN112881879 A CN 112881879A CN 202110422803 A CN202110422803 A CN 202110422803A CN 112881879 A CN112881879 A CN 112881879A
- Authority
- CN
- China
- Prior art keywords
- partial discharge
- signal
- mode
- cable terminal
- voltage cable
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 239000011159 matrix material Substances 0.000 claims abstract description 41
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 31
- 238000003909 pattern recognition Methods 0.000 claims abstract description 16
- 238000000691 measurement method Methods 0.000 claims abstract description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 9
- 230000003750 conditioning effect Effects 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 7
- 238000012567 pattern recognition method Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 abstract description 11
- 238000009413 insulation Methods 0.000 abstract description 5
- 238000009434 installation Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 35
- 238000001514 detection method Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 238000012706 support-vector machine Methods 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000005684 electric field Effects 0.000 description 2
- 238000010291 electrical method Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000001143 conditioned effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005316 response function Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
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
- G01R31/1263—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 solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation
- G01R31/1272—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 solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation of cable, line or wire insulation, e.g. using partial discharge measurements
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention discloses a method, a device and equipment for identifying a partial discharge mode of a high-voltage cable terminal, and belongs to the technical field of insulation monitoring of high-voltage power equipment. The method comprises the steps of acquiring a partial discharge signal of a cable terminal by using a high-frequency measurement method; performing modal decomposition on the discharge signal to obtain an effective mode of the partial discharge signal; obtaining a feature matrix according to the effective mode; inputting the characteristic matrix into a pattern recognition model, and outputting the type of a partial discharge pattern; the invention has the advantages of low cost, convenient installation, accurate acquisition of partial discharge signals and high accuracy of pattern recognition.
Description
The technical field is as follows:
the invention belongs to the technical field of insulation monitoring of high-voltage power equipment, and particularly relates to a method, a device and equipment for identifying a partial discharge mode of a high-voltage cable terminal.
Background art:
along with the increase of the scale of a distribution network power supply system, the ring main unit gradually occupies an important position in a power system, and the safe and stable operation of the ring main unit has important significance on the safety of a power grid. The insulation defect or the degradation and other problems of the core cable terminal in the ring main unit directly endanger the normal operation of the equipment in the ring main unit and directly influence the power utilization safety of a power grid. Partial discharge is an important sign and expression form of insulation degradation of a high-voltage cable terminal, and timely and accurate monitoring of the partial discharge of the ring main unit becomes a key link for maintaining safe and stable operation of a power grid.
The generation of partial discharge is often accompanied by a series of physical phenomena such as electricity, light, sound, heat, etc., and therefore, research on-line monitoring of partial discharge is based on detection of these electric quantities or non-electric quantities. These physical quantities are captured by sensors and characteristics of the monitoring signals are extracted to assess the extent of discharge at the cable termination. Partial discharge online monitoring means are generally divided into two categories, namely non-electrical measurement methods and electrical measurement methods. The non-electrical methods include ultrasonic methods, optical detection methods, thermal monitoring methods and the like, and the electrical methods include high-frequency detection methods, transient voltage-to-ground detection methods, ultrahigh frequency methods, pulse current methods and the like. The high-frequency method is adopted to measure the partial discharge in the ring main unit, the device is simple to install, and the original equipment in the ring main unit cannot be damaged. The existing high-frequency method adopts a high-speed acquisition card for partial discharge detection, and is difficult to realize online monitoring application in terms of complexity and cost. Therefore, it is necessary to invent a low-cost detection circuit capable of real-time online monitoring, which is convenient for popularization and application.
The partial discharge signal type identification is very important for fault processing, and the feature extraction is an important step for the pattern identification of partial discharge. At present, a feature extraction method based on a Phase Resolved Partial Discharge (PRPD) statistical spectrogram is generally adopted in a feature extraction method, such as a statistical feature analysis method based on a two-dimensional spectrogram, a fractal feature analysis method, a fractal feature of a scattered point set, and the like, and the feature quantity obtained by the method has a high dimension, so that information redundancy occurs, problems such as overfitting easily occur, and the recognition accuracy is affected.
The invention content is as follows:
in order to solve the above problems, the present application provides a method, an apparatus, and a device for identifying a local discharge mode of a high voltage cable terminal, so as to implement accurate identification of a local discharge mode of a high voltage cable terminal, and reduce maintenance cost and time cost of the cable terminal.
The invention provides a method for identifying a partial discharge mode of a high-voltage cable terminal in a first aspect, which comprises the following steps:
s1, acquiring a partial discharge signal of the cable terminal by using a high-frequency measurement method;
s2, performing modal decomposition on the discharge signal to obtain an effective mode of the partial discharge signal;
s3, obtaining a feature matrix according to the effective modes;
and S4, inputting the characteristic matrix into the pattern recognition model, and outputting the type of the partial discharge pattern.
Further, the discharge mode includes a pin plate discharge mode, a creeping discharge mode, and an internal discharge mode.
Further, step S2 includes:
performing modal decomposition by adopting a variational modal decomposition algorithm;
and screening out effective modes according to the frequency.
Further, step S3 includes:
adopting a multi-scale permutation entropy algorithm to operate the screened effective modes to obtain a multi-scale permutation entropy matrix of the effective modes;
and reducing the dimension of the multi-scale permutation entropy matrix to obtain a final characteristic matrix of the signal.
The second aspect of the present invention provides a device for identifying a partial discharge pattern of a high-voltage cable terminal, comprising:
a signal acquisition unit for acquiring a partial discharge signal of the cable terminal by using a high-frequency measurement method;
the modal acquisition unit is used for carrying out modal decomposition on the discharge signal to obtain an effective modal of the partial discharge signal;
the characteristic extraction unit is used for obtaining a characteristic matrix according to the effective mode;
and the identification unit is used for inputting the characteristic matrix into a pattern identification model and outputting the type of the partial discharge pattern.
Further, the modality acquisition unit includes:
the modal decomposition module is used for carrying out modal decomposition by adopting a variational modal decomposition algorithm;
and the mode screening module is used for screening out effective modes according to the frequency.
Further, the feature extraction unit includes:
the operation module is used for performing operation on the screened effective modes by adopting a multi-scale permutation entropy algorithm to obtain a multi-scale permutation entropy matrix of the effective modes;
and the dimension reduction module is used for reducing the dimension of the multi-scale arrangement entropy matrix to obtain a final characteristic matrix of the signal.
A third aspect of the present invention provides a high-voltage cable terminal partial discharge pattern recognition apparatus, including:
the signal conditioning circuit is used for converting the partial discharge signal of the cable terminal into a format available signal;
a processor configured to execute a high voltage cable termination partial discharge pattern recognition method according to the first aspect of the present invention via execution of the executable instructions;
a memory to store executable instructions of the processor.
Furthermore, the signal conditioning circuit comprises an amplifying circuit, a detection circuit, a follower circuit integrating circuit and an inverting circuit.
Compared with the prior art, the invention has the following effects:
1. when the conditioned signal is subjected to feature extraction, modal decomposition and dimension reduction processing are carried out, the dimension of a feature matrix is reduced, the redundancy of information is reduced, the local time-varying feature of the dischargeable signal is subjected to self-adaptive time-frequency decomposition cable terminal partial discharge mode identification, and the identification accuracy is improved.
2. The high-voltage cable terminal partial discharge monitoring method has the advantages that the discharge signal of the high-voltage terminal is obtained through the high-frequency detection method, the identification device and the identification instrument are convenient to install and collect signals, the relevant information of the partial discharge of the high-voltage cable terminal can be provided, the type of the discharge mode is analyzed, the maintenance is convenient, the maintenance cost and the time cost of the high-voltage cable terminal are greatly reduced, the problem of online partial discharge testing in certain environments is solved, and the blank of the partial discharge monitoring of the high-voltage cable terminal in China is filled.
Description of the drawings:
for ease of illustration, the invention is described in detail by the following detailed description and the accompanying drawings.
Fig. 1 is a flowchart of a partial discharge pattern recognition method for a high-voltage cable terminal according to an embodiment of the present invention;
fig. 2 is a block diagram of a partial discharge pattern recognition apparatus for a high-voltage cable terminal according to an embodiment of the present invention;
FIG. 3 is a circuit schematic of a signal conditioning circuit according to an embodiment of the present invention;
fig. 4 is a metamorphic mode exploded view of pin plate discharge in an example.
FIG. 5 is a morphotropically exploded view of creeping discharge in an example.
Fig. 6 is a morphotropic exploded view of the internal discharge of the example.
Fig. 7 is a multi-scale arrangement entropy diagram of pin plate discharge in an example.
FIG. 8 is a multi-scale permutation entropy diagram of the creeping discharge in an example.
FIG. 9 is a multi-scale arranged entropy diagram of internal discharges in an example.
Fig. 10 is a graph of the support vector machine identification results for the three discharge types in the example.
Fig. 11 is a graph of the neural network identification results of three discharge types in the example.
The specific implementation mode is as follows:
in order that the objects, aspects and advantages of the invention will become more apparent, the invention will be described by way of example only, and in connection with the accompanying drawings. It is to be understood that such description is merely illustrative and not intended to limit the scope of the present invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
As shown in fig. 1, a specific embodiment of the present invention provides a method for identifying a partial discharge mode of a high-voltage cable terminal, including the following steps:
s1, acquiring a partial discharge signal of the cable terminal by using a high-frequency measurement method;
generally, there are three types of discharge modes for cable terminations:
in the needle plate discharge mode, the defects of damage of an inner semi-conducting layer of a cable terminal, compression deformation of a connecting pipe, damage of a metal shield, burrs of a wire core and the like cause extremely uneven electric field distribution, and the needle plate discharge is caused;
in the creeping discharge mode, the fillet surfaces of the cable terminal sleeve and the stress cone are not smooth due to poor manufacturing process of the notches of the semi-conducting layer, so that creeping discharge is caused;
internal discharge mode, the presence of air gaps and impurities in the cable termination insulation causes electric field concentration, resulting in internal discharge.
In the three modes, the obtained corresponding partial discharge signals are a needle plate discharge signal, a creeping discharge signal and an internal discharge signal respectively.
S2, performing modal decomposition on the discharge signal to obtain an effective mode of the partial discharge signal;
s21, performing modal decomposition by adopting a variational modal decomposition algorithm;
the variation modal decomposition algorithm comprises the following steps:
where k is the number of modal components (k ═ 1,2,3, …), and the variable array { u ═ uk}、{ωkRespectively representing the k-th modal component and the corresponding center frequency of the partial discharge current signal; partial discharge signal f (t) is decomposed into k modal components uk(t), δ (t) is an impulse response function; fig. 6 to 6 in this embodiment are 5 typical examples of decomposition under three discharge conditions, respectively, where fig. 4a is a time domain diagram of an original signal of a creeping discharge signal, fig. 4b is a frequency spectrum diagram of the original signal of the creeping discharge signal, fig. 4c is a time domain diagram of a mode 1, fig. 4d is a frequency domain diagram of the mode 1, fig. 4e is a time domain diagram of a mode 2, fig. 4f is a frequency domain diagram of the mode 2, fig. 4g is a time domain diagram of the mode 3, fig. 4h is a frequency domain diagram of the mode 3, fig. 4i is a time domain diagram of the mode 4, fig. 4j is a frequency domain diagram of the mode 4, fig. 4k is a time domain diagram of the mode 5, and fig. 4l is a frequency domain diagram of the mode 5; fig. 5a is a time domain diagram of an original signal of an internal discharge signal, fig. 5b is a frequency spectrum diagram of an original signal of an internal discharge signal, fig. 5c is a time domain diagram of a mode 1, fig. 5d is a frequency domain diagram of a mode 1, fig. 5e is a time domain diagram of a mode 2, fig. 5f is a frequency domain diagram of a mode 2, fig. 5g is a time domain diagram of a mode 3, fig. 5h is a frequency domain diagram of a mode 3, fig. 5i is a time domain diagram of a mode 4, fig. 5j is a frequency domain diagram of a mode 4, fig. 5k is a time domain diagram of a mode 5, and fig. 5l is a frequency domain diagram of a mode 5; FIG. 6a is a time domain diagram of the original signal of the pin plate discharge signal, FIG. 6b is a spectral diagram of the original signal of the pin plate discharge signal, FIG. 6c is a time domain diagram of mode 1, FIG. 6d is a frequency domain diagram of mode 1, FIG. 6e is a time domain diagram of mode 2, FIG. 6f is a frequency domain diagram of mode 2, FIG. 6g is a time domain diagram of mode 3, and FIG. 6h is a modeThe frequency domain plot of state 3, fig. 6i is the time domain plot of state 4, fig. 6j is the frequency domain plot of state 4, fig. 6k is the time domain plot of state 5, and fig. 6l is the frequency domain plot of state 5; the decomposition of the remaining modes can be obtained by analogy with the above method, which is not exemplified in detail in this application.
S22, screening out effective modes according to the frequencies, where the effective modes described in this embodiment refer to decomposing the original partial discharge signal into k mode components according to the mode decomposition algorithm of step S21. In this embodiment, the power frequency of the original partial discharge signal f (t) is subjected to frequency reduction processing by the integrating circuit to reduce the requirement on the sampling frequency of the hardware, the frequency reduction processing step is performed by the integrating circuit, the power frequency of the signal passing through the integrating circuit becomes a fixed value, when the frequency of the k-th modal signal after decomposition is different from the frequency of the amplitude point of the original signal f (t) of the partial discharge signal, the number of effective decomposition modalities is k-1, and then according to the decomposed modalities obtained by the decomposition algorithm in step S21, the maximum modal component amplitude is taken as the effective modality of the corresponding frequency in the amplitudes of the adjacent extreme point frequencies, so that the effective modality (the maximum corresponding amplitude) and the corresponding frequency thereof are determined in the range of k-1 effective modalities. The integrating circuit described in this embodiment may adopt the integrating circuit in fig. 2, and the partial discharge signal is down-converted by the integrating circuit.
S3, obtaining a feature matrix according to the effective modes;
s31, performing multi-scale permutation entropy algorithm operation on the screened effective modes to obtain a multi-scale permutation entropy matrix of the effective modes;
wherein u isiFor the ith modal component, i is the ith component of the reconstruction arrangement, i ═ 1, 2.., N- (m-1) τ, m is the embedding dimension, τ is the delay factor, s is the scale factor parameter;
the scale factor chosen for this embodiment is 20, and each signal results in a 3 × 20 feature matrix.
And S32, reducing the dimension of the multi-scale arrangement entropy matrix to obtain a final characteristic matrix of the signal.
In order to reduce the dimensionality of the calculation of pattern recognition, the embodiment adopts a principal component analysis method, which specifically includes:
and (3) solving a covariance matrix from the characteristic matrix of 3 multiplied by 20, arranging the covariance matrix into a matrix from top to bottom according to the value of the covariance matrix, and taking the first 10 groups to form the matrix, namely forming dimension-reduced data, so that dimension reduction processing is carried out on the multi-scale arrangement entropy matrix, and 10 groups of scale factors with higher total contribution are arranged and selected.
And S4, inputting the characteristic matrix into a pattern recognition model, and outputting the type of a partial discharge mode, wherein the type of the discharge mode is a needle plate discharge mode, a creeping discharge mode and an internal discharge mode.
The pattern recognition algorithm described in this embodiment includes a support vector machine algorithm.
In order to verify the discharge pattern recognition effect of the present embodiment, in a specific embodiment, the 600 sets of sample data obtained in steps S1-S3 are divided into a training set and a test set, where the training set of the support vector machine is 480 sets and the test set is 120 sets; the final result is shown in fig. 10, where fig. 10 is the support vector machine recognition result, and it can be seen that the support vector machine algorithm average recognition rate is 98.3%, where the pin plate discharge recognition rate is 96.7%, the creeping discharge recognition rate is 100%, and the internal discharge recognition rate is 100%.
In a specific implementation process, the pattern recognition method may not be limited to the support vector machine learning method, and other machine learning methods may be adopted as required, for example, in a specific embodiment, the pattern recognition is performed by using a neural network algorithm, the neural network training set is 420 groups, the validation set is 90 groups, and the test set is 90 groups, as shown in the neural network recognition result of fig. 11, the average recognition rate of the neural network algorithm is 96.7%, wherein the needle plate discharge recognition rate is 100%, the creeping discharge recognition rate is 96.8%, and the internal discharge recognition rate is 94.1%.
In an embodiment, there is provided a partial discharge pattern recognition apparatus for a high voltage cable terminal, as shown in fig. 2, including:
a signal acquisition unit 100 for acquiring a partial discharge signal of the cable terminal by using a high frequency measurement method;
the mode obtaining unit 200 is configured to perform mode decomposition on the discharge signal to obtain an effective mode of the partial discharge signal;
a feature extraction unit 300, configured to obtain a feature matrix according to the effective mode;
the recognition unit 400 is configured to input the feature matrix into a pattern recognition model, and output a type of the partial discharge pattern.
The modality acquisition unit includes:
the modal decomposition module is used for carrying out modal decomposition by adopting a variational modal decomposition algorithm;
and the mode screening module is used for screening out effective modes according to the frequency.
The feature extraction unit includes:
the operation module is used for performing operation on the screened effective modes by adopting a multi-scale permutation entropy algorithm to obtain a multi-scale permutation entropy matrix of the effective modes;
and the dimension reduction module is used for reducing the dimension of the multi-scale arrangement entropy matrix to obtain a final characteristic matrix of the signal.
The signal obtaining unit 100, the modality obtaining unit 200, the feature extracting unit 300, and the identifying unit 400 are respectively configured to implement steps S1, S2, S3, and S4 in the method for identifying a partial discharge pattern of a high-voltage cable terminal, so that the detailed description thereof may refer to the description of the above embodiments and will not be repeated.
The signal acquiring unit 100, the modality acquiring unit 200, the feature extracting unit 300, and the identifying unit 400 may be loaded in each module in the form of software, or may be integrated in the apparatus in a manner of combining software and hardware.
A third aspect of the present invention provides a high-voltage cable terminal partial discharge pattern recognition apparatus, including:
the signal conditioning circuit is used for conditioning the discharge signal acquired by the high-frequency sensor according to the differential characteristic of the high-frequency current sensor so as to meet the signal acquisition work of AD;
as shown in fig. 3, the signal conditioning circuit includes:
the amplifying circuit is used for amplifying the acquired signal for the first time by the operational amplifier U1, so that the back-end processing is facilitated;
a detector circuit for filtering the signal at the negative half-axis and retaining the positive half-wave by a detector diode D2
The follower circuit is a follower formed by an operational amplifier U4, has the characteristic of large impedance and plays a role in circuit isolation;
an integrating circuit, which is used for integrating the signal by an operational amplifier U3 and extracting the envelope curve of the signal;
the inverting circuit is inverted by an operational amplifier U2, and because the integrated waveforms are all positioned in a negative half shaft, the inverter enables the signals to return to a positive half shaft;
a processor configured to execute a high voltage cable termination partial discharge pattern recognition method according to the first aspect of the present invention via execution of the executable instructions;
a memory to store executable instructions of the processor.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. A method for identifying a partial discharge mode of a high-voltage cable terminal is characterized by comprising the following steps:
s1, acquiring a partial discharge signal of the cable terminal by using a high-frequency measurement method;
s2, performing modal decomposition on the discharge signal to obtain an effective mode of the partial discharge signal;
s3, obtaining a feature matrix according to the effective modes;
and S4, inputting the characteristic matrix into the pattern recognition model, and outputting the type of the partial discharge pattern.
2. The method of claim 1, wherein the discharge modes include a pin plate discharge mode, a creeping discharge mode and an internal discharge mode.
3. The method for identifying the partial discharge pattern of the high-voltage cable terminal as claimed in claim 1, wherein the step S2 includes:
performing modal decomposition by adopting a variational modal decomposition algorithm;
and screening out effective modes according to the frequency.
4. The method for identifying the partial discharge pattern of the high-voltage cable terminal as claimed in claim 1, wherein the step S3 includes:
adopting a multi-scale permutation entropy algorithm to operate the screened effective modes to obtain a multi-scale permutation entropy matrix of the effective modes;
and reducing the dimension of the multi-scale permutation entropy matrix to obtain a final characteristic matrix of the signal.
5. A high voltage cable termination partial discharge pattern recognition apparatus, comprising:
a signal acquisition unit for acquiring a partial discharge signal of the cable terminal by using a high-frequency measurement method;
the modal acquisition unit is used for carrying out modal decomposition on the discharge signal to obtain an effective modal of the partial discharge signal;
the characteristic extraction unit is used for obtaining a characteristic matrix according to the effective mode;
and the identification unit is used for inputting the characteristic matrix into a pattern identification model and outputting the type of the partial discharge pattern.
6. The apparatus for identifying partial discharge patterns of a high voltage cable termination according to claim 5, wherein the mode obtaining unit comprises:
the modal decomposition module is used for carrying out modal decomposition by adopting a variational modal decomposition algorithm;
and the mode screening module is used for screening out effective modes according to the frequency.
7. The apparatus of claim 5, wherein the feature extraction unit comprises:
the operation module is used for performing operation on the screened effective modes by adopting a multi-scale permutation entropy algorithm to obtain a multi-scale permutation entropy matrix of the effective modes;
and the dimension reduction module is used for reducing the dimension of the multi-scale arrangement entropy matrix to obtain a final characteristic matrix of the signal.
8. A high voltage cable termination partial discharge pattern recognition apparatus, comprising:
the signal conditioning circuit is used for converting the partial discharge signal of the cable terminal into a format available signal;
a processor configured to execute a high voltage cable termination partial discharge pattern recognition method of any one of claims 1 to 4 via execution of the executable instructions;
a memory to store executable instructions of the processor.
9. The apparatus of claim 8, wherein the signal conditioning circuit comprises an amplifier circuit, a detector circuit, a follower circuit, an integrator circuit, and an inverter circuit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110422803.6A CN112881879A (en) | 2021-04-16 | 2021-04-16 | High-voltage cable terminal partial discharge mode identification method, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110422803.6A CN112881879A (en) | 2021-04-16 | 2021-04-16 | High-voltage cable terminal partial discharge mode identification method, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112881879A true CN112881879A (en) | 2021-06-01 |
Family
ID=76040177
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110422803.6A Pending CN112881879A (en) | 2021-04-16 | 2021-04-16 | High-voltage cable terminal partial discharge mode identification method, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112881879A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114076877A (en) * | 2021-11-19 | 2022-02-22 | 国网辽宁省电力有限公司鞍山供电公司 | High-voltage insulation state analysis method and device based on electromagnetic field big data |
| CN114754857A (en) * | 2022-06-14 | 2022-07-15 | 之江实验室 | Two-section type optical fiber sensing underwater acoustic signal compensation method and device |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1169537A (en) * | 1996-06-26 | 1998-01-07 | 甘肃工业大学高新技术实业总公司 | Electric quantity computer-controlled monitoring instrument |
| CN102684744A (en) * | 2012-05-18 | 2012-09-19 | 苏州东奇信息科技有限公司 | Power supply self-synchronizing phase inversion modulator-demodulator for power line communication |
| CN105334436A (en) * | 2015-10-30 | 2016-02-17 | 山东电力研究院 | Cross-linked cable partial discharge mode identification method based on SOM-BP combined neural network |
| CN105717422A (en) * | 2015-12-04 | 2016-06-29 | 国家电网公司 | High-voltage power equipment partial discharge feature extraction method and apparatus |
| CN106370986A (en) * | 2016-11-03 | 2017-02-01 | 合肥华义电气科技有限公司 | Switch cabinet partial discharge monitoring method |
| CN106526434A (en) * | 2016-10-11 | 2017-03-22 | 国网上海市电力公司 | Partial discharge mode identifying method and device |
| CN108983058A (en) * | 2018-08-29 | 2018-12-11 | 三峡大学 | Partial discharge of transformer ultrahigh-frequency signal denoising method based on improved variation mode and singular value decomposition |
| CN109829412A (en) * | 2019-01-24 | 2019-05-31 | 三峡大学 | The Partial Discharge Pattern Recognition Method of fractal characteristic is decomposed based on dynamic mode |
| CN111426342A (en) * | 2020-03-06 | 2020-07-17 | 国网江西省电力有限公司电力科学研究院 | State diagnosis device and method for high-voltage ring main unit |
| CN111476093A (en) * | 2020-03-06 | 2020-07-31 | 国网江西省电力有限公司电力科学研究院 | Cable terminal partial discharge mode identification method and system |
| CN112285494A (en) * | 2020-09-16 | 2021-01-29 | 北京博研中能科技有限公司 | Power cable partial discharge mode recognition analysis system |
| CN112633333A (en) * | 2020-12-11 | 2021-04-09 | 广州致新电力科技有限公司 | Method for identifying partial discharge defects |
-
2021
- 2021-04-16 CN CN202110422803.6A patent/CN112881879A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1169537A (en) * | 1996-06-26 | 1998-01-07 | 甘肃工业大学高新技术实业总公司 | Electric quantity computer-controlled monitoring instrument |
| CN102684744A (en) * | 2012-05-18 | 2012-09-19 | 苏州东奇信息科技有限公司 | Power supply self-synchronizing phase inversion modulator-demodulator for power line communication |
| CN105334436A (en) * | 2015-10-30 | 2016-02-17 | 山东电力研究院 | Cross-linked cable partial discharge mode identification method based on SOM-BP combined neural network |
| CN105717422A (en) * | 2015-12-04 | 2016-06-29 | 国家电网公司 | High-voltage power equipment partial discharge feature extraction method and apparatus |
| CN106526434A (en) * | 2016-10-11 | 2017-03-22 | 国网上海市电力公司 | Partial discharge mode identifying method and device |
| CN106370986A (en) * | 2016-11-03 | 2017-02-01 | 合肥华义电气科技有限公司 | Switch cabinet partial discharge monitoring method |
| CN108983058A (en) * | 2018-08-29 | 2018-12-11 | 三峡大学 | Partial discharge of transformer ultrahigh-frequency signal denoising method based on improved variation mode and singular value decomposition |
| CN109829412A (en) * | 2019-01-24 | 2019-05-31 | 三峡大学 | The Partial Discharge Pattern Recognition Method of fractal characteristic is decomposed based on dynamic mode |
| CN111426342A (en) * | 2020-03-06 | 2020-07-17 | 国网江西省电力有限公司电力科学研究院 | State diagnosis device and method for high-voltage ring main unit |
| CN111476093A (en) * | 2020-03-06 | 2020-07-31 | 国网江西省电力有限公司电力科学研究院 | Cable terminal partial discharge mode identification method and system |
| CN112285494A (en) * | 2020-09-16 | 2021-01-29 | 北京博研中能科技有限公司 | Power cable partial discharge mode recognition analysis system |
| CN112633333A (en) * | 2020-12-11 | 2021-04-09 | 广州致新电力科技有限公司 | Method for identifying partial discharge defects |
Non-Patent Citations (2)
| Title |
|---|
| 周利军 等: "《高压电缆现场局部放电检测百问百答及应用案例》", 上海科学技术出版社, pages: 10 * |
| 张蒙，朱永利，张宁，张媛媛: "一种基于变分模态分解和多尺度排列熵的变压器局部放电信号特征提取", 华北电力大学学报, vol. 43, no. 6, pages 31 - 36 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114076877A (en) * | 2021-11-19 | 2022-02-22 | 国网辽宁省电力有限公司鞍山供电公司 | High-voltage insulation state analysis method and device based on electromagnetic field big data |
| CN114076877B (en) * | 2021-11-19 | 2023-12-19 | 国网辽宁省电力有限公司鞍山供电公司 | High-voltage insulation state analysis method and device based on electromagnetic field big data |
| CN114754857A (en) * | 2022-06-14 | 2022-07-15 | 之江实验室 | Two-section type optical fiber sensing underwater acoustic signal compensation method and device |
| CN114754857B (en) * | 2022-06-14 | 2022-08-23 | 之江实验室 | Two-section type optical fiber sensing underwater acoustic signal compensation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | ArcNet: Series AC arc fault detection based on raw current and convolutional neural network | |
| Peng et al. | A convolutional neural network-based deep learning methodology for recognition of partial discharge patterns from high-voltage cables | |
| Lee et al. | New fault diagnosis of circuit breakers | |
| Yang et al. | A new vibration analysis approach for detecting mechanical anomalies on power circuit breakers | |
| CN109633368A (en) | The method of duration power quality disturbances containing distributed power distribution network based on VMD and DFA | |
| CN106443316A (en) | Power transformer winding deformation state multi-information detection method and device | |
| CN104198898A (en) | Local discharge development process diagnosis method based on pulse-train analysis | |
| CN110728257B (en) | Transformer winding fault monitoring method based on vibration gray level image | |
| CN112881879A (en) | High-voltage cable terminal partial discharge mode identification method, device and equipment | |
| CN110991481B (en) | High-voltage shunt reactor internal loosening fault diagnosis method based on cross wavelet transformation | |
| CN112816838B (en) | GIS equipment defect diagnosis device and method based on FFT, VMD and LS-SVM | |
| Koley et al. | Wavelet-aided SVM tool for impulse fault identification in transformers | |
| CN110632484A (en) | ELM-based GIS partial discharge defect diagnosis and classification system and method | |
| Wang et al. | Cable incipient fault identification using restricted Boltzmann machine and stacked autoencoder | |
| CN117748507A (en) | Distribution network harmonic access uncertainty assessment method based on Gaussian regression model | |
| CN112132226A (en) | Method for diagnosing defects of +/-1100 kV composite insulator | |
| Yan et al. | Mutual Information‐Assisted Wavelet Function Selection for Enhanced Rolling Bearing Fault Diagnosis | |
| Kumar et al. | Classification of PD faults using features extraction and K-means clustering techniques | |
| Chang et al. | Partial discharge pattern recognition for underground cable joints using convolutional neural network | |
| Quizhpi-Cuesta et al. | Classification of partial discharge in pin type insulators using fingerprints and neural networks | |
| CN115130516A (en) | GIS equipment state identification method and device based on spectrum power spectrum entropy | |
| CN104777446B (en) | A kind of capacitive current transformer on-line fault diagnosis device and method | |
| CN114609483A (en) | Hilbert transform-based GIS partial discharge signal feature extraction method | |
| CN109917245B (en) | Ultrasonic detection partial discharge signal mode identification method considering phase difference | |
| Liu et al. | A new identification method of high voltage circuit breaker mechanical fault based on combined analysis of time‐reference‐distance and shape entropy algorithms |
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 |