CN113671363A - High-voltage circuit breaker state identification system and method - Google Patents
High-voltage circuit breaker state identification system and method Download PDFInfo
- Publication number
- CN113671363A CN113671363A CN202110928828.3A CN202110928828A CN113671363A CN 113671363 A CN113671363 A CN 113671363A CN 202110928828 A CN202110928828 A CN 202110928828A CN 113671363 A CN113671363 A CN 113671363A
- Authority
- CN
- China
- Prior art keywords
- circuit breaker
- sound
- voltage circuit
- sensor
- data acquisition
- 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 28
- 230000007246 mechanism Effects 0.000 claims abstract description 14
- 238000003745 diagnosis Methods 0.000 claims abstract description 6
- 238000004891 communication Methods 0.000 claims abstract description 3
- 230000005236 sound signal Effects 0.000 claims description 12
- 238000001228 spectrum Methods 0.000 claims description 9
- 238000007637 random forest analysis Methods 0.000 claims description 8
- 230000009471 action Effects 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 230000035945 sensitivity Effects 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 230000008602 contraction Effects 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 230000003595 spectral effect Effects 0.000 claims description 2
- 238000006731 degradation reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000006467 substitution reaction 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
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Arc-Extinguishing Devices That Are Switches (AREA)
Abstract
The invention discloses a high-voltage circuit breaker state identification system and method, belonging to the technical field of electrical equipment fault diagnosis. The device comprises a power module, a vibration sensor, a sound sensor, a current sensor, a high-speed camera, a data acquisition device, an industrial personal computer and a shielding cable; the power supply module provides power for the sound sensor, the current sensor and the data acquisition device, each sensor transmits the measured vibration, sound and current information to the data acquisition device through a shielded cable, and the data acquisition device transmits the information to the industrial personal computer in a WIFI wireless communication mode; the high-speed camera directly transmits image information of the high-voltage circuit breaker spring operating mechanism to the industrial personal computer through the shielded cable. The method can effectively overcome the limitation of a single signal source, more comprehensively depict the operation state of the circuit breaker, and has important engineering application value for improving the pertinence and the accuracy of the state identification and the operation trend prediction of the circuit breaker.
Description
Technical Field
The invention relates to the technical field of electrical equipment fault diagnosis, in particular to a high-voltage circuit breaker state identification system and method.
Background
High-voltage circuit breakers are one of the most important types of electrical equipment in electrical power systems, and play a role in protection and control in the system. The traditional periodic maintenance test of the circuit breaker is time-consuming and high in cost, and new defect hidden dangers are easily caused. Under the big background of the power internet of things, the requirements on the intellectualization and the operational reliability of the high-voltage circuit breaker are higher and higher.
Therefore, a state identification method of the circuit breaker needs to be innovated by adopting a technical means, and the efficient and scientific state maintenance of the circuit breaker is promoted. At present, most of research focuses on vibration signals of circuit breaker operation, and the vibration signals are processed and feature quantity is extracted to complete state identification of circuit breaker operation, but the limitation of single information on state identification capacity is ignored. The sound signal generated when the circuit breaker operates can well avoid distortion due to the wide frequency band, and is just complementary with the characteristics of the vibration signal, so that the joint analysis of sound and vibration through an artificial intelligence algorithm becomes a research hotspot in recent years. However, the artificial intelligence algorithm cannot establish a one-to-one mapping relationship between sound and vibration characteristics generated in the component degradation process or when a fault occurs and various fault states, and cannot intuitively reflect the mechanism from component degradation to fault occurrence. In addition, the circuit breaker is used as a special action type device in a power grid, and the relation between special 'action characteristics' of the circuit breaker and sound and vibration signals and the changes of the 'action characteristics' generated in the process from component degradation to fault occurrence cannot be represented by the current signal acquisition means. The image recognition technology can visually represent the state change of an object in the motion process, so that the real state of the circuit breaker can be guaranteed to be described to the maximum extent by adopting a high-speed camera and analyzing the high-speed camera together with sound, vibration and current signals based on the motion image recognition technology, and the problems are solved.
In conclusion, a novel high-voltage circuit breaker state identification system and method are provided by utilizing sound, vibration, current and image signals acquired by a high-voltage circuit breaker in a multi-path mode, and the system and method have important engineering application values for improving pertinence and accuracy of circuit breaker state identification and operation trend prediction.
Disclosure of Invention
The invention aims to provide a high-voltage circuit breaker state identification system and a method.
A high-voltage circuit breaker state identification system is characterized by comprising a power module, a vibration sensor, a sound sensor, a current sensor, a high-speed camera, a data acquisition device, an industrial personal computer and a shielding cable; the power supply module provides power for the sound sensor, the current sensor and the data acquisition device, the vibration sensor, the sound sensor and the current sensor transmit the measured vibration, sound and current information to the data acquisition device through the shielded cable, and the data acquisition device transmits the vibration, sound and current information to the industrial personal computer in a WIFI wireless communication mode; the high-speed camera directly transmits image information of the high-voltage circuit breaker spring operating mechanism to the industrial personal computer through the shielded cable.
And the opening and closing current signals measured by the current sensor when the circuit breaker acts are used as trigger signals for data acquisition of the data acquisition device and work of the high-speed camera.
The power supply module is a model HA12N10B-2539 and outputs a direct current power supply with the voltage of +/-12V and 1A; the acquisition card in the data acquisition device is a model VK701W, and a four-channel wireless data acquisition card; the model of the vibration sensor is AD50S, the sensitivity is 50mV/g, and the frequency response is 0.5-15000 HZ; the type of the sound sensor is F51, the sensitivity is-48 dB, and the frequency response is 20 HZ-20 kHZ; the current sensor is of a Hall open type, and the measuring range is 0-10A; the model of the high-speed camera is Phantom V10.0, and the resolution is 1080 × 1920.
A state identification method of a high-voltage circuit breaker state identification system is characterized by comprising the following steps:
step 1: collecting vibration signals, sound signals, current signals and image information of a spring operating mechanism in the opening and closing processes of the high-voltage circuit breaker;
step 2: decomposing the vibration signals by adopting a variational modal decomposition method to obtain intrinsic mode function component signals of different frequency bands, and solving Hilbert marginal spectrum energy entropy of each component signal;
and step 3: decomposing a sound signal by adopting a wavelet packet, and taking a wavelet component energy value as a characteristic quantity;
and 4, step 4: analyzing the image information of the spring operating mechanism by adopting a normalized cross-correlation image pyramid matching algorithm estimated in the identification area, and obtaining image information characteristic quantity;
and 5: establishing a high-voltage circuit breaker state identification model, and determining a fusion diagnosis scheme of vibration signals, sound signals and spring operating mechanism image information by using a random forest.
And 2, when the Hilbert marginal spectrum energy entropy of each component signal is obtained, selecting the first 6 orders of intrinsic mode function component signals.
The image information characteristic quantity in the step 4 comprises a maximum contraction length lmaxMaximum velocity vmaxMaximum amplitude AmaxStretching frequency fmaxAnd just-in-time tg。
The step 5 is specifically as follows: respectively generating a classification regression tree by using the vibration signal, the sound signal and the spring operating mechanism image information, wherein the result of each classification regression tree is used as a reliable result of the signal information; then, carrying out uniform voting on all results according to the principle that minority obeys majority, and determining the final result by voting; the voting formula is as follows:
in the formula, m is the number of results generated after test set data are input into a random forest; x is data to be detected; y is a target classification; r (x) is the result of the classification; r isi(x) Is the ith decision tree model; arg is the average number; i is an indicative function.
The invention has the beneficial effects that:
the method comprehensively utilizes a plurality of information source new models of the action of the circuit breaker, can effectively overcome the limitation of a single signal source, more comprehensively depict the running state of the circuit breaker, directly embody the 'motion characteristic' of the circuit breaker, can ensure the evaluation sensing integrity and result preparation of equipment, and has important engineering application value for improving the pertinence and accuracy of the state identification and running trend prediction of the circuit breaker.
Drawings
FIG. 1 is a schematic diagram of a high voltage circuit breaker state identification system according to the present invention;
in the figure: 1-a vibration sensor, 2-a sound sensor, 3-a current sensor, 4-a high-speed camera, 5-a data acquisition device, 6-an industrial personal computer and 7-a shielding cable;
FIG. 2 is a general technical solution diagram of the invention;
FIG. 3 is a circuit breaker signal acquisition hardware system organizational chart;
FIG. 4 is a diagram of a random forest fusion diagnostic structure;
FIG. 5 is a comparison graph of recognition results of different methods.
Detailed Description
The present invention provides a system and a method for identifying a state of a high voltage circuit breaker, which are further described with reference to the accompanying drawings and specific embodiments.
In this embodiment, a ZN65-12 type vacuum circuit breaker is taken as an example, and as shown in fig. 1 to 3, the method specifically includes the following steps:
the first step is as follows: firstly, a circuit breaker signal acquisition hardware system is built, and positions of a vibration sensor, a sound sensor, a current sensor and a high-speed camera are arranged. AD50S vibration sensor passes through strong magnetic base and adsorbs at the operating mechanism roof, locates to lay F51 sound sensor apart from the sound source 0.5 meter department, and 2 current sensor clamp respectively in circuit breaker closing coil control circuit and separating brake coil control circuit, and sound and vibration sensor pass through the aviation plug and link to each other with collection system, and current sensor passes through the BNC plug and links to each other with collection system. The high-speed camera is adjusted to a proper focal length and a proper frame rate (3500FPS) and then fixed at a proper position of the breaker. The current signal of the opening and closing coil of the circuit breaker is used as a trigger signal for collecting by a wireless collecting card and working by a high-speed camera so as to ensure that the collected various signal information has the same time starting point. Collecting vibration signals Z (t), sound signals S (t) and image signals T (t) of the circuit breaker in different states. The different states of the circuit breaker include: and 3 typical faults of normal state, shaft pin falling, fatigue of a closing spring and jamming of a closing iron core.
The second step is that: and for the vibration signal Z (t), decomposing the vibration signal Z (t) by adopting a variational modal decomposition method (VMD) to obtain modal component signals IMF of different frequency bands, and solving the Hilbert marginal spectrum energy entropy of each IMF.
(1) The VMD method decomposes the original signal Z (t) into k bandwidth-limited eigenmode functions IMF, the k IMF component uk(t) can be expressed as:
wherein A isk(t) is the instantaneous amplitude of the original signal,
the instantaneous phase of the original signal.
(2) For each IMF component uk(t) carrying out Hilbert transform to obtain
(3) Constructing an analytic function:
(4) the original signal can be expressed as:
the residual component r is omitted heren(t)，ReRepresenting the real part, Ak(t) is the instantaneous amplitude, i.e.:
θk(t) is the instantaneous phase, i.e.:
fk(t) is the instantaneous frequency, i.e.:
(5) the Hilbert spectrum can accurately describe the change rule of the amplitude of a signal along with time and frequency and is recorded as
(6) Integrating the Hilbert spectrum to obtain a Hilbert marginal spectrum:
where T is the total length of the signal. h (f) reflects the amplitude of the signal as a function of frequency over the entire frequency band.
(7) Hilbert marginal spectral energy is defined as
E＝h2(f)
(8) Normalizing the energy values, i.e.
In the formula EkTo representEnergy value of the k-th IMF component, pkIs an energy normalization value.
(9) According to the basic theory of information entropy, defining the IMF component Hilbert marginal spectrum energy entropy according to the following formula:
Hk＝-pklogpk
analysis finds that the frequencies of the first 6 orders of IMF of the vibration signal Z (t) are concentrated near the respective central frequencies, so that modal aliasing is effectively improved, the first 6 orders of IMF are selected, and the corresponding Hilbert marginal spectrum energy entropy is obtained.
The third step: for the sound signal S (t), wavelet packet decomposition is adopted, and the energy value E of the wavelet component of the first six orders is takeni(i ═ 1,2, …,6) as a feature quantity.
The fourth step: for the image information T (t) of the spring operating mechanism, the shape characteristics of the spring are combined, the circle at the edge of the movable end of the spring is used as a tracking identification target, the image information is obtained by adopting the normalized cross-correlation image pyramid matching (NCC-P-E) algorithm estimated by an identification area to analyze, and the maximum contraction length l is usedmaxMaximum velocity vmaxMaximum amplitude AmaxStretching frequency fmaxAnd just-in-time tgAs a feature quantity of the spring image information.
The fifth step: a four-in-one breaker state identification model is established, and a random forest is utilized to determine a fusion diagnosis scheme of vibration, sound and image multi-information, which is shown in figure 4. And respectively generating a classification regression tree for the 3 kinds of signal information, wherein the result of each classification regression tree is used as a reliable result of the signal information, and then performing uniform voting on all the results, so that the multi-information decision conflict problem is greatly reduced by following the principle that a minority obeys a majority.
For the specific process of the random forest fusion diagnosis scheme, if m results are generated after test set data are input into a random forest, the final result is determined by voting, and the voting formula is as follows:
in the formula x: data to be tested; y is a target classification; r (x) is the result of the classification; r isi(x) Is the ith decision tree model; arg is the average number; i is an indicative function.
And a sixth step: 50 groups of vibration signals, sound signals and image information of normal and three simulated fault states are taken, the state of the circuit breaker is identified by the method, and the comparison is carried out with the result of identifying the state of the circuit breaker by adopting a single vibration signal, single image information and sound vibration combined signal, as shown in figure 5.
As shown in figure 5, the circuit breaker state detection method is used as a new model comprehensively utilizing various information sources of circuit breaker actions, can effectively overcome the limitation of a single signal source, more comprehensively depict the operation state of the circuit breaker, directly reflects the motion characteristic of the circuit breaker, can ensure the evaluation sensing integrity and result readiness of equipment, and has great engineering application value for promoting the state detection of electrical equipment.
The present invention is not limited to the above embodiments, and any changes or substitutions that can be easily made by those skilled in the art within the technical scope of the present invention are also within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (7)
1. A high-voltage circuit breaker state identification system is characterized by comprising a power module, a vibration sensor (1), a sound sensor (2), a current sensor (3), a high-speed camera (4), a data acquisition device (5), an industrial personal computer (6) and a shielded cable (7); the power module provides power for the sound sensor (2), the current sensor (3) and the data acquisition device (5), the vibration sensor (1), the sound sensor (2) and the current sensor (3) transmit measured vibration, sound and current information to the data acquisition device (5) through a shielded cable (7), and the data acquisition device (5) transmits the vibration, sound and current information to the industrial personal computer (6) in a WIFI wireless communication mode; the high-speed camera (4) directly transmits the image information of the high-voltage circuit breaker spring operating mechanism to the industrial personal computer (6) through the shielded cable (7).
2. The system for identifying the state of the high-voltage circuit breaker according to claim 1, wherein the opening/closing current signal measured by the current sensor (3) during the circuit breaker action is used as a trigger signal for data acquisition of the data acquisition device (5) and operation of the high-speed camera (4).
3. The system for identifying the state of the high-voltage circuit breaker as claimed in claim 1 or 2, wherein the power supply module is a model HA12N10B-2539, and outputs a direct current power supply of +/-12V and 1A; the acquisition card in the data acquisition device (5) is a model VK701W, a four-channel wireless data acquisition card; the type of the vibration sensor (1) is AD50S, the sensitivity is 50mV/g, and the frequency response is 0.5-15000 HZ; the type of the sound sensor (2) is F51, the sensitivity is-48 dB, and the frequency response is 20 HZ-20 kHZ; the current sensor (3) is of a Hall open type, and the measuring range is 0-10A; the model of the high-speed camera (4) is Phantom V10.0, and the resolution is 1080 × 1920.
4. A state recognition method of the high voltage circuit breaker state recognition system of claim 1, comprising the steps of:
step 1: collecting vibration signals, sound signals, current signals and image information of a spring operating mechanism in the opening and closing processes of the high-voltage circuit breaker;
step 2: decomposing the vibration signals by adopting a variational modal decomposition method to obtain intrinsic mode function component signals of different frequency bands, and solving Hilbert marginal spectrum energy entropy of each component signal;
and step 3: decomposing a sound signal by adopting a wavelet packet, and taking a wavelet component energy value as a characteristic quantity;
and 4, step 4: analyzing the image information of the spring operating mechanism by adopting a normalized cross-correlation image pyramid matching algorithm estimated in the identification area, and obtaining image information characteristic quantity;
and 5: establishing a high-voltage circuit breaker state identification model, and determining a fusion diagnosis scheme of vibration signals, sound signals and spring operating mechanism image information by using a random forest.
5. The method for identifying the state of a high-voltage circuit breaker according to claim 4, wherein the step 2 is to select the first 6 th order eigenmode function component signals when the Hilbert marginal spectral energy entropy of each component signal is obtained.
6. The method for identifying the status of a high voltage circuit breaker according to claim 4, wherein the image information characteristic quantity in step 4 comprises a maximum contraction length lmaxMaximum velocity vmaxMaximum amplitude AmaxStretching frequency fmaxAnd just-in-time tg。
7. The method for identifying the state of a high-voltage circuit breaker according to claim 4, wherein the step 5 comprises the following steps: respectively generating a classification regression tree by using the vibration signal, the sound signal and the spring operating mechanism image information, wherein the result of each classification regression tree is used as a reliable result of the signal information; then, carrying out uniform voting on all results according to the principle that minority obeys majority, and determining the final result by voting; the voting formula is as follows:
in the formula, m is the number of results generated after test set data are input into a random forest; x is data to be detected; y is a target classification; r (x) is the result of the classification; r isi(x) Is the ith decision tree model; arg is the average number; i is an indicative function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110928828.3A CN113671363A (en) | 2021-08-13 | 2021-08-13 | High-voltage circuit breaker state identification system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110928828.3A CN113671363A (en) | 2021-08-13 | 2021-08-13 | High-voltage circuit breaker state identification system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113671363A true CN113671363A (en) | 2021-11-19 |
Family
ID=78542766
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110928828.3A Pending CN113671363A (en) | 2021-08-13 | 2021-08-13 | High-voltage circuit breaker state identification system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113671363A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114543898A (en) * | 2022-04-07 | 2022-05-27 | 国网河北省电力有限公司超高压分公司 | Non-invasive detection system for high-voltage circuit breaker operating mechanism |
| CN114705241A (en) * | 2022-03-28 | 2022-07-05 | 广东电网有限责任公司 | Method and device for monitoring state and diagnosing fault of switch equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103189897A (en) * | 2011-11-02 | 2013-07-03 | 松下电器产业株式会社 | Image recognition device, image recognition method, and integrated circuit |
| CN103500344A (en) * | 2013-09-02 | 2014-01-08 | 中国测绘科学研究院 | Method and module for extracting and interpreting information of remote-sensing image |
| CN105512768A (en) * | 2015-12-14 | 2016-04-20 | 上海交通大学 | User electricity consumption relevant factor identification and electricity consumption quantity prediction method under environment of big data |
| CN107796602A (en) * | 2016-08-31 | 2018-03-13 | 华北电力大学（保定） | A kind of circuit breaker failure diagnostic method of sound and vibration signal fused processing |
| CN109164381A (en) * | 2018-09-07 | 2019-01-08 | 广西电网有限责任公司电力科学研究院 | A kind of mechanical state of high-voltage circuit breaker on-line monitoring and fault identification method and device |
| CN109871865A (en) * | 2019-01-08 | 2019-06-11 | 浙江大学 | A kind of coalcutter online system failure diagnosis based on colony intelligence optimizing |
| CN110119713A (en) * | 2019-05-14 | 2019-08-13 | 云南电网有限责任公司电力科学研究院 | Mechanical Failure of HV Circuit Breaker diagnostic method based on D-S evidence theory |
| CN111524140A (en) * | 2020-04-21 | 2020-08-11 | 广东职业技术学院 | Medical image semantic segmentation method based on CNN and random forest method |
| CN112036440A (en) * | 2020-07-31 | 2020-12-04 | 山东科技大学 | Satellite attitude control system fault diagnosis and early warning method based on random forest |
| CN112489330A (en) * | 2020-12-02 | 2021-03-12 | 广东电网有限责任公司江门供电局 | Warehouse anti-theft alarm method |
-
2021
- 2021-08-13 CN CN202110928828.3A patent/CN113671363A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103189897A (en) * | 2011-11-02 | 2013-07-03 | 松下电器产业株式会社 | Image recognition device, image recognition method, and integrated circuit |
| CN103500344A (en) * | 2013-09-02 | 2014-01-08 | 中国测绘科学研究院 | Method and module for extracting and interpreting information of remote-sensing image |
| CN105512768A (en) * | 2015-12-14 | 2016-04-20 | 上海交通大学 | User electricity consumption relevant factor identification and electricity consumption quantity prediction method under environment of big data |
| CN107796602A (en) * | 2016-08-31 | 2018-03-13 | 华北电力大学（保定） | A kind of circuit breaker failure diagnostic method of sound and vibration signal fused processing |
| CN109164381A (en) * | 2018-09-07 | 2019-01-08 | 广西电网有限责任公司电力科学研究院 | A kind of mechanical state of high-voltage circuit breaker on-line monitoring and fault identification method and device |
| CN109871865A (en) * | 2019-01-08 | 2019-06-11 | 浙江大学 | A kind of coalcutter online system failure diagnosis based on colony intelligence optimizing |
| CN110119713A (en) * | 2019-05-14 | 2019-08-13 | 云南电网有限责任公司电力科学研究院 | Mechanical Failure of HV Circuit Breaker diagnostic method based on D-S evidence theory |
| CN111524140A (en) * | 2020-04-21 | 2020-08-11 | 广东职业技术学院 | Medical image semantic segmentation method based on CNN and random forest method |
| CN112036440A (en) * | 2020-07-31 | 2020-12-04 | 山东科技大学 | Satellite attitude control system fault diagnosis and early warning method based on random forest |
| CN112489330A (en) * | 2020-12-02 | 2021-03-12 | 广东电网有限责任公司江门供电局 | Warehouse anti-theft alarm method |
Non-Patent Citations (2)
| Title |
|---|
| 杨秋玉: "基于VMD-Hilbert 边际谱能量熵和SVM 的高压断路器机械故障诊断", 《电机与控制学报》 * |
| 马速良: "多振动信息下的高压断路器机械故障随机森林融合诊断方法", 《电 工 技 术 学 报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114705241A (en) * | 2022-03-28 | 2022-07-05 | 广东电网有限责任公司 | Method and device for monitoring state and diagnosing fault of switch equipment |
| CN114543898A (en) * | 2022-04-07 | 2022-05-27 | 国网河北省电力有限公司超高压分公司 | Non-invasive detection system for high-voltage circuit breaker operating mechanism |
| CN114543898B (en) * | 2022-04-07 | 2023-11-24 | 国网河北省电力有限公司超高压分公司 | Non-invasive detection system of high-voltage circuit breaker operating mechanism |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | ArcNet: Series AC arc fault detection based on raw current and convolutional neural network | |
| CN108107324B (en) | Power distribution network fault positioning method based on deep convolutional neural network | |
| CN111523660B (en) | Audio-visual heat integrated abnormality detection alarm method based on artificial intelligence | |
| CN106646096B (en) | Transformer fault classification and recognition methods based on vibration analysis method | |
| CN103558529B (en) | A kind of mode identification method of three-phase cartridge type supertension GIS partial discharge altogether | |
| Do et al. | Convolutional-neural-network-based partial discharge diagnosis for power transformer using UHF sensor | |
| US20230152187A1 (en) | Fault signal locating and identifying method of industrial equipment based on microphone array | |
| CN113671363A (en) | High-voltage circuit breaker state identification system and method | |
| CN111060838B (en) | Medical electronic equipment switching power supply fault diagnosis method based on multi-dimensional feature fusion | |
| JP6476861B2 (en) | Electromagnetic field feature classification presentation device | |
| CN108693448B (en) | Partial discharge mode recognition system applied to power equipment | |
| CN117289067B (en) | Transformer running state on-line monitoring system | |
| CN115453286B (en) | GIS partial discharge diagnosis method, model training method, device and system | |
| CN110222765A (en) | A kind of permanent magnet synchronous motor health status monitoring method and system | |
| CN110632484A (en) | ELM-based GIS partial discharge defect diagnosis and classification system and method | |
| CN112348052A (en) | Power transmission and transformation equipment abnormal sound source positioning method based on improved EfficientNet | |
| Wadi | Fault detection in power grids based on improved supervised machine learning binary classification | |
| CN112986870A (en) | Distributed power transformer winding state monitoring method and system based on vibration method | |
| CN113362856A (en) | Sound fault detection method and device applied to power Internet of things | |
| CN105891635A (en) | Digital signal processing-based electric appliance type identification device and method | |
| KR101575204B1 (en) | Apparatus and method for diagnosing a partial discharging equipped | |
| CN110929673A (en) | Transformer winding vibration signal identification method based on ITD (inverse discrete cosine transformation) permutation entropy and CGWO-SVM (Carrier-support vector machine) | |
| CN111025100A (en) | Transformer ultrahigh frequency partial discharge signal mode identification method and device | |
| Happe et al. | Advanced suppression of stochastic pulse shaped partial discharge disturbances | |
| Dopierała | Fault detection method for energy measurement systems equipped with a Rogowski coil using the coil's response to a unit voltage jump and a fully 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20211119 |