CN113380258B - Substation fault judgment voiceprint recognition method - Google Patents
Substation fault judgment voiceprint recognition method Download PDFInfo
- Publication number
- CN113380258B CN113380258B CN202110476178.3A CN202110476178A CN113380258B CN 113380258 B CN113380258 B CN 113380258B CN 202110476178 A CN202110476178 A CN 202110476178A CN 113380258 B CN113380258 B CN 113380258B
- Authority
- CN
- China
- Prior art keywords
- fault
- sound
- frequency
- module
- voiceprint
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000001914 filtration Methods 0.000 claims abstract description 14
- 238000012546 transfer Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 4
- 230000000452 restraining effect Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification techniques
- G10L17/04—Training, enrolment or model building
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
- H02J13/00034—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving an electric power substation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/16—Electric power substations
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Power Engineering (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a transformer substation fault judgment voiceprint recognition method, which solves the problem of difficulty in equipment fault judgment caused by the fact that the number of transformer substations and more devices in the transformer substations are increased in the prior art. The invention adopts the voiceprint recognition method to obtain a conclusion by filtering the sound and then comparing the waveform with the graph.
Description
Technical Field
The invention relates to the technical field of substation monitoring, in particular to a substation fault judgment voiceprint recognition method.
Background
In daily life, voice is a medium for transmitting information, and can acquire speaking contents from different voices and confirm personal information of a speaker through unique characteristics in the voice. When the power equipment runs, the power equipment can also send out own voice like a person, a master power teacher with rich experience can often judge whether the equipment has potential safety hazards according to the voices, and the listening recognition capability of the master power teacher is important for safe and stable running of the transformer substation. With the development of power grid construction, the number of transformer substations is more and more, and it is unrealistic to completely rely on a master teacher to judge equipment faults. The transformer substation equipment is numerous, and there are multiple types of equipment such as transformers, switch cabinets, insulators, buses, isolating switches, and more than one type of equipment in each type. The multi-dimensional characteristic information of different devices, such as electrical characteristics, physical form characteristics, infrared characteristics, running states, voiceprint characteristics and the like, is different. The traditional equipment fault diagnosis mainly comprises several modes such as temperature detection, smell detection, appearance inspection, electrical information measurement and the like. The inspection robot applied at present can replace a person to read and identify infrared information of equipment and judge whether the equipment works normally. The temperature is only one dimension for judging whether the equipment has faults or not by people, and an experienced teacher can comprehensively judge whether the equipment has faults or not according to factors such as smell, appearance, electrical information and the like of the equipment. Such a fault detection method has obvious disadvantages.
Disclosure of Invention
The invention aims to solve the problem that the equipment fault judgment is difficult due to the fact that the number of transformer substations and more equipment in the transformer substations in the prior art, and provides a transformer substation fault judgment voiceprint recognition method.
In order to achieve the purpose, the invention adopts the following technical scheme:
a transformer substation fault judgment voiceprint recognition method comprises the following steps:
s1, establishing a system model;
s2, collecting the sound of the substation equipment;
s3, recognizing the sound of the substation equipment collected in the previous step;
s4, associating the identified result with the fault sound in the preset system model;
and S5, judging the specific fault type according to the correlation result.
The invention adopts the voiceprint recognition method to obtain the conclusion by filtering the sound and then comparing the waveform patterns, has high accuracy, and provides an alarm function to judge the fault voiceprint so as to be convenient for maintenance.
Preferably, the S1 includes that the system model is established to include a preset sound collection module, a voiceprint recognition module, a fault voiceprint association module and a fault determination module, which are connected in sequence;
the voice acquisition module is used for acquiring the voice of equipment in the transformer substation and sending the voice to the voiceprint recognition module;
the voiceprint recognition module is used for filtering out noise, each bandwidth of equipment noise is preset in the voiceprint recognition module, and the voiceprint recognition module comprises a plurality of band-pass filters for filtering the noise;
the fault voiceprint correlation module is used for comparing the waveform of the noise obtained after filtering by the voiceprint recognition module with the voiceprint waveforms of various fault noises in the substation preset in the fault voiceprint correlation module and correlating the noise obtained after filtering with various fault noises in the substation;
and the fault judging module is used for outputting a specific fault type and alarming the fault.
The modules of the four necklaces in sequence cooperate to collect the noise in the substation in real time to judge whether the noise is known fault noise,
preferably, the voiceprint acquisition module is established by the following steps:
s11, reading sounds of various faults in the substation to obtain the lowest cut-off frequency, the highest cut-off frequency and the bandwidth of the fault sounds;
s12, obtaining a high-pass filter through the lowest cut-off frequency, obtaining a low-pass filter through the highest cut-off frequency, connecting the high-pass filter and the low-pass filter in series to obtain a band-pass filter, and restraining sound below the lowest cut-off frequency and sound above the highest cut-off frequency from passing through; s13, calculating a transfer function of the band-pass filter;
and S13, sending the noise information filtered by the band-pass filter to a fault voiceprint correlation module.
Preferably, S11 includes the following: calculating the bandwidth B omega of fault soundh-ωlCenter frequency ofAnd calculating a transfer function according to the bandwidth and the center frequency to obtain a specific model of the band-pass filter.
Preferably, the transfer function is calculated in the following manner:
where B is the filter bandwidth, ωlLowest cut-off frequency, ω, of a filter determined for a fault soundhMaximum cut-off frequency, omega, of a filter determined for a fault sound0As the center frequency, s ═ j ω, s is derived from the laplace transform and represents a complex frequency.
Preferably, S4 includes the steps of:
s41, translating and translating the frequency domain oscillogram of the fault sound obtained by identification on an omega axis, wherein the position with the slope larger than 0 is taken as an origin, the omega axis is a horizontal axis, and an H (S) axis is a vertical axis;
s42, overlapping a preset voiceprint model of the fault sound in the transformer substation and a frequency domain oscillogram of the fault sound obtained by identification at the lowest cut-off frequency and the highest cut-off frequency;
s43, identifying a point of the failure sound frequency domain waveform diagram with a slope of 0 as a first set of key points a ═ a0, a1, a2, a3... an };
identifying a point with a slope of 0 of a preset fault sound frequency domain oscillogram as a second key point set B ═ { B0, B1, B2, b3... an };
s44, constructing a first slope set K ═ { K1, K2, k3... kn } and a second slope set F ═ F1, F2, f3... fn };
s45, establishing a discriminant according to the first slope set and the second slope set to determine whether the discriminant is associated with the current preset fault sound, if so, sending a result to a fault determination module, and if not, continuously performing association comparison on the identified result fault sound and the next preset fault sound;
wherein, in S44, k1 is the slope between key points a0 and a1, f1 is the slope between key points b0 and b1, and so on.
Preferably, the discriminant in S44 is:
ki*fi>0;
i belongs to [1, n ], n is the number of key points
If the judgment formula is satisfied, the association is judged, and the result is sent to a fault judgment module.
Preferably, S5 includes the following: and the fault judging module reads the last related preset fault type, judges the fault type and gives an alarm.
Therefore, the invention has the following beneficial effects:
the method comprises the steps of establishing a system model in advance to store the common noise type in the substation, storing waveforms of various noises and voiceprint information in the system model, constructing a plurality of filters according to known noises, acquiring the noise information in the substation in real time, enabling the noise information acquired in real time to pass through the filters of the system model, and judging the fault of the substation if the filtered noise can be associated with a certain prestored noise waveform.
The problem that faults cannot be judged in time due to the fact that other judging characteristics are not obvious is avoided, missing judgment is prevented, the age is judged in a layered mode, and the range of model identification errors is reduced.
Drawings
Fig. 1 is a flowchart of the present embodiment.
Fig. 2 is a waveform diagram of the band-pass filter of the present embodiment.
Detailed Description
The invention is further described with reference to the following detailed description and accompanying drawings.
Example 1:
the embodiment provides a transformer substation fault judgment voiceprint recognition method, and as shown in fig. 1, the transformer substation fault judgment voiceprint recognition method comprises the following steps:
s1, establishing a system model;
s2, collecting the sound of the substation equipment;
s3, recognizing the sound of the substation equipment collected in the previous step;
s4, associating the identified result with the fault sound in the preset system model;
and S5, judging the specific fault type according to the correlation result.
Preferably, the S1 includes that the system model is established to include a preset sound collection module, a voiceprint recognition module, a fault voiceprint association module and a fault determination module, which are connected in sequence;
the voice acquisition module is used for acquiring the voice of equipment in the transformer substation and sending the voice to the voiceprint recognition module;
the voiceprint recognition module is used for filtering out noise, each bandwidth of equipment noise is preset in the voiceprint recognition module, and the voiceprint recognition module comprises a plurality of band-pass filters for filtering the noise;
the fault voiceprint correlation module is used for comparing the waveform of the noise obtained after filtering by the voiceprint recognition module with the voiceprint waveforms of various fault noises in the substation preset in the fault voiceprint correlation module and correlating the noise obtained after filtering with various fault noises in the substation;
and the fault judging module is used for outputting a specific fault type and alarming the fault.
Preferably, the voiceprint acquisition module is established by the following steps:
s11, reading sounds of various faults in the substation to obtain the lowest cut-off frequency, the highest cut-off frequency and the bandwidth of the fault sounds;
s12, obtaining a high-pass filter through the lowest cut-off frequency, obtaining a low-pass filter through the highest cut-off frequency, connecting the high-pass filter and the low-pass filter in series to obtain a band-pass filter, and restraining sound below the lowest cut-off frequency and sound above the highest cut-off frequency from passing through; s13, calculating a transfer function of the band-pass filter;
and S13, sending the noise information filtered by the band-pass filter to a fault voiceprint correlation module.
Preferably, S11 includes the following: calculating the bandwidth B omega of fault soundh-ωlCenter frequency ofAnd calculating a transfer function according to the bandwidth and the center frequency to obtain a specific model of the band-pass filter.
Preferably, the transfer function is calculated in the following manner:
where B is the filter bandwidth, ωlLowest cut-off frequency, ω, of a filter determined for a fault soundhMaximum cut-off frequency, omega, of a filter determined for a fault sound0As the center frequency, s ═ j ω, s is derived from the laplace transform and represents a complex frequency.
Preferably, S4 includes the steps of:
s41, translating and translating the frequency domain oscillogram of the fault sound obtained by identification on an omega axis, wherein the position with the slope larger than 0 is taken as an origin, the omega axis is a horizontal axis, and an H (S) axis is a vertical axis;
s42, overlapping a preset voiceprint model of the fault sound in the transformer substation and a frequency domain oscillogram of the fault sound obtained by identification at the lowest cut-off frequency and the highest cut-off frequency;
s43, identifying a point of the failure sound frequency domain waveform diagram with a slope of 0 as a first set of key points a ═ a0, a1, a2, a3... an };
identifying a point with a slope of 0 of a preset fault sound frequency domain oscillogram as a second key point set B ═ { B0, B1, B2, b3... an };
s44, constructing a first slope set K ═ { K1, K2, k3... kn } and a second slope set F ═ F1, F2, f3... fn };
s45, establishing a discriminant according to the first slope set and the second slope set to determine whether the discriminant is associated with the current preset fault sound, if so, sending a result to a fault determination module, and if not, continuously performing association comparison on the identified result fault sound and the next preset fault sound;
wherein, in S44, k1 is the slope between key points a0 and a1, f1 is the slope between key points b0 and b1, and so on.
Preferably, the discriminant in S44 is:
ki*fi>0;
i belongs to [1, n ], n is the number of key points
If the judgment formula is satisfied, the association is judged, and the result is sent to a fault judgment module.
Preferably, S5 includes the following: and the fault judging module reads the last related preset fault type, judges the fault type and gives an alarm.
The working process of the invention is as follows: the method comprises the steps of establishing a system model in advance to store the common noise type in the substation, storing waveforms of various noises and voiceprint information in the system model, constructing a plurality of filters according to known noises, acquiring the noise information in the substation in real time, passing the acquired noise information in real time through the filters of the system model, and judging the fault of the substation if the filtered noise can be associated with a certain prestored noise waveform.
The above embodiments are described in detail for the purpose of further illustrating the present invention and should not be construed as limiting the scope of the present invention, and the skilled engineer can make insubstantial modifications and variations of the present invention based on the above disclosure.
Claims (6)
1. A transformer substation fault judgment voiceprint recognition method is characterized by comprising the following steps:
s1, establishing a system model;
s2, collecting the sound of the substation equipment;
s3, recognizing the sound of the substation equipment collected in the previous step;
s4, associating the identified result with the fault sound in the preset system model;
s4 includes the steps of:
s41, translating the frequency domain oscillogram of the fault sound obtained by identification on an omega axis, wherein the position with the slope larger than 0 is taken as an origin, the omega axis is a horizontal axis, and an H (S) axis is a vertical axis;
s42, overlapping a preset voiceprint model of the fault sound in the transformer substation and a frequency domain oscillogram of the fault sound obtained by identification at the lowest cut-off frequency and the highest cut-off frequency;
s43, identifying a point of the failure sound frequency domain waveform diagram with a slope of 0 as a first set of key points a ═ a0, a1, a2, a3... an };
identifying a point with a slope of 0 of a preset fault sound frequency domain oscillogram as a second key point set B ═ { B0, B1, B2, b3... an };
s44, constructing a first slope set K ═ { K1, K2, k3... kn } and a second slope set F ═ F1, F2, f3... fn };
s45, establishing a discriminant according to the first slope set and the second slope set to determine whether the discriminant is associated with the current preset fault sound, if so, sending a result to a fault determination module, and if not, continuously performing association comparison on the identified result fault sound and the next preset fault sound;
wherein, in S44, k1 is the slope between the key points a0 and a1, f1 is the slope between the key points b0 and b1, and so on; the discriminant in S45 is:
ki*fi>0;
i belongs to [1, n ], n is the number of key points
If the judgment formula is satisfied, judging the association and sending the result to a fault judgment module;
and S5, judging the specific fault type according to the correlation result.
2. The transformer substation fault judgment voiceprint recognition method according to claim 1, wherein S1 comprises the following steps that a system model is established, wherein the system model comprises a preset sound collection module, a voiceprint recognition module, a fault voiceprint association module and a fault judgment module which are connected in sequence;
the voice acquisition module is used for acquiring the voice of equipment in the transformer substation and sending the voice to the voiceprint recognition module;
the voiceprint recognition module is used for filtering out noise, each bandwidth of equipment noise is preset in the voiceprint recognition module, and the voiceprint recognition module comprises a plurality of band-pass filters for filtering the noise;
the fault voiceprint correlation module is used for comparing the waveform of the noise obtained after filtering by the voiceprint recognition module with the voiceprint waveforms of various fault noises in the substation preset in the fault voiceprint correlation module and correlating the noise obtained after filtering with various fault noises in the substation;
and the fault judging module is used for outputting a specific fault type and alarming the fault.
3. The substation fault judgment voiceprint recognition method according to claim 2, wherein the voiceprint collection module is established by the following steps:
s11, reading sounds of various faults in the substation to obtain the lowest cut-off frequency, the highest cut-off frequency and the bandwidth of the fault sounds;
s12, obtaining a high-pass filter through the lowest cut-off frequency, obtaining a low-pass filter through the highest cut-off frequency, connecting the high-pass filter and the low-pass filter in series to obtain a band-pass filter, and restraining sound below the lowest cut-off frequency and sound above the highest cut-off frequency from passing through;
s13, calculating a transfer function of the band-pass filter;
and S13, sending the noise information filtered by the band-pass filter to a fault voiceprint correlation module.
4. The substation fault judgment voiceprint recognition method according to claim 3, wherein S11 comprises the following contents: calculating the bandwidth B omega of fault soundh-ωlCenter frequency ofCalculating a transfer function according to the bandwidth and the center frequency to obtain a specific model of the band-pass filter;
ωllowest cut-off frequency, ω, of a filter determined for a fault soundhThe highest cut-off frequency of the filter determined for the fault sound.
5. The transformer substation fault judgment voiceprint recognition method according to claim 4, wherein the transfer function is calculated in a manner that:
where B is the filter bandwidth, ω0As the center frequency, s ═ j ω, s is derived from the laplace transform and represents a complex frequency.
6. The substation fault judgment voiceprint recognition method according to claim 1, wherein S5 comprises the following contents: and the fault judging module reads the last related preset fault type, judges the fault type and gives an alarm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110476178.3A CN113380258B (en) | 2021-04-29 | 2021-04-29 | Substation fault judgment voiceprint recognition method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110476178.3A CN113380258B (en) | 2021-04-29 | 2021-04-29 | Substation fault judgment voiceprint recognition method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113380258A CN113380258A (en) | 2021-09-10 |
CN113380258B true CN113380258B (en) | 2022-04-12 |
Family
ID=77570299
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110476178.3A Active CN113380258B (en) | 2021-04-29 | 2021-04-29 | Substation fault judgment voiceprint recognition method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113380258B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115240691B (en) * | 2022-09-23 | 2022-12-06 | 山西振中电力股份有限公司 | Substation equipment running state monitoring control system based on data analysis |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2912296C (en) * | 2007-06-27 | 2021-06-15 | Wanda G. Papadimitriou | Autonomous fitness for service assessment |
PL231399B1 (en) * | 2014-01-27 | 2019-02-28 | Adam Pluta | Method and system for decomposition acoustic signal into sound objects, the sound object and its application |
CN105136404B (en) * | 2015-09-22 | 2017-08-25 | 孙宏岩 | A kind of vocal print detecting system |
CN112420055A (en) * | 2020-09-22 | 2021-02-26 | 甘肃同兴智能科技发展有限公司 | Substation state identification method and device based on voiceprint characteristics |
CN112289341A (en) * | 2020-11-03 | 2021-01-29 | 国网智能科技股份有限公司 | Sound abnormity identification method and system for transformer substation equipment |
-
2021
- 2021-04-29 CN CN202110476178.3A patent/CN113380258B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN113380258A (en) | 2021-09-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103713237B (en) | A kind of power system transmission line short trouble diagnostic method | |
CN101696986B (en) | Fault arc detection method and protection device adopting same | |
CN104964738B (en) | A kind of power transformer noise evaluation method based on noise separation | |
Peng et al. | Application of K-Means method to pattern recognition in on-line cable partial discharge monitoring | |
CN108802525A (en) | Equipment fault intelligent Forecasting based on small sample | |
CN108414079A (en) | A kind of transformer noise monitoring system | |
CN113380258B (en) | Substation fault judgment voiceprint recognition method | |
CN111653291B (en) | Intelligent health monitoring method for power equipment based on voiceprint | |
CN110703151A (en) | Transformer fault diagnosis method based on vibration blind source separation and Bayesian model | |
CN114325256A (en) | Power equipment partial discharge identification method, system, equipment and storage medium | |
CN112016470A (en) | On-load tap-changer fault identification method based on sound signal and vibration signal | |
CN109782126B (en) | Power distribution network early fault detection method based on humanoid concept learning | |
CN108594156B (en) | Improved current transformer saturation characteristic identification method | |
CN106646138B (en) | Distribution net work earthing fault localization method based on the conversion of more sample frequency wavelet character energy | |
CN115808600B (en) | DC arc detection method based on mathematical morphology and pattern recognition | |
CN110017894B (en) | Method and device for filtering random noise in vibration and sound detection of transformer in running state | |
CN114935708A (en) | Method for identifying circuit discharge abnormity | |
CN113533904B (en) | Method, device, equipment and medium for detecting high-resistance ground fault of power distribution network | |
CN109917245B (en) | Ultrasonic detection partial discharge signal mode identification method considering phase difference | |
CN113866572A (en) | Direct-current fault arc detection and positioning method under condition of access of multiple power electronic devices | |
CN117153193B (en) | Power equipment fault voiceprint recognition method integrating physical characteristics and data diagnosis | |
CN114994442A (en) | Fault arc identification method, system and device | |
CN117849552A (en) | Ring main unit partial discharge on-line monitoring method | |
Wang et al. | Research on Voiceprint Monitoring And Diagnosis Technology for Mechanical Faults of 10kV Circuit Breakers | |
CN110532885A (en) | Transformer winding and iron coring vibration signal separating method based on RBF neural |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |