CN116665711B - Gas-insulated switchgear on-line monitoring method and device and computer equipment - Google Patents
Gas-insulated switchgear on-line monitoring method and device and computer equipment Download PDFInfo
- Publication number
- CN116665711B CN116665711B CN202310939123.0A CN202310939123A CN116665711B CN 116665711 B CN116665711 B CN 116665711B CN 202310939123 A CN202310939123 A CN 202310939123A CN 116665711 B CN116665711 B CN 116665711B
- Authority
- CN
- China
- Prior art keywords
- sound
- gas
- insulated switchgear
- data
- fault
- 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 51
- 238000012544 monitoring process Methods 0.000 title claims abstract description 18
- 238000009432 framing Methods 0.000 claims abstract description 27
- 238000000605 extraction Methods 0.000 claims abstract description 22
- 238000012806 monitoring device Methods 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims description 28
- 238000004590 computer program Methods 0.000 claims description 21
- 230000006870 function Effects 0.000 claims description 16
- 238000010219 correlation analysis Methods 0.000 claims description 4
- 230000004927 fusion Effects 0.000 description 23
- 230000002159 abnormal effect Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 229910018503 SF6 Inorganic materials 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 230000007774 longterm Effects 0.000 description 4
- SFZCNBIFKDRMGX-UHFFFAOYSA-N sulfur hexafluoride Chemical compound FS(F)(F)(F)(F)F SFZCNBIFKDRMGX-UHFFFAOYSA-N 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000037433 frameshift Effects 0.000 description 3
- 238000007499 fusion processing Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 229960000909 sulfur hexafluoride Drugs 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- 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
- G01R31/3271—Testing of circuit interrupters, switches or circuit-breakers of high voltage or medium voltage devices
- G01R31/3275—Fault detection or status indication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
- G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
-
- 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
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Signal Processing (AREA)
- Gas-Insulated Switchgears (AREA)
Abstract
The application relates to a gas-insulated switchgear on-line monitoring method, a gas-insulated switchgear on-line monitoring device, computer equipment and a storage medium. The method comprises the following steps: acquiring a sound data set of the gas-insulated switchgear to be identified when in operation; the sound data set comprises sound data acquired at a plurality of acquisition positions; for each sound data, framing each sound data in the sound data set based on time sequence to obtain frame data; extracting the sound characteristics of the frame data by adopting a sound characteristic extraction model; determining the weight of the sound characteristic of the frame data according to the acquisition position corresponding to the frame data; inputting the sound characteristics and the weight of the sound characteristics of the frame data into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized; the fault recognition model is a gating loop network model. By adopting the method, the accuracy of fault identification of the gas-insulated switchgear can be improved.
Description
Technical Field
The application relates to the technical field of electrical intelligent detection, in particular to an online monitoring method and device for gas-insulated switchgear, computer equipment and a storage medium.
Background
A GAS insulated switchgear (GAS insulated SWITCHGEAR, GIS) is a switchgear for use in a high voltage power system for controlling, protecting and isolating electrical equipment and circuits in the power system.
Currently, gas-insulated switchgear is widely used in various scenarios in high-voltage power systems, such as transmission and distribution systems, urban power grids, etc. However, the current method for identifying the fault of the gas-insulated switchgear often adopts a contact detection mode, but on site, there are a wide range of interference sources such as corona discharge, impact generated by switching action, partial discharge which may occur in the adjacent high-voltage switchgear, and the like, so that accurate fault identification information cannot be obtained, and thus the fault identification of the gas-insulated switchgear is inaccurate.
Disclosure of Invention
Based on this, it is necessary to provide a gas insulated switchgear on-line monitoring method, apparatus, computer device, computer readable storage medium and computer program product for the above-mentioned technical problem of inaccurate fault identification.
In a first aspect, the present application provides a method for on-line monitoring of a gas insulated switchgear. The method comprises the following steps:
Acquiring a sound data set of the gas-insulated switchgear to be identified when in operation; the sound data set comprises sound data acquired at a plurality of acquisition positions;
for each sound data, carrying out framing processing on each sound data in the sound data set based on time sequence to obtain frame data;
extracting the sound characteristics of the frame data by adopting a sound characteristic extraction model;
determining the weight of the sound characteristic of the frame data according to the acquisition position corresponding to the frame data;
inputting the sound characteristics of the frame data and the weights of the sound characteristics into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized; the fault identification model is a gating circulation network model.
In one embodiment, the framing the sound data based on time sequence to obtain frame data includes:
cutting head and tail Duan Jingyin data in the sound data to obtain cut sound data;
and carrying out framing processing on the cut sound data by adopting a window function to obtain frame data.
In one embodiment, the inputting the sound feature of the frame data and the weight of the sound feature into a pre-trained fault recognition model to obtain the fault recognition result of the gas-insulated switchgear to be recognized includes:
According to the weight of the sound feature, carrying out fusion processing on the sound feature of the frame data at the same time to obtain the fusion feature of the sound data at each time;
and inputting the fusion characteristics into a pre-trained fault recognition model according to the time sequence of the fusion characteristics to obtain a fault recognition result of the gas-insulated switchgear to be recognized.
In one embodiment, the inputting the fusion feature into a pre-trained fault recognition model according to the time sequence of the fusion feature to obtain a fault recognition result of the gas-insulated switchgear to be recognized includes:
inputting the fusion characteristics into a pre-trained fault recognition model to obtain the normal probability and the abnormal probability of the gas-insulated switchgear to be recognized;
and determining a fault recognition result of the gas-insulated switchgear to be recognized according to the normal probability and the abnormal probability.
In one embodiment, the inputting the sound feature of the frame data and the weight of the sound feature into a pre-trained fault recognition model to obtain the fault recognition result of the gas-insulated switchgear to be recognized includes:
Inputting sound characteristics of frame data corresponding to each acquisition position into a pre-trained fault recognition model according to the time sequence of the frame data aiming at each acquisition position to obtain a sub-fault recognition result corresponding to each acquisition position;
and determining the fault recognition result of the gas-insulated switchgear to be recognized according to the sub fault recognition result and the weight of the sound characteristic.
In one embodiment, after obtaining the fault recognition result of the gas-insulated switchgear to be recognized, the method further includes:
if the fault identification result is that the gas-insulated switchgear to be identified has a fault, generating a fault report;
and sending the fault report to the user terminal.
In a second aspect, the application also provides an on-line monitoring device for gas-insulated switchgear. The device comprises:
the sound acquisition module is used for acquiring a sound data set of the gas-insulated switchgear to be identified when the gas-insulated switchgear works; the sound data set comprises sound data acquired at a plurality of acquisition positions;
the frame processing module is used for carrying out frame processing on each sound data in the sound data set based on time sequence to obtain frame data;
The feature extraction module is used for extracting the sound features of the frame data by adopting a sound feature extraction model;
the weight determining module is used for determining the weight of the sound characteristic of the frame data according to the acquisition position corresponding to the frame data;
the result determining module is used for inputting the sound characteristics of the frame data and the weights of the sound characteristics into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized; the fault identification model is a gating circulation network model.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
acquiring a sound data set of the gas-insulated switchgear to be identified when in operation; the sound data set comprises sound data acquired at a plurality of acquisition positions;
for each sound data, carrying out framing processing on each sound data in the sound data set based on time sequence to obtain frame data;
extracting the sound characteristics of the frame data by adopting a sound characteristic extraction model;
Determining the weight of the sound characteristic of the frame data according to the acquisition position corresponding to the frame data;
inputting the sound characteristics of the frame data and the weights of the sound characteristics into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized; the fault identification model is a gating circulation network model.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring a sound data set of the gas-insulated switchgear to be identified when in operation; the sound data set comprises sound data acquired at a plurality of acquisition positions;
for each sound data, carrying out framing processing on each sound data in the sound data set based on time sequence to obtain frame data;
extracting the sound characteristics of the frame data by adopting a sound characteristic extraction model;
determining the weight of the sound characteristic of the frame data according to the acquisition position corresponding to the frame data;
inputting the sound characteristics of the frame data and the weights of the sound characteristics into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized; the fault identification model is a gating circulation network model.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
acquiring a sound data set of the gas-insulated switchgear to be identified when in operation; the sound data set comprises sound data acquired at a plurality of acquisition positions;
for each sound data, carrying out framing processing on each sound data in the sound data set based on time sequence to obtain frame data;
extracting the sound characteristics of the frame data by adopting a sound characteristic extraction model;
determining the weight of the sound characteristic of the frame data according to the acquisition position corresponding to the frame data;
inputting the sound characteristics of the frame data and the weights of the sound characteristics into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized; the fault identification model is a gating circulation network model.
The gas-insulated switchgear on-line monitoring method, the device, the computer equipment, the storage medium and the computer program product firstly acquire the sound data set of the gas-insulated switchgear to be identified when in operation, the sound data set comprises sound data acquired at a plurality of acquisition positions, and sound information from different positions is acquired, so that the comprehensive understanding of the working state of the gas-insulated switchgear can be enhanced; then, for each sound data, framing each sound data in the sound data set based on time sequence to obtain frame data, and extracting sound characteristics of the frame data by adopting a sound characteristic extraction model; then, according to the corresponding acquisition position of the frame data, determining the weight of the sound characteristic of the frame data, and introducing the information of the acquisition position into the fault recognition process to enable the sound data of different positions to have different influences on the fault recognition result; the voice characteristics and the weights of the voice characteristics of the frame data are input into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized, the fault recognition model is a gating circulation network model, and long-term dependence in time sequence data can be effectively captured by adopting the gating circulation network model, so that the characteristics of the voice data are better modeled, and further a more accurate fault recognition result is obtained. According to the method, through analysis and feature extraction of the sound data of the gas-insulated switchgear acquired at the plurality of acquisition positions, richer and diversified feature representations can be obtained, interference information in the sound data can be reduced, and whether the equipment has faults or not can be judged more accurately by combining the learning ability of the fault identification model, so that the fault identification accuracy of the gas-insulated switchgear is improved.
Drawings
FIG. 1 is a flow chart of an on-line monitoring method of a gas insulated switchgear in one embodiment;
FIG. 2 is a flow chart of an on-line monitoring method of a gas insulated switchgear in another embodiment;
FIG. 3 is a schematic diagram of a gating loop unit in a fault identification model in one embodiment;
FIG. 4 is a block diagram of an on-line monitoring device for a gas insulated switchgear in one embodiment;
fig. 5 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, an on-line monitoring method of a gas-insulated switchgear is provided, where the method is applied to a terminal for illustration, it is understood that the method may also be applied to a server, and may also be applied to a system including the terminal and the server, and implemented through interaction between the terminal and the server. The terminal may be, but is not limited to, various personal computers, notebook computers, smart phones and tablet computers. The server may be implemented as a stand-alone server or as a server cluster composed of a plurality of servers. In this embodiment, the method includes the steps of:
Step S101, acquiring a sound data set of the gas-insulated switchgear to be identified when in operation.
The sound data set comprises sound data acquired at a plurality of acquisition positions.
Illustratively, the gas-insulated switchgear (GAS insulated SWITCHGEAR, abbreviated as GIS) is composed of a circuit breaker, a disconnecting switch, a grounding switch, a transformer, a lightning arrester, a bus, a connecting piece, an outgoing terminal and the like, all of which are enclosed in a metal-grounded shell, and SF6 insulating gas (sulfur hexafluoride gas) with a certain pressure is filled in the metal-grounded shell, so that the gas-insulated switchgear is also called as an SF6 fully-enclosed combined electrical appliance. GIS may cause internal flashover fault due to SF6 gas leakage, external moisture infiltration, existence of conductive impurities, insulator aging, etc. The terminal may collect corresponding sound data in real time when the gas-insulated switchgear is operated by means of sound sensors and the like arranged at a plurality of collecting positions, wherein the sound data may include gas sound, mechanical sound, electrical sound, environmental noise and the like generated when the gas-insulated switchgear is operated. The plurality of acquisition positions may be trained from historical data in advance, and analyzed to determine the most effective acquisition position, wherein the acquisition positions may include positions on the gas-insulated switchgear and positions on similar components of the gas-insulated switchgear.
Step S102, for each sound data, framing each sound data in the sound data set based on time sequence to obtain frame data.
For example, in order to acquire dynamic characteristics of sound data that vary with time, the terminal needs to perform framing processing on the sound data. The framing process is typically 20ms per frame time length, and typically employs overlapping segmentation, i.e., a portion between two adjacent frames that has an overlap, which is typically 50%. Meanwhile, in order to reduce frequency domain energy leakage caused by frame truncation and avoid frequency spectrum distortion caused by mutation of frame data at two ends, the terminal also needs to carry out windowing processing on the frame data by adopting a window function.
Step S103, extracting the sound characteristics of the frame data by adopting a sound characteristic extraction model.
Illustratively, the sound features may be Mel Frequency Cepstral Coefficients (MFCCs), linear Predictive Cepstral Coefficients (LPCCs), and the like. The terminal may extract MFCC features or LPCC features of the frame data using a corresponding acoustic feature extraction model, or may extract other acoustic features using a neural network model. In addition, the extracted features can be directly used as final sound features, or multiple features can be stacked or fused to enhance the diversity and expressive power of the features, for example, the first-order differential MFCCs of the MFCCs are obtained to pay more attention to the dynamic features of the sound data, and the MFCCs and the first-order differential MFCCs are used together as final sound features.
Step S104, determining the weight of the sound characteristic of the frame data according to the acquisition position corresponding to the frame data.
For example, it is necessary to determine in advance the contribution degree of the sound data at different acquisition positions to the fault, and a position correlation analysis may be performed. For example, a correlation or correlation coefficient between the sound feature at each location and the known fault may be calculated. Based on the results of the position correlation analysis, a corresponding weight may be determined for the importance of each acquisition position. The terminal takes the weight corresponding to the predetermined acquisition position as the characteristic weight of the sound characteristic of the frame data.
Step S105, inputting the sound characteristics and the weight of the sound characteristics of the frame data into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized.
The fault identification model is a gating circulation network model.
Illustratively, the terminal first acquires a pre-trained failure recognition model, and inputs the sound features of the frame data and the weights of the sound features into the failure recognition model. Meanwhile, because the fault recognition model is a gating circulation network model, when the fault recognition is carried out, the processing is needed based on the time sequence of the frame data, and the long-term dependency relationship in the time sequence data is effectively captured, so that the characteristics of the sound data are better modeled. The fault recognition model performs weighting processing on the sound features of the frame data of each acquisition position according to the weight of the sound features, and may perform weighting fusion on the sound features of the frame data at each time, or perform weighting fusion on the fault recognition results corresponding to each acquisition position.
In the online monitoring method of the gas-insulated switchgear, firstly, the sound data set of the gas-insulated switchgear to be identified is acquired when in operation, the sound data set comprises sound data acquired at a plurality of acquisition positions, and sound information from different positions is acquired, so that the comprehensive understanding of the working state of the gas-insulated switchgear can be enhanced; then, for each sound data, framing each sound data in the sound data set based on time sequence to obtain frame data, and extracting sound characteristics of the frame data by adopting a sound characteristic extraction model; then, according to the corresponding acquisition position of the frame data, determining the weight of the sound characteristic of the frame data, and introducing the information of the acquisition position into the fault recognition process to enable the sound data of different positions to have different influences on the fault recognition result; the voice characteristics and the weights of the voice characteristics of the frame data are input into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized, the fault recognition model is a gating circulation network model, and long-term dependence in time sequence data can be effectively captured by adopting the gating circulation network model, so that the characteristics of the voice data are better modeled, and further a more accurate fault recognition result is obtained. According to the method, through analysis and feature extraction of the sound data of the gas-insulated switchgear acquired at the plurality of acquisition positions, richer and diversified feature representations can be obtained, interference information in the sound data can be reduced, and whether the equipment has faults or not can be judged more accurately by combining the learning ability of the fault identification model, so that the fault identification accuracy of the gas-insulated switchgear is improved.
In one embodiment, the step S102 performs framing processing on each sound data in the sound data set based on time sequence to obtain frame data, and further includes: cutting head and tail Duan Jingyin data in the sound data to obtain cut sound data; and carrying out framing treatment on the cut sound data by adopting a window function to obtain frame data.
In an exemplary embodiment, before the framing process, the terminal may perform silence detection on the sound data, and cut off the silence data of the first and second segments, specifically, may determine whether the audio is silence by setting an appropriate energy threshold. And preprocessing the collected sound data, including removing a mute section, reducing noise and the like, so as to reduce interference information in the sound data. The window length, which is the number of samples for which the window function is applied within each frame, and the frame shift, which is the number of samples difference between adjacent frames, is then determined, typically in the range of 10-30 milliseconds, and typically half the window length, i.e. 50% overlap. Then, the moving window is slid over the sound data according to the determined window length and frame shift. Sample data within a window is sequentially selected starting from a starting position of the sound data. The window is moved back by the size of the frame shift and the process is repeated until the entire sound data is covered. The selected window function is applied to the sample data within each window, and the window function may be selected from the group consisting of a conventional hanning window, a hamming window, a rectangular window, and the like. By applying a window function to the sample data within each window, it can be smoothly weighted, reducing the effects of edge effects and spectral leakage. After the window function is applied, the windowed sample data within each window is taken as one frame data.
In this embodiment, the quality and continuity of the sound data can be improved by cutting off the silence data of the head and tail sections and windowing, and the edge effect can be reduced and the characteristics of adapting to different sound signals can be adapted by inter-frame overlapping and dynamic frame length adjustment, so that the accuracy of the subsequent fault recognition is improved.
In one embodiment, the step S105 inputs the sound feature and the weight of the sound feature of the frame data into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized, and further includes: according to the weight of the sound characteristics, carrying out fusion processing on the sound characteristics of the frame data at the same time to obtain fusion characteristics of the sound data at each time; and inputting the fusion characteristics into a pre-trained fault recognition model according to the time sequence of the fusion characteristics to obtain a fault recognition result of the gas-insulated switchgear to be recognized.
For example, the terminal may apply a feature weighted fusion method to the sound features of the frame data at the same time to obtain fusion features of the sound data at respective times. Then, the fusion features are input into a pre-trained fault recognition model according to a time sequence, and time sequence modeling is carried out. Among other things, a gated loop network (GRNN) is a model suitable for time series modeling that can capture the evolution and dynamic changes of sound data over time. By using the time series information, the understanding and analyzing ability of the fault recognition model to the sound data can be improved.
In this embodiment, feature fusion is performed through corresponding weights, so that sound features at different acquisition positions can be comprehensively considered, and sensitivity to specific faults is improved. Meanwhile, time sequence modeling is utilized, time sequence information of sound data can be captured, and performance of the fault identification model is improved.
In an embodiment, the inputting the fusion feature into a pre-trained fault recognition model according to the time sequence of the fusion feature to obtain a fault recognition result of the gas-insulated switchgear to be recognized, and further includes: inputting the fusion characteristics into a pre-trained fault recognition model to obtain the normal probability and the abnormal probability of the gas-insulated switchgear to be recognized; and determining a fault recognition result of the gas-insulated switchgear to be recognized according to the normal probability and the abnormal probability.
The terminal inputs the characteristics into a pre-trained fault recognition model, and the model performs classification processing on the gas-insulated switchgear to be recognized to obtain the probability of the gas-insulated switchgear to be recognized to be broken down and the probability of no fault, and the terminal selects the condition with higher probability as the fault recognition result of the gas-insulated switchgear to be recognized. Further, the pre-trained fault recognition model can also obtain a fault recognition result of a fault type, namely, multi-classification training is carried out on the fault recognition model, and each fault type when faults occur and each type when no faults occur are used as the same classification information for training, so that the fault recognition model can directly determine the fault type of the gas-insulated switchgear to be recognized.
In this embodiment, by inputting the extracted sound features into the fault recognition model, the working state (fault type or no fault) of the gas-insulated switchgear to be recognized can be obtained, thereby realizing fault recognition and monitoring of the equipment. The fault detection efficiency of the gas-insulated switchgear can be improved, a user is helped to take measures in time to repair the equipment faults, and the stable operation of the power system is ensured.
In one embodiment, the step S105 inputs the sound feature and the weight of the sound feature of the frame data into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized, and further includes: inputting the sound characteristics of the frame data corresponding to each acquisition position into a pre-trained fault recognition model according to the time sequence of the frame data aiming at each acquisition position to obtain a sub-fault recognition result corresponding to each acquisition position; and determining the fault recognition result of the gas-insulated switchgear to be recognized according to the sub-fault recognition results and the weights of the sound features corresponding to all the acquisition positions.
Illustratively, first, the terminal performs individual failure recognition processing on the sound data obtained for each acquisition position: according to the time sequence of the frame data, inputting the sound characteristics of the frame data corresponding to each acquisition position into a pre-trained fault recognition model to obtain a sub-fault recognition result corresponding to each acquisition position. Then, the terminal synthesizes all sub-fault recognition results: and (3) fusing all sub-fault recognition results by adopting weighted average, voting or other integrated learning methods to obtain the final fault recognition result of the gas-insulated switchgear to be recognized. Namely, a multi-stage identification strategy is adopted to further improve the fault identification performance. And in the first stage of recognition, sub-fault recognition is carried out for each acquisition position, so as to obtain a preliminary fault judgment result. And then, in the second stage of recognition, comprehensively analyzing and judging by combining the sub-fault recognition results and the weights of the sound features corresponding to all the acquisition positions to obtain a final fault recognition result.
In this embodiment, the sub-fault recognition results of each acquisition position are weighted and fused, so that the contribution and weight of different acquisition positions can be comprehensively considered, and the accuracy and applicability of overall fault recognition are improved. The multi-stage identification strategy can improve the fault identification performance through multi-stage analysis and judgment.
In one embodiment, after obtaining the fault recognition result of the gas-insulated switchgear to be recognized in step S105, the method further includes: if the fault identification result is that the gas-insulated switchgear to be identified has a fault, generating a fault report; and sending the fault report to the user terminal.
The terminal generates a corresponding fault report according to the fault identification result. The fault report may include the following information: fault type, time of occurrence of the fault, location of the faulty device, fault level, fault description, etc. The terminal may then send a fault report to the user terminal via network communication, which may take the form of wireless communication, wired communication, etc., to alert the user to handle the fault. In addition, a fault report management and archiving system can be established, so that the generated fault report can be effectively recorded and tracked, and subsequent fault analysis, statistics and decision support are facilitated.
In the embodiment, through generation, transmission and management of the fault report, timely and accurate fault information can be provided for the user, and the user is supported to take corresponding measures for maintenance and management. Meanwhile, the automatic generation and real-time transmission of the fault report can improve the working efficiency.
In one embodiment, as shown in fig. 2, there is also provided another gas-insulated switchgear on-line monitoring method, the method comprising the steps of:
step S201, acquiring a sound data set of the gas-insulated switchgear to be identified when in operation.
Step S202, for each piece of sound data, cutting out the first and last Duan Jingyin data in the sound data, and obtaining cut-out sound data.
Step S203, a window function is adopted to carry out framing processing on the cut sound data, and frame data is obtained.
Step S204, extracting the sound characteristics of the frame data by adopting a sound characteristic extraction model.
Step S205, according to the collection position corresponding to the frame data, the weight of the sound characteristic of the frame data is determined.
Step S206, according to the weight of the sound feature, the sound feature of the frame data at the same time is fused to obtain the fused feature of the sound data at each time.
Step S207, inputting the fusion characteristics into a pre-trained fault recognition model according to the time sequence of the fusion characteristics, and obtaining the normal probability and the abnormal probability of the gas-insulated switchgear to be recognized.
Step S208, inputting the sound characteristics of the frame data corresponding to each acquisition position into a pre-trained fault recognition model according to the time sequence of the frame data for each acquisition position to obtain a sub-fault recognition result corresponding to each acquisition position.
Step S209, determining the normal probability and the abnormal probability of the gas-insulated switchgear to be identified according to the sub-fault identification results and the weights of the sound features corresponding to all the acquisition positions.
Step S210, determining a fault recognition result of the gas-insulated switchgear to be recognized according to the normal probability and the abnormal probability.
Step S211, if the fault identification result is that the gas-insulated switchgear to be identified has a fault, generating a fault report, and sending the fault report to the user terminal.
The sound data set comprises sound data acquired at a plurality of acquisition positions.
The fault identification model is a gating circulation network model.
Illustratively, the above method may be implemented by cloud-edge collaboration. And after the cloud server finishes the training processing of the fault recognition model, the trained fault recognition model is sent to the edge terminal equipment through network communication, and the edge terminal equipment acquires sound data in real time, the trained fault recognition model is directly adopted for fault recognition, and a fault recognition result of the gas-insulated switchgear is obtained. Meanwhile, the edge terminal equipment can upload the sound data and the fault recognition result to the cloud server, and the cloud server can readjust and update the fault recognition model based on fault judgment given by a user later, so that the self-adaptive dynamic update of the fault recognition model is realized. In addition, the cloud server can also have functions of account record, fault alarm, fault statistics and the like, and meets the network security requirement of the power grid. The electronic ledger management is mainly used for managing specific information such as the number, the applicable specification, the year, the use department and the like of equipment, and is convenient for checking and checking equipment assets. The electronic ledgers are finally formed into tables for reference by the manager and plan for the next device management task. The quality of technical equipment of a factory can be improved, the efficiency of the equipment can be fully exerted, the equipment of the factory is ensured to be intact, and good equipment investment benefit is obtained.
Further, as shown in fig. 3, a schematic diagram of a gating cycle unit in the gating cycle network model is shown. Wherein the inputs of the reset gate and the update gate in the gate control circulation unit are the current time step input X t Hidden state H with last time step t-1 The output is calculated from the fully connected layer whose activation function is the sigmoid function. In particular, assuming the number of hidden units is h, a small batch of inputs X for a given time step t t ∈R n X d (number of samples n, number of inputs d) and last time step hidden state H t -1∈R n And x h. Reset gate R t ∈R n X h and update door Z t ∈R n The x h calculation is as follows: r is R t =σ(X t W xr +H t-1 W hr +b r )，Z t =σ(X t W xz +H t-1 W hz +b z ) Wherein W is xr ，W xz ∈R d X h and W hr ，W hz ∈R h X h is a weight parameter, b r ，b z ∈R 1 X h is the deviation parameter.
Next, the gating loop unit will calculate candidate hidden states to assist later hidden state calculations. The output of the reset gate of the current time step is multiplied by the hidden state of the previous time step by element (the sign is as #). If the value of the element in the reset gate is close to 0, this means that the corresponding hidden state element is reset to 0, i.e. the hidden state of the last time step is discarded. If the element value is close to 1, this indicates that the hidden state of the last time step is preserved. Then, the result of the multiplication by element is connected with the input of the current time step, and then the candidate hidden state is calculated through the full connection layer containing the activation function tanh. Tool with For the body, candidate hidden states H-T in time step t t ∈R n The x h calculation is: H-H t =tanh(X t W xh +(R t ⊙H t-1 )W hh +b h ) Wherein W is xh ∈R d X h and W hh ∈R h X h is a weight parameter, b h ∈R 1 X h is the deviation parameter. From the above formula, it can be seen that the reset gate controls how the hidden state of the previous time step flows into the candidate hidden state of the current time step. The hidden state of the previous time step may include all the history information of the time sequence cut to the previous time step. Thus, the reset gate may be used to discard historical information that is not relevant to the prediction.
Finally, hidden state H of time step t t ∈R n X h calculation uses the update gate Z of the current time step t To conceal the state H from the previous time step t-1 And candidate hidden states H-H of the current time step t And (3) combining: h t =Z t ⊙H t-1 +(1-Z t )⊙H~ t 。
It should be noted that the update gate may control how the hidden state should be updated by the candidate hidden state containing the current time step information, provided that the update gate is updated at time steps t 'to t (t'<t) is always approximately 1. Then the input information between time steps t' to t hardly flows into the hidden state H of time step t t . In practice this can be seen as the hidden state H at an earlier instant t′-1 The passing time is always saved and passed to the current time step t. The method can effectively solve the gradient attenuation problem in the cyclic neural network and better capture the dependency relationship with larger time step distance in the time sequence.
In the embodiment, firstly, a sound data set of the gas-insulated switchgear to be identified is obtained when the gas-insulated switchgear works, the sound data set comprises sound data acquired at a plurality of acquisition positions, sound information from different positions is obtained, and comprehensive understanding of the working state of the gas-insulated switchgear can be enhanced; then, for each sound data, framing each sound data in the sound data set based on time sequence to obtain frame data, and extracting sound characteristics of the frame data by adopting a sound characteristic extraction model; then, according to the corresponding acquisition position of the frame data, determining the weight of the sound characteristic of the frame data, and introducing the information of the acquisition position into the fault recognition process to enable the sound data of different positions to have different influences on the fault recognition result; the voice characteristics and the weights of the voice characteristics of the frame data are input into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized, the fault recognition model is a gating circulation network model, and long-term dependence in time sequence data can be effectively captured by adopting the gating circulation network model, so that the characteristics of the voice data are better modeled, and further a more accurate fault recognition result is obtained. According to the method, through analysis and feature extraction of the sound data of the gas-insulated switchgear acquired at the plurality of acquisition positions, richer and diversified feature representations can be obtained, interference information in the sound data can be reduced, and whether the equipment has faults or not can be judged more accurately by combining the learning ability of the fault identification model, so that the fault identification accuracy of the gas-insulated switchgear is improved.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides an online monitoring device for the gas-insulated switchgear, which is used for realizing the online monitoring method for the gas-insulated switchgear. The implementation scheme of the device for solving the problem is similar to that described in the method, so the specific limitation of the embodiment of the online monitoring device for the gas-insulated switchgear provided below can be referred to the limitation of the online monitoring method for the gas-insulated switchgear hereinabove, and will not be repeated here.
In one embodiment, as shown in fig. 4, there is provided an on-line monitoring apparatus for a gas-insulated switchgear, comprising: a sound acquisition module 401, a framing processing module 402, a feature extraction module 403, a weight determination module 404, and a result determination module 405, wherein:
a sound acquisition module 401, configured to acquire a sound data set of the gas-insulated switchgear to be identified when the gas-insulated switchgear is operating; the sound data set comprises sound data acquired at a plurality of acquisition positions;
a framing processing module 402, configured to perform framing processing on each sound data in the sound data set based on a time sequence for each sound data to obtain frame data;
a feature extraction module 403, configured to extract a sound feature of the frame data by using a sound feature extraction model;
the weight determining module 404 is configured to determine a weight of a sound feature of the frame data according to an acquisition position corresponding to the frame data;
the result determining module 405 is configured to input the sound feature and the weight of the sound feature of the frame data into a pre-trained fault recognition model, so as to obtain a fault recognition result of the gas-insulated switchgear to be recognized; the fault recognition model is a gating loop network model.
In one embodiment, the framing processing module 402 is further configured to cut out the first and second Duan Jingyin data in the sound data, so as to obtain cut-out sound data; and carrying out framing treatment on the cut sound data by adopting a window function to obtain frame data.
In one embodiment, the result determining module 405 is further configured to perform fusion processing on the sound features of the frame data at the same time according to the weights of the sound features, so as to obtain fusion features of the sound data at each time; and inputting the fusion characteristics into a pre-trained fault recognition model according to the time sequence of the fusion characteristics to obtain a fault recognition result of the gas-insulated switchgear to be recognized.
In one embodiment, the result determining module 405 is further configured to input the fusion feature into a pre-trained fault recognition model, so as to obtain a normal probability and an abnormal probability of the gas-insulated switchgear to be recognized; and determining a fault recognition result of the gas-insulated switchgear to be recognized according to the normal probability and the abnormal probability.
In one embodiment, the result determining module 405 is further configured to input, for each acquisition location, according to a time sequence of the frame data, a sound feature of the frame data corresponding to each acquisition location into a pre-trained fault recognition model, so as to obtain a sub-fault recognition result corresponding to each acquisition location; and determining the fault recognition result of the gas-insulated switchgear to be recognized according to the sub-fault recognition results and the weights of the sound features corresponding to all the acquisition positions.
In one embodiment, the online monitoring device of gas-insulated switchgear further includes a report generating module, configured to generate a fault report when the fault identification result indicates that the gas-insulated switchgear to be identified has a fault; and sending the fault report to the user terminal.
The modules in the gas-insulated switchgear on-line monitoring device can be all or partially realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input means. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program, when executed by a processor, implements a method for on-line monitoring of a gas insulated switchgear. The display unit of the computer device is used for forming a visual picture, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be a key, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as Static Random access memory (Static Random access memory AccessMemory, SRAM) or dynamic Random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A method for on-line monitoring of a gas insulated switchgear, the method comprising:
acquiring a sound data set of the gas-insulated switchgear to be identified when in operation; the sound data set comprises sound data acquired at a plurality of acquisition positions;
for each sound data, carrying out framing processing on each sound data in the sound data set based on time sequence to obtain frame data;
Extracting the sound characteristics of the frame data by adopting a sound characteristic extraction model; the sound features are Mel frequency cepstrum coefficients and first-order differential Mel frequency cepstrum coefficients;
determining the weight of the sound characteristic of the frame data according to the acquisition position corresponding to the frame data; the weight of the sound characteristic is obtained by carrying out correlation analysis on the acquisition position;
inputting the sound characteristics of the frame data and the weights of the sound characteristics into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized; the fault identification model is a gating circulation network model;
the step of inputting the sound characteristics of the frame data and the weights of the sound characteristics into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized, wherein the step of obtaining the fault recognition result of the gas-insulated switchgear to be recognized comprises the following steps:
inputting sound characteristics of frame data corresponding to each acquisition position into a pre-trained fault recognition model according to the time sequence of the frame data aiming at each acquisition position to obtain a sub-fault recognition result corresponding to each acquisition position;
and determining the fault recognition result of the gas-insulated switchgear to be recognized according to the sub-fault recognition results corresponding to all the acquisition positions and the weights of the sound features.
2. The method of claim 1, wherein framing the sound data based on a time sequence to obtain frame data comprises:
cutting head and tail Duan Jingyin data in the sound data to obtain cut sound data;
and carrying out framing processing on the cut sound data by adopting a window function to obtain frame data.
3. The method of claim 1, wherein the sound data comprises at least gas sound data, mechanical sound data, electrical sound data, and ambient noise data.
4. The method according to claim 1, wherein the plurality of acquisition locations comprises at least a location on the gas-insulated switchgear to be identified and a location on a nearby component of the gas-insulated switchgear to be identified.
5. The method according to claim 1, further comprising, after obtaining the result of fault identification of the gas-insulated switchgear to be identified:
if the fault identification result is that the gas-insulated switchgear to be identified has a fault, generating a fault report;
and sending the fault report to the user terminal.
6. An on-line monitoring device for gas insulated switchgear, the device comprising:
the sound acquisition module is used for acquiring a sound data set of the gas-insulated switchgear to be identified when the gas-insulated switchgear works; the sound data set comprises sound data acquired at a plurality of acquisition positions;
the frame processing module is used for carrying out frame processing on each sound data in the sound data set based on time sequence to obtain frame data;
the feature extraction module is used for extracting the sound features of the frame data by adopting a sound feature extraction model; the sound features are Mel frequency cepstrum coefficients and first-order differential Mel frequency cepstrum coefficients;
the weight determining module is used for determining the weight of the sound characteristic of the frame data according to the acquisition position corresponding to the frame data; the weight of the sound characteristic is obtained by carrying out correlation analysis on the acquisition position;
the result determining module is used for inputting the sound characteristics of the frame data and the weights of the sound characteristics into a pre-trained fault recognition model to obtain a fault recognition result of the gas-insulated switchgear to be recognized; the fault identification model is a gating circulation network model;
The result determining module is further configured to input, for each acquisition position, according to the time sequence of the frame data, sound features of frame data corresponding to each acquisition position into a pre-trained fault recognition model, so as to obtain a sub-fault recognition result corresponding to each acquisition position; and determining the fault recognition result of the gas-insulated switchgear to be recognized according to the sub-fault recognition results corresponding to all the acquisition positions and the weights of the sound features.
7. The apparatus of claim 6, wherein the framing processing module is further configured to cut out first and last Duan Jingyin data in the sound data to obtain cut-out sound data; and carrying out framing treatment on the cut sound data by adopting a window function to obtain frame data.
8. The device according to claim 6, wherein the gas-insulated switchgear on-line monitoring device further comprises a report generating module for generating a fault report in case the fault recognition result is that the gas-insulated switchgear to be recognized is faulty; and sending the fault report to the user terminal.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 5 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310939123.0A CN116665711B (en) | 2023-07-26 | 2023-07-26 | Gas-insulated switchgear on-line monitoring method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310939123.0A CN116665711B (en) | 2023-07-26 | 2023-07-26 | Gas-insulated switchgear on-line monitoring method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116665711A CN116665711A (en) | 2023-08-29 |
| CN116665711B true CN116665711B (en) | 2024-01-12 |
Family
ID=87715650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310939123.0A Active CN116665711B (en) | 2023-07-26 | 2023-07-26 | Gas-insulated switchgear on-line monitoring method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116665711B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117233589A (en) * | 2023-09-14 | 2023-12-15 | 中国南方电网有限责任公司超高压输电公司广州局 | GIS equipment fault diagnosis method and device, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110867196A (en) * | 2019-12-03 | 2020-03-06 | 桂林理工大学 | Machine equipment state monitoring system based on deep learning and voice recognition |
| CN114859269A (en) * | 2022-05-13 | 2022-08-05 | 杭州巨骐信息科技股份有限公司 | Cable fault diagnosis method based on voiceprint recognition technology |
| CN115240687A (en) * | 2022-06-30 | 2022-10-25 | 国网安徽省电力有限公司电力科学研究院 | GIS voiceprint signal acquisition device |
| CN115684911A (en) * | 2022-11-03 | 2023-02-03 | 国网山东省电力公司菏泽供电公司 | GIS operating mechanism fault diagnosis method and system based on independent component analysis |
| CN116127383A (en) * | 2022-10-18 | 2023-05-16 | 南京上铁电子工程有限公司 | Fault detection method and device, electronic equipment and storage medium |
-
2023
- 2023-07-26 CN CN202310939123.0A patent/CN116665711B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110867196A (en) * | 2019-12-03 | 2020-03-06 | 桂林理工大学 | Machine equipment state monitoring system based on deep learning and voice recognition |
| CN114859269A (en) * | 2022-05-13 | 2022-08-05 | 杭州巨骐信息科技股份有限公司 | Cable fault diagnosis method based on voiceprint recognition technology |
| CN115240687A (en) * | 2022-06-30 | 2022-10-25 | 国网安徽省电力有限公司电力科学研究院 | GIS voiceprint signal acquisition device |
| CN116127383A (en) * | 2022-10-18 | 2023-05-16 | 南京上铁电子工程有限公司 | Fault detection method and device, electronic equipment and storage medium |
| CN115684911A (en) * | 2022-11-03 | 2023-02-03 | 国网山东省电力公司菏泽供电公司 | GIS operating mechanism fault diagnosis method and system based on independent component analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116665711A (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112348660B (en) | Method and device for generating risk warning information and electronic equipment | |
| JP6355683B2 (en) | Risk early warning method, apparatus, storage medium, and computer program | |
| CN116665711B (en) | Gas-insulated switchgear on-line monitoring method and device and computer equipment | |
| CN114285728A (en) | Prediction model training method, flow prediction method, device and storage medium | |
| WO2023216553A1 (en) | Multi-fault diagnosis method for power distribution network, and system | |
| CN113886181B (en) | Dynamic threshold prediction method, device and medium applied to AIOps fault early warning | |
| CN116665710B (en) | Fault identification method and device for gas-insulated switchgear and computer equipment | |
| Lu et al. | Affine projection algorithm-based high-order error power for partial discharge denoising in power cables | |
| CN110263944A (en) | A kind of multivariable failure prediction method and device | |
| CN113343467A (en) | Electric power system elasticity evaluation method and system under extreme disaster condition | |
| KR102389439B1 (en) | RNN based partial discharge detection apparatus and method in gas-insulated switchgear | |
| Avila et al. | Bayesian restoration of audio signals degraded by impulsive noise modeled as individual pulses | |
| CN113869205A (en) | Object detection method and device, electronic equipment and storage medium | |
| CN116701031A (en) | Root cause model training method, analysis method and device in micro-service system | |
| CN110704614B (en) | Information processing method and device for predicting user group type in application | |
| KR20220064604A (en) | Temperature estimation system | |
| CN115389812B (en) | Artificial neural network short-circuit current zero prediction method and prediction terminal | |
| Tendijck et al. | A model for the directional evolution of severe ocean storms | |
| CN115906942A (en) | Arc fault identification method, device, equipment and readable storage medium | |
| CN113240098B (en) | Fault prediction method and device based on hybrid gated neural network and storage medium | |
| CN114595746A (en) | Method, device, equipment and storage medium for classifying power distribution network fault reasons | |
| CN113766405A (en) | Method and device for detecting noise of loudspeaker, electronic equipment and storage medium | |
| CN109358222A (en) | Power Quality Transient event recognition method and system | |
| CN117667495B (en) | Association rule and deep learning integrated application system fault prediction method | |
| Aiswarya et al. | LSTM Based Approach for Timely Detection of Gradual Development of Electrical Fault in Power System |
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 |