CN117590223B - Online monitoring system and method for circuit breaker - Google Patents
Online monitoring system and method for circuit breaker Download PDFInfo
- Publication number
- CN117590223B CN117590223B CN202410071994.XA CN202410071994A CN117590223B CN 117590223 B CN117590223 B CN 117590223B CN 202410071994 A CN202410071994 A CN 202410071994A CN 117590223 B CN117590223 B CN 117590223B
- Authority
- CN
- China
- Prior art keywords
- time sequence
- current
- training
- feature
- voltage
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000012549 training Methods 0.000 claims description 172
- 239000013598 vector Substances 0.000 claims description 114
- 238000005728 strengthening Methods 0.000 claims description 52
- 239000011159 matrix material Substances 0.000 claims description 45
- 238000010586 diagram Methods 0.000 claims description 43
- 230000004927 fusion Effects 0.000 claims description 26
- 238000000605 extraction Methods 0.000 claims description 22
- 238000013527 convolutional neural network Methods 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 10
- 238000010219 correlation analysis Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 8
- 238000004458 analytical method Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000011897 real-time detection Methods 0.000 abstract description 4
- 238000009826 distribution Methods 0.000 description 13
- 238000012423 maintenance Methods 0.000 description 10
- 230000002159 abnormal effect Effects 0.000 description 9
- 238000007689 inspection Methods 0.000 description 8
- 230000005856 abnormality Effects 0.000 description 6
- 230000000737 periodic effect Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
- G01R31/3271—Testing of circuit interrupters, switches or circuit-breakers of high voltage or medium voltage devices
- G01R31/3272—Apparatus, systems or circuits therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses an on-line monitoring system and a method thereof for a circuit breaker, which are characterized in that the current, voltage and temperature data of the circuit breaker are monitored and collected in real time, and a data processing and analyzing technology is introduced at the rear end to carry out time sequence collaborative analysis on each data parameter of the circuit breaker so as to carry out real-time detection on the running state of the circuit breaker.
Description
Technical Field
The invention relates to the technical field of intelligent online monitoring, in particular to an online monitoring system and method of a circuit breaker.
Background
The circuit breaker has the advantages of complex structure, severe working environment, high operating frequency and the like, and the circuit breaker has high failure rate, so that once the circuit breaker fails, the circuit breaker can cause instability and even damage of a power system, thereby causing serious economic loss and social influence. Therefore, it is critical that the circuit breaker be effectively monitored to discover anomalies and faults in time.
However, the conventional circuit breaker monitoring system mainly relies on manual inspection and periodic maintenance, and this method has the following problems: the manual inspection requires a lot of time and manpower resources, and the running state of the circuit breaker cannot be monitored in real time. Periodic maintenance may result in unnecessary power outages and production interruptions, as well as failure to discover the breaker's hidden danger and failure in time. Manual inspection and periodic maintenance cannot provide comprehensive analysis and judgment of the operating state of the circuit breaker, and some tiny abnormal signals are easy to ignore.
Accordingly, an optimized circuit breaker on-line monitoring system is desired.
Disclosure of Invention
The embodiment of the invention provides an on-line monitoring system and a method thereof for a circuit breaker, which are used for carrying out real-time monitoring and acquisition on current, voltage and temperature data of the circuit breaker, introducing a data processing and analyzing technology at the rear end to carry out time sequence collaborative analysis on each data parameter of the circuit breaker so as to carry out real-time detection on the running state of the circuit breaker.
The embodiment of the invention also provides an on-line monitoring system of the circuit breaker, which comprises:
The data acquisition module is used for acquiring current values, voltage values and temperature values of the monitored circuit breaker at a plurality of preset time points in a preset time period;
The data time sequence arrangement module is used for respectively arranging the current values, the voltage values and the temperature values of the plurality of preset time points into a current time sequence input vector, a voltage time sequence input vector and a temperature time sequence input vector according to the time dimension;
The current-voltage time sequence correlation characteristic extraction module is used for carrying out time sequence correlation analysis on the current time sequence input vector and the voltage time sequence input vector through a current-voltage time sequence correlation mode characteristic extractor based on a deep neural network model so as to obtain a current-voltage time sequence correlation characteristic diagram;
The temperature time sequence feature extraction module is used for extracting time sequence features of the temperature time sequence input vector to obtain a temperature time sequence feature vector;
The multi-mode time sequence feature guiding and fusing module is used for carrying out multi-mode feature time sequence guiding and fusing on the current-voltage time sequence associated feature map and the temperature time sequence feature vector so as to obtain temperature time sequence feature guiding and strengthening current-voltage time sequence associated features;
And the circuit breaker working state detection module is used for guiding the intensified current-voltage time sequence correlation characteristic based on the temperature time sequence characteristic and determining whether the working state of the monitored circuit breaker is normal or not.
The embodiment of the invention also provides an on-line monitoring method of the circuit breaker, which comprises the following steps:
Acquiring current values, voltage values and temperature values of a monitored circuit breaker at a plurality of preset time points in a preset time period;
Arranging the current values, the voltage values and the temperature values of the plurality of preset time points into a current time sequence input vector, a voltage time sequence input vector and a temperature time sequence input vector according to time dimensions respectively;
Performing time sequence correlation analysis on the current time sequence input vector and the voltage time sequence input vector through a current-voltage time sequence correlation mode feature extractor based on a deep neural network model to obtain a current-voltage time sequence correlation feature map;
extracting time sequence characteristics of the temperature time sequence input vector to obtain a temperature time sequence characteristic vector;
Carrying out multi-mode characteristic time sequence guiding fusion on the current-voltage time sequence related characteristic diagram and the temperature time sequence characteristic vector to obtain a temperature time sequence characteristic guiding strengthening current-voltage time sequence related characteristic;
and based on the temperature time sequence characteristic, guiding the intensified current-voltage time sequence correlation characteristic, and determining whether the working state of the monitored circuit breaker is normal.
The beneficial effects of the invention are as follows:
According to the invention, the current, voltage and temperature data of the circuit breaker are monitored and collected in real time, and the data processing and analyzing technology is introduced into the rear end to perform time sequence collaborative analysis on each data parameter of the circuit breaker so as to perform real-time detection on the operating state of the circuit breaker.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
Fig. 1 is a block diagram of an on-line monitoring system of a circuit breaker according to an embodiment of the present invention.
Fig. 2 is a flowchart of an on-line monitoring method of a circuit breaker according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a system architecture of an on-line monitoring method of a circuit breaker according to an embodiment of the present invention.
Fig. 4 is an application scenario diagram of an on-line monitoring system of a circuit breaker according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
Unless defined otherwise, all technical and scientific terms used in the embodiments of the application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application.
In describing embodiments of the present application, unless otherwise indicated and limited thereto, the term "connected" should be construed broadly, for example, it may be an electrical connection, or may be a communication between two elements, or may be a direct connection, or may be an indirect connection via an intermediate medium, and it will be understood by those skilled in the art that the specific meaning of the term may be interpreted according to circumstances.
It should be noted that, the term "first\second\third" related to the embodiment of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that embodiments of the application described herein may be practiced in sequences other than those illustrated or described herein.
A circuit breaker is an electrical device for protecting an electrical power system and electrical equipment, and is mainly used to break a current in a circuit to prevent damage or accidents caused by overload, short-circuit or other faults of the circuit. The circuit breaker plays an important role in a power system, and can rapidly and reliably cut off a circuit so as to protect safety of power equipment and personnel.
The working principle of the circuit breaker is based on the principles of electromagnetic attraction and electromagnetic release, when current passes through the circuit breaker, a magnetic field generated by the current can enable an electromagnet in the circuit breaker to generate attraction force, and contacts of the circuit breaker are closed, so that the current can normally pass through. When overload or fault occurs in the circuit, the current can be rapidly increased and exceeds the rated current value which can be born by the circuit breaker, the circuit breaker can be automatically triggered at the moment, and the contact is opened and the circuit is cut off by releasing the attraction force of the electromagnet so as to prevent the current from continuously flowing, thereby protecting the safety of the power equipment and the circuit.
The circuit breaker is an important device in a power system, is used for protecting a circuit from overload, short circuit, ground fault and other abnormal conditions, plays a role of a switch in the circuit, and can break off current flow in the circuit so as to prevent dangerous conditions such as equipment damage in the circuit and fire.
Efficient monitoring of circuit breakers is critical to the safe operation of power systems. Circuit breakers are typically comprised of mechanical components, electrical components, and control systems, having complex structures and operating principles that often operate under harsh environmental conditions, such as high temperatures, high humidity, corrosive gases, etc., which can cause the circuit breaker to fail. Circuit breakers often switch and break electrical circuits in electrical power systems, particularly when the load changes are large or faults occur, such high frequency operation increasing the risk of wear and failure of the circuit breaker. Once the breaker fails, the power system may be unstable or even damaged, and serious consequences such as power failure, equipment damage, production interruption and the like are caused, so that economic loss can be brought to enterprises and users, and normal operation of society can be negatively influenced.
In order to discover the abnormality and the fault of the circuit breaker in time so as to ensure the safe and stable operation of the power system, the circuit breaker needs to be effectively monitored. Traditional breaker monitoring systems rely mainly on manual inspection and periodic maintenance to ensure the normal operation of the breaker. However, this approach has problems that limit the ability to monitor the breaker status in real time and predict faults.
The traditional circuit breaker monitoring needs to dispatch maintenance personnel regularly to carry out inspection, consumes a large amount of time and manpower resources, and particularly for a large-scale power system, the inspection workload is huge and the efficiency is low, so that the cost is increased, the inspection frequency is low, the coverage range is not complete, and potential problems are delayed to be found. The manual inspection can only rely on experience and observation to judge whether the circuit breaker is abnormal, the method has the risk of delaying the discovery of problems, and the expansion of faults and serious consequences can be caused, and the real-time monitoring of the running state of the circuit breaker is important for timely discovering abnormal conditions and predicting fault risks. Conventional periodic maintenance is typically performed at regular intervals, which may result in unnecessary outages and production breaks, and businesses and users may therefore suffer economic losses. In addition, the hidden danger and faults of the circuit breaker cannot be found in time by regular maintenance, and the faults can be generated and expanded.
To address these issues, it is desirable to introduce a more optimized circuit breaker on-line monitoring system. The system can monitor and collect key parameters of the circuit breaker, such as current, voltage, temperature and the like in real time by using advanced sensor and data processing technology. Meanwhile, through data analysis and pattern recognition technology, fault prediction and timely abnormality discovery can be realized, so that the monitoring efficiency can be improved, the maintenance cost can be reduced, and the safe operation of the power system can be ensured.
In one embodiment of the present invention, fig. 1 is a block diagram of an on-line monitoring system of a circuit breaker according to an embodiment of the present invention. As shown in fig. 1, an on-line monitoring system 100 of a circuit breaker according to an embodiment of the present invention includes: a data acquisition module 110, configured to acquire current values, voltage values, and temperature values of the monitored circuit breaker at a plurality of predetermined time points within a predetermined time period; a data timing arrangement module 120, configured to arrange the current values, the voltage values, and the temperature values at the plurality of predetermined time points into a current timing input vector, a voltage timing input vector, and a temperature timing input vector according to a time dimension, respectively; a current-voltage timing correlation feature extraction module 130, configured to perform timing correlation analysis on the current timing input vector and the voltage timing input vector by using a current-voltage timing correlation pattern feature extractor based on a deep neural network model to obtain a current-voltage timing correlation feature map; a temperature time sequence feature extraction module 140, configured to perform time sequence feature extraction on the temperature time sequence input vector to obtain a temperature time sequence feature vector; the multi-mode time sequence feature guiding and fusing module 150 is configured to perform multi-mode time sequence feature guiding and fusing on the current-voltage time sequence associated feature map and the temperature time sequence feature vector to obtain a temperature time sequence feature guiding and strengthening current-voltage time sequence associated feature; the circuit breaker operating state detection module 160 is configured to guide the enhanced current-voltage timing correlation characteristic based on the temperature timing characteristic, and determine whether the operating state of the monitored circuit breaker is normal.
In the data acquisition module 110, the current value, the voltage value and the temperature value of the monitored circuit breaker at a plurality of preset time points in a preset time period are acquired, so that the accuracy and the reliability of the data acquisition equipment and the accuracy of data acquisition at the preset time points are ensured. Thus, accurate breaker parameter data can be provided, and a basis is provided for subsequent analysis and judgment. In the data timing arrangement module 120, the current values, the voltage values, and the temperature values at the plurality of predetermined time points are arranged into a current timing input vector, a voltage timing input vector, and a temperature timing input vector according to a time dimension, so as to ensure that the data are arranged in a correct time sequence. In this way, the raw data is consolidated into a conveniently processed time series data form for subsequent time series analysis and feature extraction. In the current-voltage timing correlation feature extraction module 130, a current timing input vector and a voltage timing input vector are subjected to timing correlation analysis using a current-voltage timing correlation pattern feature extractor based on a deep neural network model. And selecting a proper deep neural network model and a training algorithm to extract accurate current-voltage time sequence correlation characteristics so as to analyze the correlation between current and voltage and provide useful characteristic information for subsequent state detection. In the temperature time sequence feature extraction module 140, time sequence feature extraction is performed on the temperature time sequence input vector, and a suitable feature extraction method, such as statistical feature, frequency domain feature or time domain feature, is selected to capture key features of temperature variation. In this way, important features of temperature variation are extracted for subsequent status determination. In the multi-mode time sequence feature guiding fusion module 150, multi-mode time sequence guiding fusion is performed on the current-voltage time sequence associated feature map and the temperature time sequence feature vector, a proper feature fusion method is designed, and features of different modes are effectively fused, so that accuracy and robustness of state detection are improved. Thus, the time sequence characteristics of current, voltage and temperature are comprehensively utilized, and the capability of state detection is enhanced. In the circuit breaker operating state detection module 160, the enhanced current-voltage timing correlation characteristic is guided based on the temperature timing characteristic to determine whether the operating state of the monitored circuit breaker is normal. And establishing a proper state detection algorithm, improving detection accuracy by using a characteristic guide strengthening method, and setting a proper threshold or rule to judge the working state of the circuit breaker so as to monitor the working state of the circuit breaker in real time, discover abnormal conditions in time and take corresponding measures.
Aiming at the technical problems, the technical concept of the application is that the current, voltage and temperature data of the circuit breaker are monitored and collected in real time, and the data processing and analyzing technology is introduced into the rear end to carry out time sequence collaborative analysis on each data parameter of the circuit breaker so as to carry out real-time detection on the running state of the circuit breaker.
Specifically, in the technical scheme of the application, firstly, current values, voltage values and temperature values of a monitored circuit breaker at a plurality of preset time points in a preset time period are obtained. Then, considering that the current value, the voltage value and the temperature value of the monitored circuit breaker have time sequence dynamic change rules respectively in the time dimension, that is, the current value, the voltage value and the temperature value of the plurality of preset time points have association relations respectively in the time dimension. Therefore, in order to be able to capture the time-series variation pattern and trend of each data parameter about the monitored circuit breaker, it is necessary to further arrange the current value, the voltage value and the temperature value at the plurality of predetermined time points into a current time-series input vector, a voltage time-series input vector and a temperature time-series input vector, respectively, in a time dimension, so as to integrate the distribution information of the current value, the voltage value and the temperature value in time series, respectively.
In power systems, current and voltage are closely related, and the pattern of variation and phase relationship between them can provide important clues about the operating state of the circuit breaker. Therefore, in order to capture the time sequence correlation information between the current and the voltage, in the technical scheme of the application, the current time sequence input vector and the voltage time sequence input vector are further subjected to correlation coding to obtain a current-voltage time sequence correlation matrix. In particular, here, the current-voltage timing correlation matrix may reflect a timing relationship between current and voltage, such as their waveform shape, amplitude variation, phase difference, and the like. By extracting and analyzing the characteristics of the correlation matrix, the complex relation between the current and the voltage can be revealed, and whether the working state of the circuit breaker is normal or not can be judged.
In a specific embodiment of the present application, the current-voltage timing related feature extraction module includes: a current-voltage time sequence association coding unit, configured to perform association coding on the current time sequence input vector and the voltage time sequence input vector to obtain a current-voltage time sequence association matrix; and the current-voltage time sequence feature extraction unit is used for enabling the current-voltage time sequence correlation matrix to pass through a current-voltage time sequence correlation mode feature extractor based on a convolutional neural network model so as to obtain the current-voltage time sequence correlation feature map.
And then, carrying out feature mining on the current-voltage time sequence correlation matrix by a current-voltage time sequence correlation pattern feature extractor based on a convolutional neural network model so as to extract time sequence pattern correlation feature information of the current and the voltage, thereby obtaining a current-voltage time sequence correlation feature map.
Then, considering that the temperature value of the monitored circuit breaker also has certain regularity in time sequence, in order to analyze the temperature time sequence change condition, in the technical scheme of the application, the temperature time sequence input vector is subjected to feature mining in a time sequence feature extractor based on a one-dimensional convolution layer so as to extract time sequence feature information of the temperature, thereby obtaining a temperature time sequence feature vector.
In a specific embodiment of the present application, the temperature timing feature extraction module is configured to: and the temperature time sequence input vector passes through a time sequence feature extractor based on a one-dimensional convolution layer to obtain a temperature time sequence feature vector.
Further, in the on-line monitoring system of the circuit breaker, current and voltage are main monitoring parameters, and temperature is an important auxiliary parameter. The current-voltage timing correlation feature map may provide useful information about the operating state of the circuit breaker, while the temperature timing feature vector may provide clues about the thermal state and potential faults of the circuit breaker. Therefore, in order to enhance the expression capability of the current-voltage time sequence correlation characteristic diagram and guide the attention to the temperature time sequence, in the technical scheme of the application, the current-voltage time sequence correlation characteristic diagram and the temperature time sequence characteristic vector are further led to strengthen the current-voltage time sequence correlation characteristic diagram through a multi-mode characteristic time sequence fusion module based on MetaNet so as to obtain the temperature time sequence characteristic guide. It should be understood that, by the processing of the multi-modal feature timing fusion module based on MetaNet, the current-voltage timing correlation feature map and the temperature timing feature vector may be multi-modal fused to obtain a comprehensive feature representation. The fused characteristic representation can comprehensively consider the relation among current, voltage and temperature, so that the working state of the circuit breaker is more comprehensively described. Specifically, the temperature time sequence characteristic vector can be guided and intensified to enable the current-voltage time sequence correlation characteristic diagram to pay attention to the temperature time sequence change condition of the circuit breaker, so that the sensitivity to the abnormal state of the circuit breaker is further improved.
In a specific embodiment of the present application, the multi-mode timing feature guidance fusion module is configured to: and passing the current-voltage time sequence correlation characteristic diagram and the temperature time sequence characteristic vector through a MetaNet-based multi-mode characteristic time sequence fusion module to obtain a temperature time sequence characteristic guiding strengthening current-voltage time sequence correlation characteristic diagram.
And then, the temperature time sequence characteristic is led to strengthen the current-voltage time sequence related characteristic diagram to pass through a classifier so as to obtain a classification result, wherein the classification result is used for indicating whether the working state of the monitored circuit breaker is normal or not. That is, the current and voltage time sequence of the circuit breaker after the temperature time sequence change characteristic guide reinforcement of the circuit breaker is utilized to carry out classification processing in cooperation with the associated characteristic information, so as to judge whether the working state of the circuit breaker is normal. Therefore, the running state of the circuit breaker can be obtained in real time, so that the abnormality and the fault of the circuit breaker can be found in time, corresponding measures are taken for repairing or maintaining, and the safe and stable running of the power system is ensured.
In a specific embodiment of the present application, the circuit breaker operating state detection module is configured to: and leading the temperature time sequence characteristic to a strengthening current-voltage time sequence correlation characteristic diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the working state of the monitored circuit breaker is normal or not.
By inputting the feature images into the classifier, whether the working state of the monitored circuit breaker is normal or not can be judged according to the output result of the classifier, and the classifier can learn and identify feature image modes under different working states, such as abnormal states of normal working, overload, short circuit and the like, so that the automatic judgment of the state of the circuit breaker is realized. The classifier can predict the possible fault types of the circuit breaker according to the mode and the trend in the feature map, potential fault risks can be found in advance by training the classifier and predicting by using historical data, and corresponding repair or maintenance measures are adopted to avoid occurrence and expansion of faults.
The characteristic diagram is generated through current, voltage and temperature data acquired in real time, and the characteristic diagram is classified in real time through the classifier, so that the state of the circuit breaker can be monitored in real time, abnormal conditions can be found in time, corresponding measures are taken, and potential safety problems and production interruption are avoided. By comparing the classification result with a preset threshold value, decision support can be automatically performed. For example, when the classification result indicates that the state of the circuit breaker is abnormal, the system can automatically send an alarm or trigger a maintenance process, so that the requirement of manual intervention is reduced, and the response speed and efficiency are improved.
In one embodiment of the present application, the on-line monitoring system of the circuit breaker further includes a training module for training the current-voltage time sequence correlation mode feature extractor based on the convolutional neural network model, the time sequence feature extractor based on the one-dimensional convolutional layer, the multi-mode feature time sequence fusion module based on MetaNet, and the classifier. The training module comprises: the system comprises a training data acquisition unit, a monitoring unit and a control unit, wherein the training data acquisition unit is used for acquiring training data, the training data comprises training current values, training voltage values and training temperature values of a monitored circuit breaker at a plurality of preset time points in a preset time period, and a true value of whether the working state of the monitored circuit breaker is normal or not; the training data time sequence arrangement unit is used for arranging the training current values, the training voltage values and the training temperature values of the plurality of preset time points into training current time sequence input vectors, training voltage time sequence input vectors and training temperature time sequence input vectors according to time dimensions respectively; the training voltage-current time sequence association unit is used for carrying out association coding on the training current time sequence input vector and the training voltage time sequence input vector to obtain a training current-voltage time sequence association matrix; the training current-voltage time sequence correlation characteristic extraction unit is used for enabling the training current-voltage time sequence correlation matrix to pass through the current-voltage time sequence correlation mode characteristic extractor based on the convolutional neural network model so as to obtain a training current-voltage time sequence correlation characteristic diagram; the training temperature time sequence feature extraction unit is used for enabling the training temperature time sequence input vector to pass through the time sequence feature extractor based on the one-dimensional convolution layer to obtain a training temperature time sequence feature vector; the training multi-mode time sequence feature fusion unit is used for enabling the training current-voltage time sequence associated feature map and the training temperature time sequence feature vector to pass through the MetaNet-based multi-mode feature time sequence fusion module to obtain a training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map; the feature optimization unit is used for optimizing the training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map to obtain an optimized training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map; the classification loss unit is used for guiding the optimized training temperature time sequence characteristic to the intensified current-voltage time sequence associated characteristic diagram to pass through the classifier so as to obtain a classification loss function value; the model training unit is used for training the current-voltage time sequence correlation mode feature extractor based on the convolutional neural network model, the time sequence feature extractor based on the one-dimensional convolutional layer, the multi-mode feature time sequence fusion module based on MetaNet and the classifier based on the classification loss function value and through gradient descent direction propagation.
In particular, in the technical scheme of the application, each feature matrix of the training current-voltage time sequence correlation feature map expresses local time domain high order correlation features of full time domain first order correlation of the training current value and the training voltage value, channel distribution of a convolutional neural network model is met among feature matrices, and the training temperature time sequence feature vector expresses one-dimensional time sequence correlation features of training temperature values. In this way, after the training current-voltage time sequence correlation feature map and the training temperature time sequence feature vector pass through the multi-mode feature time sequence fusion module based on MetaNet, the channel distribution of the training current-voltage time sequence correlation feature map can be constrained based on the time sequence correlation feature distribution of training temperature values, so that the training temperature time sequence feature guide strengthening current-voltage time sequence correlation feature map has time sequence correlation in the space distribution dimension in the feature matrix and the channel distribution dimension among the feature matrices.
However, considering the mixed characteristic correlation property of the training temperature time sequence characteristic guiding strengthening current-voltage time sequence correlation characteristic diagram in the channel distribution dimension among characteristic matrixes, the overall characteristic distribution of the training temperature time sequence characteristic guiding strengthening current-voltage time sequence correlation characteristic diagram also has the problem of poor channel dimension characteristic distribution integrity, and the convergence difficulty is caused when the training temperature time sequence characteristic guiding strengthening current-voltage time sequence correlation characteristic diagram converges in a class probability through a classifier. Therefore, the present application preferably firstly performs linear transformation on the training temperature time sequence characteristic guiding intensified current-voltage time sequence correlation characteristic diagram so as to make the width and the height of the characteristic matrix equal, and then performs channel dimension optimization on the converted training temperature time sequence characteristic guiding intensified current-voltage time sequence correlation characteristic diagram.
That is, the feature optimizing unit includes: performing linear transformation on the training temperature time sequence feature guiding strengthening current-voltage time sequence correlation feature map to obtain a converted training temperature time sequence feature guiding strengthening current-voltage time sequence correlation feature map, wherein the width and the height of a feature matrix of the converted training temperature time sequence feature guiding strengthening current-voltage time sequence correlation feature map are equal; and carrying out channel dimension optimization on the converted training temperature time sequence feature-guided intensified current-voltage time sequence associated feature map to obtain an optimized training temperature time sequence feature-guided intensified current-voltage time sequence associated feature map.
In a specific embodiment of the present application, channel dimension optimization is performed on the converted training temperature timing feature-guided enhanced current-voltage timing correlation feature map to obtain an optimized training temperature timing feature-guided enhanced current-voltage timing correlation feature map, including: carrying out channel dimension optimization on the converted training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map by using the following optimization formula to obtain an optimized training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map; wherein, the formula is:
Wherein, And/>The training temperature time sequence characteristic after conversion guides the strengthening current-voltage time sequence associated characteristic diagram to the/>, along the channel directionAnd/>Feature matrix of location, and/>Is a scale-adjusting hyper-parameter,/>Representing the transpose of the matrix,/>Representing matrix multiplication,/>Representing the dot-by-location multiplication of a matrix,/>Representing the per-position addition of matrices,/>Is the/>, along the channel direction, of the time sequence correlation characteristic diagram among the optimized training performance indexesA feature matrix of locations.
Here, predicting, in a high-dimensional feature space, a coupling distribution direction of a local feature distribution of the training temperature time sequence feature-guided enhanced current-voltage time sequence associated feature map along a channel by progressive structured embedding calculation of a feature matrix with channel adjacent distribution of the training temperature time sequence feature-guided enhanced current-voltage time sequence associated feature map, thereby determining, based on a distribution progressive center, a transmission pattern representation generated based on iteration of channel coupling, reconstructing a context relation of the training temperature time sequence feature-guided enhanced current-voltage time sequence associated feature map based on a scene layout of the feature matrix in a manner of refining a projection normalization proposal of the training temperature time sequence feature-guided enhanced current-voltage time sequence associated feature map from bottom to top along the channel dimension, so as to improve channel dimension integrity of the feature representation of the training temperature time sequence feature-guided enhanced current-voltage time sequence associated feature map, improve a convergence effect when the training temperature time sequence feature-guided enhanced current-voltage time sequence associated feature map is subjected to class probability convergence by a classifier, and improve training efficiency and accuracy of classification results. Therefore, the running state of the circuit breaker can be detected in real time, so that the abnormality and the fault of the circuit breaker can be found out in time, corresponding measures are taken for repairing or maintaining the abnormality and the fault, and the safe and stable running of the power system is ensured.
In a specific embodiment of the present application, the classification loss unit includes: a training classification subunit, configured to process the optimized training temperature timing feature-guided enhanced current-voltage timing correlation feature map with a training classification formula using the classifier to generate a training classification result, where the training classification formula is: Wherein/> Representing projection of the optimized training temperature timing feature-guided enhanced current-voltage timing correlation feature map as a vector,/>To/>Is a weight matrix,/>To/>Representing a bias matrix; and a classification loss function value calculation subunit for calculating a cross entropy value between the training classification result and a true value as the classification loss function value.
In summary, the on-line monitoring system 100 of the circuit breaker according to the embodiment of the present invention is illustrated, which can acquire the operation state of the circuit breaker in real time, so as to find out the abnormality and the fault of the circuit breaker in time, and take corresponding measures to repair or maintain, so as to ensure the safe and stable operation of the power system.
As described above, the on-line monitoring system 100 of a circuit breaker according to an embodiment of the present invention may be implemented in various terminal devices, such as a server for on-line monitoring of a circuit breaker, and the like. In one example, the on-line monitoring system 100 of a circuit breaker according to an embodiment of the present invention may be integrated into the terminal device as one software module and/or hardware module. For example, the on-line monitoring system 100 of the circuit breaker may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the on-line monitoring system 100 of the circuit breaker can also be one of a number of hardware modules of the terminal device.
Alternatively, in another example, the on-line monitoring system 100 of the circuit breaker and the terminal device may be separate devices, and the on-line monitoring system 100 of the circuit breaker may be connected to the terminal device through a wired and/or wireless network and transmit the interactive information in a agreed data format.
Fig. 2 is a flowchart of an on-line monitoring method of a circuit breaker according to an embodiment of the present invention. Fig. 3 is a schematic diagram of a system architecture of an on-line monitoring method of a circuit breaker according to an embodiment of the present invention. As shown in fig. 2 and 3, an on-line monitoring method of a circuit breaker includes: 210, acquiring current values, voltage values and temperature values of a monitored circuit breaker at a plurality of preset time points in a preset time period; 220, arranging the current values, the voltage values and the temperature values of the plurality of preset time points into a current time sequence input vector, a voltage time sequence input vector and a temperature time sequence input vector according to a time dimension respectively; 230, performing time-sequence correlation analysis on the current time sequence input vector and the voltage time sequence input vector through a current-voltage time sequence correlation mode feature extractor based on a deep neural network model to obtain a current-voltage time sequence correlation feature map; 240, extracting time sequence characteristics of the temperature time sequence input vector to obtain a temperature time sequence characteristic vector; 250, performing multi-mode feature timing guidance fusion on the current-voltage timing correlation feature map and the temperature timing feature vector to obtain a temperature timing feature guidance strengthening current-voltage timing correlation feature; 260, based on the temperature time sequence characteristic, guiding the intensified current-voltage time sequence correlation characteristic, determining whether the working state of the monitored circuit breaker is normal.
In the on-line monitoring method of the circuit breaker, the current time sequence input vector and the voltage time sequence input vector are subjected to time sequence correlation analysis by a current-voltage time sequence correlation mode feature extractor based on a deep neural network model to obtain a current-voltage time sequence correlation feature map, and the method comprises the following steps: performing association coding on the current time sequence input vector and the voltage time sequence input vector to obtain a current-voltage time sequence association matrix; and passing the current-voltage time sequence correlation matrix through a current-voltage time sequence correlation pattern feature extractor based on a convolutional neural network model to obtain the current-voltage time sequence correlation feature map.
It will be appreciated by those skilled in the art that the specific operation of the respective steps in the above-described on-line monitoring method of the circuit breaker has been described in detail in the above description of the on-line monitoring system of the circuit breaker with reference to fig. 1, and thus, repetitive description thereof will be omitted.
Fig. 4 is an application scenario diagram of an on-line monitoring system of a circuit breaker according to an embodiment of the present invention. As shown in fig. 4, in this application scenario, first, current values (e.g., C1 as illustrated in fig. 4), voltage values (e.g., C2 as illustrated in fig. 4), and temperature values (e.g., C3 as illustrated in fig. 4) of a monitored circuit breaker at a plurality of predetermined time points within a predetermined period of time are acquired; then, the acquired current value, voltage value, and temperature value are input into a server (e.g., S as illustrated in fig. 4) in which an on-line monitoring algorithm of the circuit breaker is deployed, wherein the server is capable of processing the current value, the voltage value, and the temperature value based on the on-line monitoring algorithm of the circuit breaker to determine whether the operating state of the monitored circuit breaker is normal.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (7)
1. An on-line monitoring system for a circuit breaker, comprising:
The data acquisition module is used for acquiring current values, voltage values and temperature values of the monitored circuit breaker at a plurality of preset time points in a preset time period;
The data time sequence arrangement module is used for respectively arranging the current values, the voltage values and the temperature values of the plurality of preset time points into a current time sequence input vector, a voltage time sequence input vector and a temperature time sequence input vector according to the time dimension;
The current-voltage time sequence correlation characteristic extraction module is used for carrying out time sequence correlation analysis on the current time sequence input vector and the voltage time sequence input vector through a current-voltage time sequence correlation mode characteristic extractor based on a deep neural network model so as to obtain a current-voltage time sequence correlation characteristic diagram;
The temperature time sequence feature extraction module is used for extracting time sequence features of the temperature time sequence input vector to obtain a temperature time sequence feature vector;
The multi-mode time sequence feature guiding and fusing module is used for carrying out multi-mode feature time sequence guiding and fusing on the current-voltage time sequence associated feature map and the temperature time sequence feature vector so as to obtain temperature time sequence feature guiding and strengthening current-voltage time sequence associated features;
the circuit breaker working state detection module is used for guiding the intensified current-voltage time sequence correlation characteristic based on the temperature time sequence characteristic and determining whether the working state of the monitored circuit breaker is normal or not;
The multi-mode time sequence feature guiding fusion module is used for: passing the current-voltage time sequence correlation characteristic diagram and the temperature time sequence characteristic vector through a MetaNet-based multi-mode characteristic time sequence fusion module to obtain a temperature time sequence characteristic guiding strengthening current-voltage time sequence correlation characteristic diagram;
the device further comprises a training module for training a current-voltage time sequence correlation mode feature extractor based on a convolutional neural network model, a time sequence feature extractor based on a one-dimensional convolutional layer, a multi-mode feature time sequence fusion module based on MetaNet and a classifier;
Wherein, training module includes:
The system comprises a training data acquisition unit, a monitoring unit and a control unit, wherein the training data acquisition unit is used for acquiring training data, the training data comprises training current values, training voltage values and training temperature values of a monitored circuit breaker at a plurality of preset time points in a preset time period, and a true value of whether the working state of the monitored circuit breaker is normal or not;
The training data time sequence arrangement unit is used for arranging the training current values, the training voltage values and the training temperature values of the plurality of preset time points into training current time sequence input vectors, training voltage time sequence input vectors and training temperature time sequence input vectors according to time dimensions respectively;
The training voltage-current time sequence association unit is used for carrying out association coding on the training current time sequence input vector and the training voltage time sequence input vector to obtain a training current-voltage time sequence association matrix;
The training current-voltage time sequence correlation characteristic extraction unit is used for enabling the training current-voltage time sequence correlation matrix to pass through the current-voltage time sequence correlation mode characteristic extractor based on the convolutional neural network model so as to obtain a training current-voltage time sequence correlation characteristic diagram;
the training temperature time sequence feature extraction unit is used for enabling the training temperature time sequence input vector to pass through the time sequence feature extractor based on the one-dimensional convolution layer to obtain a training temperature time sequence feature vector;
The training multi-mode time sequence feature fusion unit is used for enabling the training current-voltage time sequence associated feature map and the training temperature time sequence feature vector to pass through the MetaNet-based multi-mode feature time sequence fusion module to obtain a training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map;
The feature optimization unit is used for optimizing the training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map to obtain an optimized training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map;
The classification loss unit is used for guiding the optimized training temperature time sequence characteristic to the intensified current-voltage time sequence associated characteristic diagram to pass through the classifier so as to obtain a classification loss function value;
The model training unit is used for training the current-voltage time sequence correlation mode feature extractor based on the convolutional neural network model, the time sequence feature extractor based on the one-dimensional convolutional layer, the multi-mode feature time sequence fusion module based on MetaNet and the classifier based on the classification loss function value and through gradient descent direction propagation;
wherein the feature optimization unit includes: performing linear transformation on the training temperature time sequence feature guiding strengthening current-voltage time sequence correlation feature map to obtain a converted training temperature time sequence feature guiding strengthening current-voltage time sequence correlation feature map, wherein the width and the height of a feature matrix of the converted training temperature time sequence feature guiding strengthening current-voltage time sequence correlation feature map are equal; channel dimension optimization is carried out on the converted training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map so as to obtain an optimized training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map;
The channel dimension optimization is performed on the converted training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map to obtain an optimized training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map, which comprises the following steps: carrying out channel dimension optimization on the converted training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map by using the following optimization formula to obtain an optimized training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map; wherein, the formula is:
Wherein, And/>The training temperature time sequence characteristic after conversion guides the strengthening current-voltage time sequence associated characteristic diagram to the/>, along the channel directionAnd/>Feature matrix of location, and/>Is a scale-adjusting hyper-parameter,/>Representing the transpose of the matrix,/>Representing matrix multiplication,/>Representing the dot-by-location multiplication of a matrix,/>Representing the per-position addition of matrices,/>Is the/>, along the channel direction, of the time sequence correlation characteristic diagram among the optimized training performance indexesA feature matrix of locations.
2. The on-line monitoring system of a circuit breaker according to claim 1, wherein the current-voltage timing correlation feature extraction module comprises:
a current-voltage time sequence association coding unit, configured to perform association coding on the current time sequence input vector and the voltage time sequence input vector to obtain a current-voltage time sequence association matrix;
And the current-voltage time sequence feature extraction unit is used for enabling the current-voltage time sequence correlation matrix to pass through a current-voltage time sequence correlation mode feature extractor based on a convolutional neural network model so as to obtain the current-voltage time sequence correlation feature map.
3. The circuit breaker on-line monitoring system of claim 2, wherein the temperature timing feature extraction module is configured to: and the temperature time sequence input vector passes through a time sequence feature extractor based on a one-dimensional convolution layer to obtain a temperature time sequence feature vector.
4. The on-line monitoring system of a circuit breaker according to claim 3, wherein the circuit breaker operating state detection module is configured to: and leading the temperature time sequence characteristic to a strengthening current-voltage time sequence correlation characteristic diagram to pass through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the working state of the monitored circuit breaker is normal or not.
5. The on-line monitoring system of circuit breakers of claim 4, wherein the categorical loss unit comprises:
A training classification subunit, configured to process the optimized training temperature timing feature-guided enhanced current-voltage timing correlation feature map with a training classification formula using the classifier to generate a training classification result, where the training classification formula is: Wherein/> Representing projection of the optimized training temperature timing feature-guided enhanced current-voltage timing correlation feature map as a vector,/>To/>Is a weight matrix,/>To/>Representing a bias matrix; and
And the classification loss function value calculation subunit is used for calculating a cross entropy value between the training classification result and a true value as the classification loss function value.
6. An on-line monitoring method of a circuit breaker, comprising:
Acquiring current values, voltage values and temperature values of a monitored circuit breaker at a plurality of preset time points in a preset time period;
Arranging the current values, the voltage values and the temperature values of the plurality of preset time points into a current time sequence input vector, a voltage time sequence input vector and a temperature time sequence input vector according to time dimensions respectively;
Performing time sequence correlation analysis on the current time sequence input vector and the voltage time sequence input vector through a current-voltage time sequence correlation mode feature extractor based on a deep neural network model to obtain a current-voltage time sequence correlation feature map;
extracting time sequence characteristics of the temperature time sequence input vector to obtain a temperature time sequence characteristic vector;
Carrying out multi-mode characteristic time sequence guiding fusion on the current-voltage time sequence related characteristic diagram and the temperature time sequence characteristic vector to obtain a temperature time sequence characteristic guiding strengthening current-voltage time sequence related characteristic;
Based on the temperature time sequence characteristic, guiding the intensified current-voltage time sequence correlation characteristic, and determining whether the working state of the monitored circuit breaker is normal or not;
The multi-mode feature time sequence guiding fusion is carried out on the current-voltage time sequence related feature graph and the temperature time sequence feature vector to obtain a temperature time sequence feature guiding intensified current-voltage time sequence related feature, which comprises the following steps: passing the current-voltage time sequence correlation characteristic diagram and the temperature time sequence characteristic vector through a MetaNet-based multi-mode characteristic time sequence fusion module to obtain a temperature time sequence characteristic guiding strengthening current-voltage time sequence correlation characteristic diagram;
The device further comprises a current-voltage time sequence correlation mode feature extractor based on a convolutional neural network model, a time sequence feature extractor based on a one-dimensional convolutional layer, a multi-mode feature time sequence fusion module based on MetaNet and a classifier for training;
The training method for the current-voltage time sequence correlation mode feature extractor based on the convolutional neural network model, the time sequence feature extractor based on the one-dimensional convolutional layer, the multi-mode feature time sequence fusion module based on MetaNet and the classifier comprises the following steps:
Acquiring training data, wherein the training data comprises training current values, training voltage values and training temperature values of a monitored circuit breaker at a plurality of preset time points in a preset time period, and a true value of whether the working state of the monitored circuit breaker is normal or not;
Respectively arranging the training current values, the training voltage values and the training temperature values of the plurality of preset time points into training current time sequence input vectors, training voltage time sequence input vectors and training temperature time sequence input vectors according to time dimensions;
Performing association coding on the training current time sequence input vector and the training voltage time sequence input vector to obtain a training current-voltage time sequence association matrix;
passing the training current-voltage time sequence correlation matrix through the current-voltage time sequence correlation mode feature extractor based on the convolutional neural network model to obtain a training current-voltage time sequence correlation feature map;
the training temperature time sequence input vector passes through the time sequence feature extractor based on the one-dimensional convolution layer to obtain a training temperature time sequence feature vector;
Passing the training current-voltage time sequence correlation characteristic diagram and the training temperature time sequence characteristic vector through the MetaNet-based multi-mode characteristic time sequence fusion module to obtain a training temperature time sequence characteristic guiding strengthening current-voltage time sequence correlation characteristic diagram;
Optimizing the training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map to obtain an optimized training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map;
leading the optimized training temperature time sequence characteristic to a strengthening current-voltage time sequence associated characteristic diagram through the classifier to obtain a classification loss function value;
Training the current-voltage time sequence correlation mode feature extractor based on the convolutional neural network model, the time sequence feature extractor based on the one-dimensional convolutional layer, the multi-mode feature time sequence fusion module based on MetaNet and the classifier based on the classification loss function value and through gradient descent direction propagation;
Wherein optimizing the training temperature timing feature-directed enhanced current-voltage timing correlation feature map to obtain an optimized training temperature timing feature-directed enhanced current-voltage timing correlation feature map, comprises: performing linear transformation on the training temperature time sequence feature guiding strengthening current-voltage time sequence correlation feature map to obtain a converted training temperature time sequence feature guiding strengthening current-voltage time sequence correlation feature map, wherein the width and the height of a feature matrix of the converted training temperature time sequence feature guiding strengthening current-voltage time sequence correlation feature map are equal; channel dimension optimization is carried out on the converted training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map so as to obtain an optimized training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map;
The channel dimension optimization is performed on the converted training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map to obtain an optimized training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map, which comprises the following steps: carrying out channel dimension optimization on the converted training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map by using the following optimization formula to obtain an optimized training temperature time sequence feature guiding strengthening current-voltage time sequence associated feature map; wherein, the formula is:
Wherein, And/>The training temperature time sequence characteristic after conversion guides the strengthening current-voltage time sequence associated characteristic diagram to the/>, along the channel directionAnd/>Feature matrix of location, and/>Is a scale-adjusting hyper-parameter,/>Representing the transpose of the matrix,/>Representing matrix multiplication,/>Representing the dot-by-location multiplication of a matrix,/>Representing the per-position addition of matrices,/>Is the/>, along the channel direction, of the time sequence correlation characteristic diagram among the optimized training performance indexesA feature matrix of locations.
7. The on-line monitoring method of a circuit breaker according to claim 6, wherein the performing a time-series correlation analysis on the current time-series input vector and the voltage time-series input vector by a current-voltage time-series correlation pattern feature extractor based on a deep neural network model to obtain a current-voltage time-series correlation feature map comprises:
performing association coding on the current time sequence input vector and the voltage time sequence input vector to obtain a current-voltage time sequence association matrix;
And passing the current-voltage time sequence correlation matrix through a current-voltage time sequence correlation pattern feature extractor based on a convolutional neural network model to obtain the current-voltage time sequence correlation feature map.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410071994.XA CN117590223B (en) | 2024-01-18 | 2024-01-18 | Online monitoring system and method for circuit breaker |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410071994.XA CN117590223B (en) | 2024-01-18 | 2024-01-18 | Online monitoring system and method for circuit breaker |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117590223A CN117590223A (en) | 2024-02-23 |
| CN117590223B true CN117590223B (en) | 2024-04-30 |
Family
ID=89920470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410071994.XA Active CN117590223B (en) | 2024-01-18 | 2024-01-18 | Online monitoring system and method for circuit breaker |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117590223B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117805607B (en) * | 2024-02-29 | 2024-05-07 | 山西漳电科学技术研究院(有限公司) | DC level difference matching test method for power plant DC system |
| CN117872124A (en) * | 2024-03-12 | 2024-04-12 | 杭州布雷科电气有限公司 | Off-line testing system and method for circuit breaker based on neural network |
Citations (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103439650A (en) * | 2013-08-07 | 2013-12-11 | 王岩 | Method and device used for state monitoring and fault diagnosis of relay |
| CN104616121A (en) * | 2015-02-28 | 2015-05-13 | 南京飞腾电子科技有限公司 | Regional energy comprehensive coordination management and control system |
| CN106291351A (en) * | 2016-09-20 | 2017-01-04 | 西安工程大学 | Primary cut-out fault detection method based on convolutional neural networks algorithm |
| CN108321760A (en) * | 2018-02-23 | 2018-07-24 | 南京飞腾电子科技有限公司 | breaker and its operation method |
| CN111612128A (en) * | 2020-05-14 | 2020-09-01 | 国网江苏省电力有限公司电力科学研究院 | Active early warning method and device for SF6 high-voltage circuit breaker state |
| CN111863559A (en) * | 2020-07-03 | 2020-10-30 | 威胜信息技术股份有限公司 | Low-voltage Internet of things breaker and fault detection method thereof |
| CN113376516A (en) * | 2021-06-07 | 2021-09-10 | 科润智能控制股份有限公司 | Medium-voltage vacuum circuit breaker operation fault self-diagnosis and early-warning method based on deep learning |
| WO2021212752A1 (en) * | 2020-04-23 | 2021-10-28 | 平安科技（深圳）有限公司 | Device index data-based anomaly detection method and apparatus, device, and storage medium |
| CN113761226A (en) * | 2021-11-10 | 2021-12-07 | 中国电子科技集团公司第二十八研究所 | Ontology construction method of multi-modal airport data |
| CN115097296A (en) * | 2022-06-22 | 2022-09-23 | 云南电网有限责任公司电力科学研究院 | Relay reliability evaluation method and device |
| CN115327369A (en) * | 2022-09-13 | 2022-11-11 | 国网安徽省电力有限公司宿州供电公司 | On-line monitoring and analyzing system for opening and closing current of switch cabinet circuit breaker |
| CN115575811A (en) * | 2022-10-28 | 2023-01-06 | 国网陕西省电力有限公司电力科学研究院 | Method, system, storage medium and equipment for predicting and evaluating electric service life of circuit breaker |
| CN116482524A (en) * | 2023-04-23 | 2023-07-25 | 云南远信科技有限公司 | Power transmission and distribution switch state detection method and system |
| CN116610990A (en) * | 2023-04-06 | 2023-08-18 | 安徽继远软件有限公司 | Method and device for identifying hidden danger of breaker based on characteristic space differentiation |
| CN116627708A (en) * | 2023-07-24 | 2023-08-22 | 湖南惟储信息技术有限公司 | Storage fault analysis system and method thereof |
| CN116639010A (en) * | 2023-07-24 | 2023-08-25 | 江西驴宝宝通卡科技有限公司 | Intelligent control system and method for charging pile |
| CN116893336A (en) * | 2023-07-11 | 2023-10-17 | 浙江和能电力设备有限公司 | High-low voltage switching device and method thereof |
| CN116929815A (en) * | 2023-07-20 | 2023-10-24 | 漳州市诺兰信息科技有限公司 | Equipment working state monitoring system and method based on Internet of things |
| CN117113218A (en) * | 2023-08-04 | 2023-11-24 | 杭州国辰智企科技有限公司 | Visual data analysis system and method thereof |
| CN117124910A (en) * | 2023-09-20 | 2023-11-28 | 漳州建源电力工程有限公司 | Smart city charging pile node fault alarm system and method |
| CN117189071A (en) * | 2023-11-07 | 2023-12-08 | 克拉玛依市远山石油科技有限公司 | Automatic control method for core drilling rig operation |
| CN117269743A (en) * | 2023-08-31 | 2023-12-22 | 库顿电子科技(上海)有限公司 | Detection module suitable for relay monitoring system |
| CN117330948A (en) * | 2023-10-19 | 2024-01-02 | 山东泰开成套电器有限公司 | Online monitoring method and system for mechanical characteristics of circuit breaker |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9864008B2 (en) * | 2014-03-31 | 2018-01-09 | Schweitzer Engineering Laboratories, Inc. | Electric power system circuit breaker trip diagnostic |
| DE112016005476T5 (en) * | 2015-12-28 | 2018-08-09 | Eaton Intelligent Power Limited | Forecasting and health monitoring system for circuit breakers |
-
2024
- 2024-01-18 CN CN202410071994.XA patent/CN117590223B/en active Active
Patent Citations (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103439650A (en) * | 2013-08-07 | 2013-12-11 | 王岩 | Method and device used for state monitoring and fault diagnosis of relay |
| CN104616121A (en) * | 2015-02-28 | 2015-05-13 | 南京飞腾电子科技有限公司 | Regional energy comprehensive coordination management and control system |
| CN106291351A (en) * | 2016-09-20 | 2017-01-04 | 西安工程大学 | Primary cut-out fault detection method based on convolutional neural networks algorithm |
| CN108321760A (en) * | 2018-02-23 | 2018-07-24 | 南京飞腾电子科技有限公司 | breaker and its operation method |
| WO2021212752A1 (en) * | 2020-04-23 | 2021-10-28 | 平安科技（深圳）有限公司 | Device index data-based anomaly detection method and apparatus, device, and storage medium |
| CN111612128A (en) * | 2020-05-14 | 2020-09-01 | 国网江苏省电力有限公司电力科学研究院 | Active early warning method and device for SF6 high-voltage circuit breaker state |
| CN111863559A (en) * | 2020-07-03 | 2020-10-30 | 威胜信息技术股份有限公司 | Low-voltage Internet of things breaker and fault detection method thereof |
| CN113376516A (en) * | 2021-06-07 | 2021-09-10 | 科润智能控制股份有限公司 | Medium-voltage vacuum circuit breaker operation fault self-diagnosis and early-warning method based on deep learning |
| CN113761226A (en) * | 2021-11-10 | 2021-12-07 | 中国电子科技集团公司第二十八研究所 | Ontology construction method of multi-modal airport data |
| CN115097296A (en) * | 2022-06-22 | 2022-09-23 | 云南电网有限责任公司电力科学研究院 | Relay reliability evaluation method and device |
| CN115327369A (en) * | 2022-09-13 | 2022-11-11 | 国网安徽省电力有限公司宿州供电公司 | On-line monitoring and analyzing system for opening and closing current of switch cabinet circuit breaker |
| CN115575811A (en) * | 2022-10-28 | 2023-01-06 | 国网陕西省电力有限公司电力科学研究院 | Method, system, storage medium and equipment for predicting and evaluating electric service life of circuit breaker |
| CN116610990A (en) * | 2023-04-06 | 2023-08-18 | 安徽继远软件有限公司 | Method and device for identifying hidden danger of breaker based on characteristic space differentiation |
| CN116482524A (en) * | 2023-04-23 | 2023-07-25 | 云南远信科技有限公司 | Power transmission and distribution switch state detection method and system |
| CN116893336A (en) * | 2023-07-11 | 2023-10-17 | 浙江和能电力设备有限公司 | High-low voltage switching device and method thereof |
| CN116929815A (en) * | 2023-07-20 | 2023-10-24 | 漳州市诺兰信息科技有限公司 | Equipment working state monitoring system and method based on Internet of things |
| CN116627708A (en) * | 2023-07-24 | 2023-08-22 | 湖南惟储信息技术有限公司 | Storage fault analysis system and method thereof |
| CN116639010A (en) * | 2023-07-24 | 2023-08-25 | 江西驴宝宝通卡科技有限公司 | Intelligent control system and method for charging pile |
| CN117113218A (en) * | 2023-08-04 | 2023-11-24 | 杭州国辰智企科技有限公司 | Visual data analysis system and method thereof |
| CN117269743A (en) * | 2023-08-31 | 2023-12-22 | 库顿电子科技(上海)有限公司 | Detection module suitable for relay monitoring system |
| CN117124910A (en) * | 2023-09-20 | 2023-11-28 | 漳州建源电力工程有限公司 | Smart city charging pile node fault alarm system and method |
| CN117330948A (en) * | 2023-10-19 | 2024-01-02 | 山东泰开成套电器有限公司 | Online monitoring method and system for mechanical characteristics of circuit breaker |
| CN117189071A (en) * | 2023-11-07 | 2023-12-08 | 克拉玛依市远山石油科技有限公司 | Automatic control method for core drilling rig operation |
Non-Patent Citations (1)
| Title |
|---|
| 多振动信息下的高压断路器机械故障随机森林融合诊断方法;马速良;《电工技术学报》;20201231;第35卷(第增刊2期);421-431 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117590223A (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117590223B (en) | Online monitoring system and method for circuit breaker | |
| CN106597231B (en) | GIS fault detection system and method based on Multi-source Information Fusion and deep learning network | |
| CN109787979B (en) | Method for detecting electric power network event and invasion | |
| CN111898669B (en) | Abnormal event early warning system of direct-current submerged arc furnace based on machine learning | |
| Long | Research on status information monitoring of power equipment based on Internet of Things | |
| CN116740654B (en) | Substation operation prevention and control method based on image recognition technology | |
| CN105548744A (en) | Substation equipment fault identification method based on operation-detection large data and system thereof | |
| CN105139158A (en) | Power grid abnormal information intelligent alarming and assistant decision-making method | |
| CN104360194A (en) | Fault diagnosis method for smart power grid | |
| CN114091549A (en) | Equipment fault diagnosis method based on deep residual error network | |
| CN113572771A (en) | Power grid CPS network attack identification method and system | |
| CN201666923U (en) | Device for processing DSP failure diagnosis of electric power system by using immune genetic algorithm | |
| CN110070266B (en) | Method and system for identifying major event of power grid cascading failure | |
| Teng et al. | On-line fault diagnosis technology and application based on deep learning of fault characteristic of power grid | |
| CN106022950B (en) | Power distribution network secondary equipment type identification method and system | |
| CN115146727A (en) | Intelligent power utilization system fault detection method and system | |
| CN111401481A (en) | Power grid operation mode automatic identification method based on multi-source information fusion technology | |
| Qiu et al. | Cross-Space Conduction Assessment Method of Network Attack Risk under the Strong Coupling Characteristics of Electric Power Cyber Physics | |
| Strachan et al. | Trip coil signature analysis and interpretation for distribution circuit breaker condition assessment and diagnosis | |
| Sun et al. | Transmission Line Fault Diagnosis Method Based on Improved Multiple SVM Model | |
| CN111915855B (en) | Alarm analysis method for alarm system of million-kilowatt ultra-supercritical unit | |
| CN117612345A (en) | Power equipment state monitoring and alarming system and method | |
| Ning | Relay protection hidden fault monitoring and risk analysis based on the power system | |
| Maurya et al. | A Short Review on Fault Detection and Fault Classification in Transmission Lines | |
| Bai et al. | Abnormal Detection Scheme of Substation Equipment based on Intelligent Fusion Terminal |
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 |