CN117458710A - Remote control misoperation prevention method and system for transformer substation - Google Patents

Remote control misoperation prevention method and system for transformer substation Download PDF

Info

Publication number
CN117458710A
CN117458710A CN202311396950.6A CN202311396950A CN117458710A CN 117458710 A CN117458710 A CN 117458710A CN 202311396950 A CN202311396950 A CN 202311396950A CN 117458710 A CN117458710 A CN 117458710A
Authority
CN
China
Prior art keywords
time sequence
training
temperature
remote control
current
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311396950.6A
Other languages
Chinese (zh)
Inventor
郁海彭
费皓月
冯博
李仁其
张明清
张连花
朱灵
陆娴
赵楠
吴栋伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nantong Power Supply Co Of State Grid Jiangsu Electric Power Co
Original Assignee
Nantong Power Supply Co Of State Grid Jiangsu Electric Power Co
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nantong Power Supply Co Of State Grid Jiangsu Electric Power Co filed Critical Nantong Power Supply Co Of State Grid Jiangsu Electric Power Co
Priority to CN202311396950.6A priority Critical patent/CN117458710A/en
Publication of CN117458710A publication Critical patent/CN117458710A/en
Pending legal-status Critical Current

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
    • 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
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
    • H02J13/00034—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving an electric power substation
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
    • H02J13/00036—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving switches, relays or circuit breakers
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
    • H02J13/00036—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving switches, relays or circuit breakers
    • H02J13/0004—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for the elements or equipment being or involving switches, relays or circuit breakers involved in a protection system
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/16—Electric power substations

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Water Supply & Treatment (AREA)
  • Biomedical Technology (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Human Resources & Organizations (AREA)
  • General Business, Economics & Management (AREA)
  • Public Health (AREA)
  • Human Computer Interaction (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Marketing (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Remote Monitoring And Control Of Power-Distribution Networks (AREA)

Abstract

The invention discloses a remote control misoperation prevention method and a remote control misoperation prevention system for a transformer substation, which are characterized in that a sensor group is used for acquiring current values, temperature values and frequency values of a monitored transformer substation at a plurality of preset time points in a preset time period after a first remote control operation is executed; arranging the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector according to the time dimension; performing time sequence response association coding on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector to obtain multi-parameter transfer association characteristics; and determining whether the first remote control operation is a malfunction based on the multi-parameter transfer association feature. Therefore, abnormal conditions can be identified, whether the first remote control operation is misoperation or not can be judged, and early warning is carried out, so that the real-time detection of the rationality and the safety of the remote control operation is realized, and the accuracy and the reliability of the remote control operation are improved.

Description

Remote control misoperation prevention method and system for transformer substation
Technical Field
The invention relates to the technical field of intelligent operation, in particular to a remote control misoperation prevention method and system for a transformer substation.
Background
Substations are an important component in electrical power systems for converting high voltage electrical energy into low voltage electrical energy for use by consumers. In the running process, the transformer substation needs to be remotely controlled to monitor, control and protect the power system. The remote control operation of the transformer substation refers to the operation of equipment such as a switch, a breaker and the like of the transformer substation through remote control equipment so as to realize the operation control and fault handling of the transformer substation.
The remote control operation of the transformer substation has the advantages of high efficiency, flexibility, safety and the like, but the risk of misoperation exists, and the misoperation can cause equipment damage of the transformer substation, instability of a power grid and even occurrence of accidents, so that the safety and the stability of a power system are threatened. Therefore, how to prevent misoperation of the remote control of the transformer substation is an important problem. However, the conventional misoperation preventing method mainly depends on experience and attention of operators, but the method has subjectivity and limitation, and the accuracy of operation cannot be completely ensured.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a remote control misoperation prevention method and a remote control misoperation prevention system for a transformer substation, so as to solve the problems.
In order to achieve the above object, the present invention is achieved by the following technical scheme.
A remote control misoperation prevention method for a transformer substation comprises the following steps:
acquiring current values, temperature values and frequency values of a plurality of preset time points of a monitored transformer substation in a preset time period after a first remote control operation is executed by a sensor group;
arranging the current values, the temperature values and the frequency values of the plurality of preset time points into a current time sequence input vector, a temperature time sequence input vector and a frequency time sequence input vector according to a time dimension;
performing time sequence response association coding on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector to obtain multi-parameter transfer association characteristics;
and determining whether the first remote control operation is misoperation based on the multi-parameter transfer association characteristic, so that abnormal conditions can be identified, and whether the first remote control operation is misoperation can be judged, thereby carrying out early warning, realizing real-time detection on the rationality and the safety of the remote control operation, and improving the accuracy and the reliability of the remote control operation.
Preferably, performing time-series response correlation encoding on the current time-series input vector, the temperature time-series input vector and the frequency time-series input vector to obtain a multi-parameter transfer correlation feature, including:
Respectively carrying out feature extraction on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector through a time sequence feature extractor based on a deep neural network model so as to obtain a current time sequence multi-scale feature vector, a temperature time sequence multi-scale feature vector and a frequency time sequence multi-scale feature vector;
calculating the response estimation of the temperature time sequence multi-scale feature vector relative to the current time sequence multi-scale feature vector to obtain a current-temperature response fusion feature matrix; and
and performing responsive transfer analysis on the frequency time sequence multi-scale feature vector relative to the current-temperature responsive fusion feature matrix to obtain the multi-parameter transfer association feature.
Preferably, the deep neural network model is a multi-scale neighborhood feature extraction module.
Preferably, performing a response transfer analysis on the frequency-sequential multi-scale feature vector with respect to the current-temperature response fusion feature matrix to obtain the multi-parameter transfer correlation feature, including: and calculating the response transfer of the frequency time sequence multiscale feature vector relative to the current-temperature response fusion feature matrix to obtain a multi-parameter transfer association feature vector as the multi-parameter transfer association feature.
Preferably, determining whether the first remote control operation is a malfunction based on the multi-parameter transfer association feature includes:
the multi-parameter transfer association feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the monitored transformer substation has abnormality or not;
based on the classification result, it is determined whether the first remote operation is an erroneous operation.
Preferably, the method further comprises the training step of: and the time sequence feature extractor and the classifier are used for training the time sequence feature extractor and the classifier based on the multi-scale neighborhood feature extraction module.
Preferably, the training step includes:
acquiring training data, wherein the training data comprises training current values, training temperature values and training frequency values of the monitored transformer substation at a plurality of preset time points in a preset time period after a first remote control operation is executed, and whether the monitored transformer substation has an abnormal real value or not;
arranging the training current values, the training temperature values and the training frequency values of the plurality of preset time points into training current time sequence input vectors, training temperature time sequence input vectors and training frequency time sequence input vectors according to time dimensions;
passing the training current time sequence input vector, the training temperature time sequence input vector and the training frequency time sequence input vector through the time sequence feature extractor based on the multi-scale neighborhood feature extraction module to obtain a training current time sequence multi-scale feature vector, a training temperature time sequence multi-scale feature vector and a training frequency time sequence multi-scale feature vector;
Calculating the response estimation of the training temperature time sequence multi-scale feature vector relative to the training current time sequence multi-scale feature vector to obtain a training current-temperature response fusion feature matrix;
calculating the response transfer of the training frequency time sequence multi-scale feature vector relative to the training current-temperature response fusion feature matrix to obtain a training multi-parameter transfer associated feature vector;
passing the training multi-parameter transfer associated feature vector through the classifier to obtain a classification loss function value;
training a time sequence feature extractor and a classifier based on the multi-scale neighborhood feature extraction module based on the classification loss function value and through gradient descent direction propagation, wherein the training multi-parameter transfer associated feature vector is subjected to weight space iterative recursive orientation proposal optimization at each iteration of the training.
A remote control anti-misoperation system of a transformer substation, comprising:
the data acquisition module is used for acquiring current values, temperature values and frequency values of a plurality of preset time points of the monitored transformer substation in a preset time period after the first remote control operation is executed by the sensor group;
A vector arrangement module, configured to arrange the current values, the temperature values, and the frequency values at the plurality of predetermined time points into a current timing input vector, a temperature timing input vector, and a frequency timing input vector according to a time dimension;
the association coding module is used for carrying out time sequence response association coding on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector so as to obtain multi-parameter transfer association characteristics; and
and the first remote control operation determining module is used for determining whether the first remote control operation is misoperation or not based on the multi-parameter transfer association characteristic.
Preferably, the association coding module includes:
the characteristic extraction unit is used for respectively carrying out characteristic extraction on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector through a time sequence characteristic extractor based on a deep neural network model so as to obtain a current time sequence multi-scale characteristic vector, a temperature time sequence multi-scale characteristic vector and a frequency time sequence multi-scale characteristic vector;
the responsiveness estimation calculation unit is used for calculating responsiveness estimation of the temperature time sequence multi-scale characteristic vector relative to the current time sequence multi-scale characteristic vector so as to obtain a current-temperature responsiveness fusion characteristic matrix; and
And the responsiveness transfer analysis unit is used for performing responsiveness transfer analysis on the frequency time sequence multi-scale feature vector relative to the current-temperature responsiveness fusion feature matrix so as to obtain the multi-parameter transfer association feature.
Preferably, the deep neural network model is a multi-scale neighborhood feature extraction module.
Compared with the prior art, the invention discloses a remote control misoperation prevention method and a remote control misoperation prevention system for a transformer substation,
(1) the remote control operation can be used for remotely controlling equipment such as a switch and a breaker of a transformer substation to realize distribution, switching and adjustment of electric energy, for example, switching on and off of the switch can be remotely controlled to realize on-off operation of a circuit so as to meet the operation requirement of a power system, when the transformer substation breaks down, the remote control operation can be used for remotely switching off or switching on the fault equipment to isolate the fault and protect the safety of the power system, for example, when a certain equipment breaks down, the breaker can be remotely operated to switch off so as to prevent the expansion of the fault or influence on other equipment, and the remote control operation can be used for monitoring the state and parameters such as current, voltage, temperature and the like of the transformer substation equipment in real time, and meanwhile, the debugging and maintenance operation of the equipment can be also carried out so as to ensure the normal operation and the performance optimization of the equipment;
(2) The remote control operation of the transformer substation has the advantages of high efficiency, flexibility and safety, can reduce the workload and risk of manual operation, improve the accuracy and reliability of operation, and simultaneously, the remote control operation can realize the control of remote or inaccessible equipment, and improve the convenience and flexibility of operation;
(3) in the step 110, when obtaining the current value, the temperature value and the frequency value of the monitored substation, it is necessary to ensure that the data collected by the sensor group are accurate and reliable, the specific situation and the monitoring requirement of the substation should be considered in the selection and arrangement of the sensors, in addition, the time range in which misoperation may occur should be fully covered by the selection of the predetermined time period, and by obtaining the current values, the temperature values and the frequency values at a plurality of predetermined time points, multidimensional data about the running state of the substation can be obtained, and these data can be used for subsequent time sequence association analysis to help determine whether the first remote control operation is an misoperation;
(4) in the step 120, when the current value, the temperature value and the frequency value are arranged in time dimension as time sequence input vectors, it is necessary to ensure that the corresponding relationship of the data is accurate, ensure that the time intervals of the data are consistent and are arranged according to time sequence, in addition, the data can be considered to be standardized or normalized for subsequent analysis and processing, and the data at multiple time points can be integrated into a sequence by arranging the data in time dimension as time sequence input vectors, so that the time relationship of the data is reserved, the subsequent time sequence association analysis is facilitated, and the dynamic characteristics among the data are better captured;
(5) In the step 130, when performing time-series response association coding on the current time-series input vector, the temperature time-series input vector and the frequency time-series input vector, a proper coding method and model need to be selected, and common methods include a cyclic neural network (RNN) and a Convolutional Neural Network (CNN), a proper model structure and parameter setting can be selected according to specific situations, by performing time-series response association coding on the time-series input vector, transfer association characteristics among multiple parameters can be extracted, which are helpful for capturing time-series relationship and mutual influence among data, providing a more comprehensive and accurate basis for judging whether the first remote control operation is an misoperation,
(6) in the step 140, when determining whether the first remote control operation is a misoperation based on the multi-parameter transfer association feature, a proper classification model or rule determination method needs to be established, accurate label data needs to be used for training and verification of the model to ensure reliability of the determination result, and meanwhile, a proper threshold or rule needs to be set according to actual conditions to balance risks of false alarm and false omission, and by determining whether the first remote control operation is a misoperation based on the multi-parameter transfer association feature, detection accuracy and efficiency of the misoperation can be improved, timely discovery and correction of the misoperation are facilitated, and potential risks to substation equipment and a power system are reduced
(7) The time sequence analysis of the transformer substation parameter data is carried out by monitoring the parameter data, such as a current value, a temperature value and a frequency value, of the transformer substation after the first remote control operation is carried out in real time, introducing a data processing and analyzing algorithm at the rear end, so as to monitor the state and the running condition of the transformer substation based on the time sequence change trend of the current, the temperature and the frequency of the transformer substation after the first remote control operation is carried out, identify the abnormal condition and judge whether the first remote control operation is in misoperation or not, thereby carrying out early warning, realizing the real-time detection of the rationality and the safety of the remote control operation, and improving the accuracy and the reliability of the remote control operation
(8) The information of the current and the temperature can be fused, and the correlation characteristics between the current and the temperature can be further extracted, so that the relation between the current and the temperature can be more comprehensively analyzed, and whether the remote control operation is misoperation or not can be more accurately judged
(9) Further calculating the response transfer of the frequency time sequence multiscale feature vector relative to the current-temperature response fusion feature matrix to obtain a multi-parameter transfer association feature vector, and comprehensively considering the association information among current, temperature and frequency by obtaining the multi-parameter transfer association feature vector, so that the comprehensive influence among the current, temperature and frequency can be more comprehensively analyzed, and the accuracy and reliability of remote control operation are further improved
Compared with the traditional rule-based method, the method based on the feature vector and the classifier can capture the abnormal mode more accurately, improve the accuracy of misoperation detection, realize real-time monitoring and early warning of the running state of the transformer substation by continuously acquiring and analyzing the multi-parameter transfer associated feature vector and performing classification judgment in real time, once the transformer substation is abnormal, operators can take measures in time to avoid further loss and risk, the classification result can provide information about the state of the transformer substation for the operators to help the operators to make decisions and execute operations, and if the classification result shows that the transformer substation is normal, the operators can continue to execute the planned operations; if the classification result shows abnormality, an operator can pause operation and further check and confirm to avoid potential risks caused by misoperation, the time sequence analysis of the substation parameter data is carried out by monitoring the parameter data, such as a current value, a temperature value and a frequency value, of the substation after the first remote control operation is carried out in real time and introducing a data processing and analyzing algorithm at the rear end, so that the monitoring of the state and the running condition of the substation is carried out based on the time sequence change trend of the current, the temperature and the frequency of the substation after the first remote control operation is carried out, the abnormal condition is identified, whether the first remote control operation is misoperation is judged, and early warning is carried out, thereby realizing the real-time detection of the rationality and the safety of the remote control operation, and improving the accuracy and the reliability of the remote control operation.
Drawings
Fig. 1 is a flowchart of a remote control misoperation prevention method of a transformer substation provided in an embodiment of the present invention;
fig. 2 is a schematic diagram of a system architecture of a remote control misoperation prevention method of a transformer substation provided in an embodiment of the present invention;
fig. 3 is a block diagram of a remote control misoperation prevention system of a transformer substation provided in an embodiment of the present invention;
fig. 4 is an application scenario diagram of a remote control misoperation prevention method for a transformer substation provided in an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
A remote control misoperation prevention method and system for a transformer substation comprise the following steps:
acquiring current values, temperature values and frequency values of a plurality of preset time points of a monitored transformer substation in a preset time period after a first remote control operation is executed by a sensor group;
arranging the current values, the temperature values and the frequency values of the plurality of preset time points into a current time sequence input vector, a temperature time sequence input vector and a frequency time sequence input vector according to a time dimension;
Performing time sequence response association coding on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector to obtain multi-parameter transfer association characteristics;
and determining whether the first remote control operation is misoperation based on the multi-parameter transfer association characteristic, so that abnormal conditions can be identified, and whether the first remote control operation is misoperation can be judged, thereby carrying out early warning, realizing real-time detection on the rationality and the safety of the remote control operation, and improving the accuracy and the reliability of the remote control operation. Performing time sequence response associated coding on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector to obtain a multi-parameter transfer associated feature, wherein the method comprises the following steps of:
respectively carrying out feature extraction on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector through a time sequence feature extractor based on a deep neural network model so as to obtain a current time sequence multi-scale feature vector, a temperature time sequence multi-scale feature vector and a frequency time sequence multi-scale feature vector;
calculating the response estimation of the temperature time sequence multi-scale feature vector relative to the current time sequence multi-scale feature vector to obtain a current-temperature response fusion feature matrix; and
And performing responsive transfer analysis on the frequency time sequence multi-scale feature vector relative to the current-temperature responsive fusion feature matrix to obtain the multi-parameter transfer association feature. The deep neural network model is a multi-scale neighborhood feature extraction module. Performing a responsive transfer analysis on the frequency-sequential multi-scale feature vector relative to the current-temperature responsive fusion feature matrix to obtain the multi-parameter transfer-related feature, comprising: and calculating the response transfer of the frequency time sequence multiscale feature vector relative to the current-temperature response fusion feature matrix to obtain a multi-parameter transfer association feature vector as the multi-parameter transfer association feature. Based on the multi-parameter transfer association feature, determining whether the first remote operation is a malfunction includes:
the multi-parameter transfer association feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the monitored transformer substation has abnormality or not;
based on the classification result, it is determined whether the first remote operation is an erroneous operation. The training method further comprises the following training steps: and the time sequence feature extractor and the classifier are used for training the time sequence feature extractor and the classifier based on the multi-scale neighborhood feature extraction module. The training step comprises the following steps:
Acquiring training data, wherein the training data comprises training current values, training temperature values and training frequency values of the monitored transformer substation at a plurality of preset time points in a preset time period after a first remote control operation is executed, and whether the monitored transformer substation has an abnormal real value or not;
arranging the training current values, the training temperature values and the training frequency values of the plurality of preset time points into training current time sequence input vectors, training temperature time sequence input vectors and training frequency time sequence input vectors according to time dimensions;
passing the training current time sequence input vector, the training temperature time sequence input vector and the training frequency time sequence input vector through the time sequence feature extractor based on the multi-scale neighborhood feature extraction module to obtain a training current time sequence multi-scale feature vector, a training temperature time sequence multi-scale feature vector and a training frequency time sequence multi-scale feature vector;
calculating the response estimation of the training temperature time sequence multi-scale feature vector relative to the training current time sequence multi-scale feature vector to obtain a training current-temperature response fusion feature matrix;
calculating the response transfer of the training frequency time sequence multi-scale feature vector relative to the training current-temperature response fusion feature matrix to obtain a training multi-parameter transfer associated feature vector;
Passing the training multi-parameter transfer associated feature vector through the classifier to obtain a classification loss function value;
training a time sequence feature extractor and a classifier based on the multi-scale neighborhood feature extraction module based on the classification loss function value and through gradient descent direction propagation, wherein the training multi-parameter transfer associated feature vector is subjected to weight space iterative recursive orientation proposal optimization at each iteration of the training.
A remote control anti-misoperation system of a transformer substation, comprising:
the data acquisition module is used for acquiring current values, temperature values and frequency values of a plurality of preset time points of the monitored transformer substation in a preset time period after the first remote control operation is executed by the sensor group;
a vector arrangement module, configured to arrange the current values, the temperature values, and the frequency values at the plurality of predetermined time points into a current timing input vector, a temperature timing input vector, and a frequency timing input vector according to a time dimension;
the association coding module is used for carrying out time sequence response association coding on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector so as to obtain multi-parameter transfer association characteristics; and
And the first remote control operation determining module is used for determining whether the first remote control operation is misoperation or not based on the multi-parameter transfer association characteristic. The association coding module comprises:
the characteristic extraction unit is used for respectively carrying out characteristic extraction on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector through a time sequence characteristic extractor based on a deep neural network model so as to obtain a current time sequence multi-scale characteristic vector, a temperature time sequence multi-scale characteristic vector and a frequency time sequence multi-scale characteristic vector;
the responsiveness estimation calculation unit is used for calculating responsiveness estimation of the temperature time sequence multi-scale characteristic vector relative to the current time sequence multi-scale characteristic vector so as to obtain a current-temperature responsiveness fusion characteristic matrix;
and the responsiveness transfer analysis unit is used for performing responsiveness transfer analysis on the frequency time sequence multi-scale feature vector relative to the current-temperature responsiveness fusion feature matrix so as to obtain the multi-parameter transfer association feature. The deep neural network model is a multi-scale neighborhood feature extraction module.
The transformer substation is a key component in the power system and is used for converting high-voltage electric energy into low-voltage electric energy and distributing, controlling and protecting the electric energy, plays an important role in the power system and ensures the safety and reliability of electric energy transmission and supply.
A substation is generally composed of the following main components:
a transformer: the transformer is a core device of the substation for converting high voltage electrical energy delivered to the substation into low voltage electrical energy suitable for use by a user. The voltage level of the electric energy can be changed through the transformer, and energy conversion between power transmission and distribution is achieved.
Switching device: substations are equipped with various switching devices, such as circuit breakers, disconnectors, load switches, etc., for controlling the on-off and distribution of electrical energy. The switching equipment can realize the switching, isolation and protection of the circuit, and ensure the safe operation of the power system.
Protection equipment: the substation is also equipped with various protection devices including differential protection, overcurrent protection, overvoltage protection, etc., for monitoring the operating state of the power system and taking protective measures in case of a fault or abnormal situation. The protection equipment can timely detect and isolate faults, and the safety of the equipment and personnel is protected.
And (3) a control system: the control system of the transformer substation is used for monitoring and controlling the operation state of the transformer substation. Various parameters and signals can be obtained in real time, and the equipment is remotely controlled and regulated so as to meet the operation requirement of a power system.
Auxiliary equipment: the substation also comprises auxiliary equipment such as a power supply system, a battery pack, communication equipment, monitoring meters and the like. The equipment provides the functions of power supply support, data transmission, equipment state monitoring and the like, and ensures the normal operation and management of the transformer substation.
The remote control operation of the transformer substation refers to the operation of equipment such as a switch and a breaker of the transformer substation through remote control equipment so as to realize the operation control and fault handling of the transformer substation, and an operation instruction is transmitted to the site of the transformer substation through wireless communication, network communication or other remote communication modes so as to realize the remote control operation of the equipment.
Through remote control operation, the equipment such as a switch, a breaker and the like of the transformer substation can be remotely controlled, and distribution, switching and adjustment of electric energy are realized. For example, the switch can be remotely controlled to be switched on and off, so that the on-off operation of the circuit is realized, and the operation requirement of the power system is met. When a transformer station fails, the fault equipment can be subjected to remote power-off or switching operation through remote control operation, so that the fault is isolated, and the safety of a power system is protected. For example, when a certain device fails, the circuit breaker may be remotely operated to cut off power to prevent the fault from expanding or affecting other devices. By remote control operation, the state and parameters of the substation equipment, such as current, voltage, temperature and the like, can be monitored in real time. Meanwhile, debugging and overhauling operations of the equipment can be performed, so that normal operation and performance optimization of the equipment are ensured.
The remote control operation of the transformer substation has the advantages of high efficiency, flexibility and safety, can reduce the workload and risk of manual operation, and improves the accuracy and reliability of operation. Meanwhile, remote control can also realize control of remote or inaccessible equipment, and convenience and flexibility of operation are improved. However, operator inattention, fatigue, inexperience, or undertraining may lead to misoperations. In order to reduce the influence of human factors, the operators need to be fully trained and educated, the operation skills and consciousness of the operators are improved, and meanwhile, strict operation rules and standards are established to ensure the consistency and the correctness of the operation. Substation remote control usually relies on a communication system for instruction transmission, and if the communication system has problems such as faults, delay or interference, misoperation may be caused. In order to prevent the risk of malfunction due to communication problems, it is necessary to ensure the reliability and stability of the communication system, to perform regular maintenance and overhaul, and to establish a backup communication system to cope with possible failures. Malfunction of substation equipment may lead to occurrence of erroneous operation. For example, a malfunction of a switching device may result in a false switch-on or a false switch-off. In order to prevent misoperation caused by equipment faults, regular equipment overhaul and maintenance are needed to ensure the normal operation and reliability of equipment, and meanwhile, an equipment state monitoring and fault diagnosis system is established to discover and process equipment faults in time. To prevent misuse, some security measures and authentication mechanisms may be employed. For example, a double confirmation mechanism is set, and an operator is required to perform double verification to execute key operations; using techniques such as passwords, identity verification or fingerprint identification, and the like, limiting the access and operation of unauthorized personnel; and pre-operation confirmation and check are carried out before key operation, so that the operation correctness is ensured.
In order to reduce the risk of misoperation, the remote control operation of the transformer substation needs to pay attention to training and consciousness of operators, ensure the reliability of a communication system, maintain and overhaul equipment, and take corresponding safety measures and verification mechanisms. In addition, it is also important to continuously monitor and improve the security of substation remote control operating systems.
In one embodiment of the present invention, fig. 1 is a flowchart of a remote control misoperation prevention method for a transformer substation provided in the embodiment of the present invention. Fig. 2 is a schematic diagram of a system architecture of a remote control misoperation prevention method of a transformer substation provided in an embodiment of the present invention. As shown in fig. 1 and 2, a remote control misoperation prevention method for a transformer substation according to an embodiment of the present invention includes: 110, acquiring current values, temperature values and frequency values of a plurality of preset time points of the monitored transformer substation in a preset time period after the first remote control operation is executed by a sensor group; 120, arranging the current values, the temperature values and the frequency values of the plurality of preset time points into a current time sequence input vector, a temperature time sequence input vector and a frequency time sequence input vector according to a time dimension; 130, performing time sequence response association coding on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector to obtain multi-parameter transfer association characteristics; and 140, determining whether the first remote control operation is a misoperation based on the multi-parameter transfer association feature.
In the step 110, when the current value, the temperature value and the frequency value of the monitored substation are obtained, the accuracy and reliability of the data collected by the sensor group need to be ensured. The selection and arrangement of the sensors should take into account the specific situation of the substation and the monitoring requirements. Further, the predetermined period of time should be selected to sufficiently cover a time range in which a malfunction may occur. By acquiring the current values, the temperature values and the frequency values at a plurality of predetermined time points, multi-dimensional data about the operation state of the substation can be acquired, and the data can be used for subsequent time sequence association analysis to help judge whether the first remote control operation is a misoperation.
In the step 120, when the current value, the temperature value, and the frequency value are arranged in time dimension as the time sequence input vector, it is necessary to ensure that the correspondence relationship of the data is accurate. Ensuring that the time intervals of the data are consistent and arranged in time sequence. In addition, normalization or normalization of the data for subsequent analysis and processing may be considered. By arranging the data into time sequence input vectors according to time dimension, the data at a plurality of time points can be integrated into a sequence, the time relation of the data is reserved, the subsequent time sequence association analysis is facilitated, and the dynamic characteristics among the data are captured better.
In the step 130, when the current timing input vector, the temperature timing input vector, and the frequency timing input vector are subjected to the timing response correlation encoding, an appropriate encoding method and model need to be selected. Common methods include Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs), and suitable model structures and parameter settings may be selected according to the particular situation. By performing time sequence response association coding on the time sequence input vector, transfer association characteristics among multiple parameters can be extracted, time sequence relation and mutual influence among captured data are facilitated, and a more comprehensive and accurate basis is provided for judging whether the first remote control operation is misoperation or not.
In the step 140, when determining whether the first remote control operation is a malfunction based on the multi-parameter transfer association feature, an appropriate classification model or rule determination method needs to be established. The training and verification of the model requires the use of accurate tag data to ensure the reliability of the judgment result. Meanwhile, proper thresholds or rules are required to be set according to actual conditions so as to balance the risks of false alarm and missing alarm. Whether the first remote control operation is misoperation or not is judged based on the multi-parameter transfer association characteristics, so that the detection accuracy and efficiency of misoperation can be improved, timely discovery and correction of misoperation are facilitated, and potential risks to substation equipment and a power system are reduced.
Aiming at the technical problems, the technical conception of the invention is that the time sequence analysis of the parameter data of the transformer substation is carried out by monitoring the parameter data, such as a current value, a temperature value and a frequency value, of the transformer substation after the first remote control operation is carried out in real time and introducing a data processing and analyzing algorithm at the rear end, so that the monitoring of the state and the running condition of the transformer substation is carried out based on the time sequence change trend of the current, the temperature and the frequency of the transformer substation after the first remote control operation is carried out, the abnormal condition is identified, whether the first remote control operation is misoperation is judged, and the early warning is carried out, thereby realizing the real-time detection of the rationality and the safety of the remote control operation and improving the accuracy and the reliability of the remote control operation.
Specifically, in the technical solution of the present application, first, current values, temperature values, and frequency values at a plurality of predetermined time points of the monitored substation in a predetermined period of time after the first remote control operation is performed are acquired by the sensor group. Then, considering that the current value, the temperature value and the frequency value of the monitored transformer substation after the first remote control operation are performed have respective time sequence dynamic change rules in the time dimension, and the current value, the temperature value and the frequency value also have time sequence cooperative association relations, the method provides sufficient basis for detecting the state of the monitored transformer substation after the first remote control operation is performed and judging the misoperation related to the first remote control operation. Therefore, in the technical solution of the present application, it is necessary to further arrange the current values, the temperature values, and the frequency values at the plurality of predetermined time points into a current timing input vector, a temperature timing input vector, and a frequency timing input vector according to a time dimension, so as to integrate distribution information of the current values, the temperature values, and the frequency values in time sequence, respectively.
In one embodiment of the present application, performing time-series responsive correlated encoding on the current time-series input vector, the temperature time-series input vector and the frequency time-series input vector to obtain a multi-parameter transfer correlated feature includes: respectively carrying out feature extraction on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector through a time sequence feature extractor based on a deep neural network model so as to obtain a current time sequence multi-scale feature vector, a temperature time sequence multi-scale feature vector and a frequency time sequence multi-scale feature vector; calculating the response estimation of the temperature time sequence multi-scale feature vector relative to the current time sequence multi-scale feature vector to obtain a current-temperature response fusion feature matrix; and performing a responsive transfer analysis on the frequency-sequential multi-scale feature vector relative to the current-temperature responsive fusion feature matrix to obtain the multi-parameter transfer correlation feature.
The deep neural network model is a multi-scale neighborhood feature extraction module.
Then, feature mining of the current timing input vector, the temperature timing input vector, and the frequency timing input vector is performed using a convolutional neural network model having excellent performance in terms of implicit correlation feature extraction, respectively, particularly considering that since the current value, the temperature value, and the frequency value all have fluctuation in the time dimension, and the time-series variation condition and the fluctuation condition may be weak, it is difficult to perform effective feature capturing and characterization by the conventional feature extraction manner. Therefore, in the technical scheme of the invention, the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector are further subjected to feature mining in a time sequence feature extractor based on a multi-scale neighborhood feature extraction module so as to extract time sequence multi-scale change feature information of the current value, the temperature value and the frequency value under different time spans respectively, thereby obtaining the current time sequence multi-scale feature vector, the temperature time sequence multi-scale feature vector and the frequency time sequence multi-scale feature vector.
During operation of a substation, current and temperature are often closely related, as the magnitude of the current is related to the load conditions of the substation, and an increase or decrease in the load may result in a change in the temperature of the substation. Therefore, in the technical scheme of the application, the response estimation of the temperature time sequence multi-scale feature vector relative to the current time sequence multi-scale feature vector is further calculated to obtain a current-temperature response fusion feature matrix. The sensitivity of temperature to current changes can be measured by calculating a responsiveness estimate of the temperature-time-series multi-scale feature vector relative to the current-time-series multi-scale feature vector. If the temperature is very sensitive to the change in current, i.e. the temperature changes rapidly with the change in current, in remote operation, if a large change in current is found and a small change in temperature is found, it may mean that an abnormal situation exists, possibly caused by a malfunction. And by obtaining the current-temperature response fusion characteristic matrix, the information of the current and the temperature can be fused, and the association characteristic between the current and the temperature can be further extracted, so that the relation between the current and the temperature can be more comprehensively analyzed, and whether the remote control operation is misoperation or not can be more accurately judged.
In one embodiment of the present application, performing a response transfer analysis on the frequency-sequential multi-scale feature vector with respect to the current-temperature responsive fusion feature matrix to obtain the multi-parameter transfer-related feature includes: and calculating the response transfer of the frequency time sequence multiscale feature vector relative to the current-temperature response fusion feature matrix to obtain a multi-parameter transfer association feature vector as the multi-parameter transfer association feature.
In the operation process of the transformer substation, the frequency is an important parameter, and reflects the stability and the operation state of the power system. When the frequency deviates from the standard value, the individual devices in the power system may not be operated synchronously, causing unbalance and instability of the power system, which may lead to an improper supply of the power load and even a malfunction of the power system. In addition, it is also considered that the frequency variation of the substation may be related to the variation of current and temperature, for example, when the load increases, the current increases, which may lead to a decrease in frequency; the change in temperature also affects the frequency back, for example, an increase in temperature can lead to increased loss of the device, which in turn affects frequency stability. Therefore, in the technical scheme of the invention, the response transfer of the frequency time sequence multi-scale feature vector relative to the current-temperature response fusion feature matrix is further calculated to obtain a multi-parameter transfer association feature vector. By obtaining the multi-parameter transfer correlation feature vector, correlation information among current, temperature and frequency can be comprehensively considered. Thus, the comprehensive influence between the two can be more comprehensively analyzed, and the accuracy and the reliability of remote control operation are further improved.
In one embodiment of the present application, determining whether the first remote operation is a malfunction based on the multi-parameter transfer association feature includes: the multi-parameter transfer association feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the monitored transformer substation has abnormality or not; and determining whether the first remote control operation is an erroneous operation based on the classification result.
And then, the multi-parameter transfer association feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the monitored transformer substation has an abnormality or not. That is, the classification processing is performed by utilizing the comprehensive response time sequence association characteristic information among the current value, the temperature value and the frequency value of the monitored transformer substation after the first remote control operation is performed, so that whether the monitored transformer substation has an abnormality or not is detected and judged, and whether the first remote control operation is an misoperation or not is determined based on the classification result, thereby realizing the real-time detection of the rationality and the safety of the remote control operation and improving the accuracy and the reliability of the remote control operation.
Classifying the multi-parameter transfer associated feature vectors through a classifier to obtain a classification result of whether the monitored transformer substation has abnormality. This classification result may be used to indicate whether the operating state of the substation is normal. If the classification result shows that there is an abnormality, it may mean that the substation has a fault, an abnormality of equipment or other abnormal conditions, and further inspection and processing are required.
Based on the classification result, it can be determined whether the first remote operation is an erroneous operation. If the classification result shows that there is an abnormality in the substation and the execution of the first remote operation is related to this abnormal state, it may be preliminarily determined that the first remote operation is likely to be an erroneous operation. The judgment based on the classification result can provide a quick preliminary screening method to help operators identify potential misoperation conditions.
By inputting the multi-parameter transfer associated feature vector into a classifier for classification, the abnormal state of the transformer substation can be automatically identified by using a machine learning or statistical method. Compared with the traditional rule-based method, the feature vector and classifier-based method can capture abnormal modes more accurately, and accuracy of misoperation detection is improved. The real-time monitoring and early warning of the running state of the transformer substation can be realized by continuously acquiring and analyzing the multi-parameter transfer associated feature vector and carrying out classification judgment in real time. Once the transformer substation is abnormal, operators can take measures in time, so that further loss and risk are avoided. The classification results may provide operators with information about the status of the substation, helping them to make decisions and perform operations. If the classification result shows that the transformer substation is normal, the operator can continue to execute the planned operation; if the classification result shows abnormality, the operator can pause the operation and further check and confirm to avoid potential risks caused by misoperation.
In an embodiment of the present application, the substation remote control anti-misoperation method further includes a training step: and the time sequence feature extractor and the classifier are used for training the time sequence feature extractor and the classifier based on the multi-scale neighborhood feature extraction module. The training step comprises the following steps: acquiring training data, wherein the training data comprises training current values, training temperature values and training frequency values of the monitored transformer substation at a plurality of preset time points in a preset time period after a first remote control operation is executed, and whether the monitored transformer substation has an abnormal real value or not; arranging the training current values, the training temperature values and the training frequency values of the plurality of preset time points into training current time sequence input vectors, training temperature time sequence input vectors and training frequency time sequence input vectors according to time dimensions; passing the training current time sequence input vector, the training temperature time sequence input vector and the training frequency time sequence input vector through the time sequence feature extractor based on the multi-scale neighborhood feature extraction module to obtain a training current time sequence multi-scale feature vector, a training temperature time sequence multi-scale feature vector and a training frequency time sequence multi-scale feature vector; calculating the response estimation of the training temperature time sequence multi-scale feature vector relative to the training current time sequence multi-scale feature vector to obtain a training current-temperature response fusion feature matrix; calculating the response transfer of the training frequency time sequence multi-scale feature vector relative to the training current-temperature response fusion feature matrix to obtain a training multi-parameter transfer associated feature vector; passing the training multi-parameter transfer associated feature vector through the classifier to obtain a classification loss function value; training a time sequence feature extractor and a classifier based on the multi-scale neighborhood feature extraction module based on the classification loss function value and through gradient descent direction propagation, wherein the training multi-parameter transfer associated feature vector is subjected to weight space iterative recursive orientation proposal optimization at each iteration of the training.
In particular, in the technical solution of the present application, a training current time-series multiscale feature vector, a training temperature time-series multiscale feature vector and a training frequency time-series multiscale feature vector respectively express local time-series associated features of a current value, a temperature value and a frequency value, so that the training current-temperature response fusion feature matrix obtained by calculating the response estimation of the training temperature time-series multiscale feature vector relative to the training current time-series multiscale feature vector is used for expressing the current-temperature feature domain response of time-series feature distribution, and the training multi-parameter transfer associated feature vector obtained by calculating the response transfer of the training frequency time-series multiscale feature vector relative to the training current-temperature response fusion feature matrix further expresses the frequency-current temperature feature domain response transfer of time-series feature distribution. However, although the training multi-parameter transfer correlation feature vector substantially follows the local timing correlation distribution, misalignment of the current value, the temperature value, and the frequency value in the timing direction also causes deviation of the timing feature space expression on the timing distribution of the training multi-parameter transfer correlation feature vector from the respective timing feature space expressions of the current value, the temperature value, and the frequency value, which also causes difficulty in convergence of the weight matrix of the classifier with respect to class labels belonging to the timing feature space dimension of a predetermined sample when the training multi-parameter transfer correlation feature vector is classified by the classifier, affecting the training effect of the classifier.
Therefore, when classifying the training multi-parameter transfer associated feature vector by a classifier, the applicant of the present application performs weight space iterative recursive directional proposed optimization on the training multi-parameter transfer associated feature vector at each iteration, specifically expressed as: carrying out weight space iterative recursive directional proposal optimization on the training multi-parameter transfer associated feature vector by using the following optimization formula to obtain an optimized training multi-parameter transfer associated feature vector; wherein, the optimization formula is:
wherein M is 1 And M 2 The weight matrix of the last iteration and the current iteration are respectively V c Is the training multi-parameter transfer association feature vector,represents matrix multiplication, +. the exponential operation of the vector represents the calculation of a natural exponential function value raised to the power of the eigenvalue of each position in the vector, V' c Representing the optimization training multi-parameter transfer association feature vector.
Here, the weighted spatial iterative recursive directed proposed optimization may be performed by shifting the training multi-parameter to be classified initially into an associated feature vector V c As anchor points to transfer associated feature vectors V corresponding to the training multiple parameters based on weight matrix iteration in weight space c Anchor footprints (anchor points) under different sample time sequence space feature distribution dimensions are obtained from different sample time sequence space feature distribution directions to serve as directional proposals (oriented proposal) for iterative recursion in a weight space, so that class confidence and local accuracy of weight matrix convergence are improved based on prediction proposals, and training effect of the training multi-parameter transfer associated feature vectors through a classifier is improved. Therefore, the state and the running condition of the transformer substation can be monitored based on the time sequence variation trend of the current, the temperature and the frequency of the transformer substation after the first remote control operation is executed, so that abnormal conditions are identified, whether the first remote control operation is misoperation or not is judged, and early warning is carried out, so that the real-time detection of the rationality and the safety of the remote control operation is realized, and the accuracy and the reliability of the remote control operation are improved.
In summary, the remote control misoperation prevention method for the transformer substation according to the embodiment of the invention is explained, which monitors parameter data, such as a current value, a temperature value and a frequency value, of the transformer substation after the first remote control operation is executed in real time, and introduces a data processing and analyzing algorithm at the rear end to perform time sequence analysis of the parameter data of the transformer substation, so as to monitor the state and the running condition of the transformer substation based on the time sequence variation trend of the current, the temperature and the frequency of the transformer substation after the first remote control operation is executed, to identify abnormal conditions and judge whether the first remote control operation is misoperation or not, thereby performing early warning, realizing real-time detection of the rationality and the safety of the remote control operation, and improving the accuracy and the reliability of the remote control operation.
Fig. 3 is a block diagram of a remote control misoperation prevention system of a transformer substation provided in an embodiment of the present invention. As shown in fig. 3, the remote control anti-misoperation system 200 of the transformer substation includes: a data acquisition module 210, configured to acquire, by a sensor group, current values, temperature values, and frequency values at a plurality of predetermined time points of a monitored substation within a predetermined period of time after performing a first remote control operation; a vector arrangement module 220, configured to arrange the current values, the temperature values, and the frequency values at the plurality of predetermined time points into a current timing input vector, a temperature timing input vector, and a frequency timing input vector according to a time dimension; a correlation encoding module 230, configured to perform a time-sequence response correlation encoding on the current time-sequence input vector, the temperature time-sequence input vector and the frequency time-sequence input vector to obtain a multi-parameter transfer correlation characteristic; and a first remote control operation determining module 240, configured to determine whether the first remote control operation is a malfunction based on the multi-parameter transfer association feature.
In the remote control misoperation prevention system of the transformer substation, the associated coding module comprises: the characteristic extraction unit is used for respectively carrying out characteristic extraction on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector through a time sequence characteristic extractor based on a deep neural network model so as to obtain a current time sequence multi-scale characteristic vector, a temperature time sequence multi-scale characteristic vector and a frequency time sequence multi-scale characteristic vector; the responsiveness estimation calculation unit is used for calculating responsiveness estimation of the temperature time sequence multi-scale characteristic vector relative to the current time sequence multi-scale characteristic vector so as to obtain a current-temperature responsiveness fusion characteristic matrix; and the responsiveness transfer analysis unit is used for performing responsiveness transfer analysis on the frequency time sequence multi-scale feature vector relative to the current-temperature responsiveness fusion feature matrix so as to obtain the multi-parameter transfer association feature.
In the remote control misoperation prevention system of the transformer substation, the deep neural network model is a multi-scale neighborhood feature extraction module.
It will be appreciated by those skilled in the art that the specific operations of the respective steps in the above-described substation remote control anti-misoperation system have been described in detail in the above description of the substation remote control anti-misoperation method with reference to fig. 1 to 2, and thus, repetitive descriptions thereof will be omitted.
As described above, the substation remote control anti-misoperation system 200 according to the embodiment of the present invention can be implemented in various terminal devices, for example, a server or the like for substation remote control anti-misoperation. In one example, the substation remote control anti-misoperation system 200 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 substation remote control anti-misoperation system 200 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 remote control anti-misoperation system 200 of the transformer substation can also be one of a plurality of hardware modules of the terminal equipment.
Alternatively, in another example, the substation remote control anti-misoperation system 200 and the terminal device may be separate devices, and the substation remote control anti-misoperation system 200 may be connected to the terminal device through a wired and/or wireless network, and transmit interaction information according to a agreed data format.
Fig. 4 is an application scenario diagram of a remote control misoperation prevention method for a transformer substation provided in 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), temperature values (e.g., C2 as illustrated in fig. 4), and frequency values (e.g., C3 as illustrated in fig. 4) of a plurality of predetermined time points of the monitored substation within a predetermined period of time after performing the first remote control operation are acquired by the sensor group; then, the acquired current value, temperature value, and frequency value are input into a server (e.g., S as illustrated in fig. 4) in which a substation remote control anti-misoperation algorithm is deployed, wherein the server is capable of processing the current value, the temperature value, and the frequency value based on the substation remote control anti-misoperation algorithm to determine whether the first remote control operation is an misoperation.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or described herein.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A remote control misoperation prevention method for a transformer substation is characterized by comprising the following steps:
acquiring current values, temperature values and frequency values of a plurality of preset time points of a monitored transformer substation in a preset time period after a first remote control operation is executed by a sensor group;
arranging the current values, the temperature values and the frequency values of the plurality of preset time points into a current time sequence input vector, a temperature time sequence input vector and a frequency time sequence input vector according to a time dimension;
Performing time sequence response association coding on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector to obtain multi-parameter transfer association characteristics;
and determining whether the first remote control operation is a malfunction based on the multi-parameter transfer association feature.
2. The substation remote control anti-misoperation method according to claim 1, characterized in that performing time-series response association coding on the current time-series input vector, the temperature time-series input vector and the frequency time-series input vector to obtain a multi-parameter transfer association feature comprises:
respectively carrying out feature extraction on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector through a time sequence feature extractor based on a deep neural network model so as to obtain a current time sequence multi-scale feature vector, a temperature time sequence multi-scale feature vector and a frequency time sequence multi-scale feature vector;
calculating the response estimation of the temperature time sequence multi-scale feature vector relative to the current time sequence multi-scale feature vector to obtain a current-temperature response fusion feature matrix; and
and performing responsive transfer analysis on the frequency time sequence multi-scale feature vector relative to the current-temperature responsive fusion feature matrix to obtain the multi-parameter transfer association feature.
3. The substation remote control misoperation prevention method according to claim 2, wherein the deep neural network model is a multi-scale neighborhood feature extraction module.
4. The method for remote control anti-misoperation of a transformer substation according to claim 3, wherein performing a response transfer analysis on the frequency-sequential multi-scale feature vector relative to the current-temperature response fusion feature matrix to obtain the multi-parameter transfer association feature comprises: and calculating the response transfer of the frequency time sequence multiscale feature vector relative to the current-temperature response fusion feature matrix to obtain a multi-parameter transfer association feature vector as the multi-parameter transfer association feature.
5. The substation remote control misoperation prevention method according to claim 4 wherein determining whether a first remote operation is an misoperation based on the multi-parameter transfer correlation feature comprises:
the multi-parameter transfer association feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the monitored transformer substation has abnormality or not;
based on the classification result, it is determined whether the first remote operation is an erroneous operation.
6. The substation remote control misoperation prevention method according to claim 5, further comprising the training step of: and the time sequence feature extractor and the classifier are used for training the time sequence feature extractor and the classifier based on the multi-scale neighborhood feature extraction module.
7. The substation remote control misoperation prevention method according to claim 6, characterized in that the training step includes:
acquiring training data, wherein the training data comprises training current values, training temperature values and training frequency values of the monitored transformer substation at a plurality of preset time points in a preset time period after a first remote control operation is executed, and whether the monitored transformer substation has an abnormal real value or not;
arranging the training current values, the training temperature values and the training frequency values of the plurality of preset time points into training current time sequence input vectors, training temperature time sequence input vectors and training frequency time sequence input vectors according to time dimensions;
passing the training current time sequence input vector, the training temperature time sequence input vector and the training frequency time sequence input vector through the time sequence feature extractor based on the multi-scale neighborhood feature extraction module to obtain a training current time sequence multi-scale feature vector, a training temperature time sequence multi-scale feature vector and a training frequency time sequence multi-scale feature vector;
calculating the response estimation of the training temperature time sequence multi-scale feature vector relative to the training current time sequence multi-scale feature vector to obtain a training current-temperature response fusion feature matrix;
Calculating the response transfer of the training frequency time sequence multi-scale feature vector relative to the training current-temperature response fusion feature matrix to obtain a training multi-parameter transfer associated feature vector;
passing the training multi-parameter transfer associated feature vector through the classifier to obtain a classification loss function value;
training a time sequence feature extractor and a classifier based on the multi-scale neighborhood feature extraction module based on the classification loss function value and through gradient descent direction propagation, wherein the training multi-parameter transfer associated feature vector is subjected to weight space iterative recursive orientation proposal optimization at each iteration of the training.
8. A remote control anti-misoperation system of a transformer substation, which is characterized by comprising:
the data acquisition module is used for acquiring current values, temperature values and frequency values of a plurality of preset time points of the monitored transformer substation in a preset time period after the first remote control operation is executed by the sensor group;
a vector arrangement module, configured to arrange the current values, the temperature values, and the frequency values at the plurality of predetermined time points into a current timing input vector, a temperature timing input vector, and a frequency timing input vector according to a time dimension;
The association coding module is used for carrying out time sequence response association coding on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector so as to obtain multi-parameter transfer association characteristics; and
and the first remote control operation determining module is used for determining whether the first remote control operation is misoperation or not based on the multi-parameter transfer association characteristic.
9. The substation remote control anti-misoperation system according to claim 8, wherein the association coding module comprises:
the characteristic extraction unit is used for respectively carrying out characteristic extraction on the current time sequence input vector, the temperature time sequence input vector and the frequency time sequence input vector through a time sequence characteristic extractor based on a deep neural network model so as to obtain a current time sequence multi-scale characteristic vector, a temperature time sequence multi-scale characteristic vector and a frequency time sequence multi-scale characteristic vector;
the responsiveness estimation calculation unit is used for calculating responsiveness estimation of the temperature time sequence multi-scale characteristic vector relative to the current time sequence multi-scale characteristic vector so as to obtain a current-temperature responsiveness fusion characteristic matrix; and
and the responsiveness transfer analysis unit is used for performing responsiveness transfer analysis on the frequency time sequence multi-scale feature vector relative to the current-temperature responsiveness fusion feature matrix so as to obtain the multi-parameter transfer association feature.
10. The substation remote control anti-misoperation system according to claim 9, wherein the deep neural network model is a multi-scale neighborhood feature extraction module.
CN202311396950.6A 2023-10-26 2023-10-26 Remote control misoperation prevention method and system for transformer substation Pending CN117458710A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311396950.6A CN117458710A (en) 2023-10-26 2023-10-26 Remote control misoperation prevention method and system for transformer substation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311396950.6A CN117458710A (en) 2023-10-26 2023-10-26 Remote control misoperation prevention method and system for transformer substation

Publications (1)

Publication Number Publication Date
CN117458710A true CN117458710A (en) 2024-01-26

Family

ID=89584802

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311396950.6A Pending CN117458710A (en) 2023-10-26 2023-10-26 Remote control misoperation prevention method and system for transformer substation

Country Status (1)

Country Link
CN (1) CN117458710A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113124929A (en) * 2021-04-13 2021-07-16 国网陕西省电力公司铜川供电公司 Transformer substation multi-parameter signal acquisition comprehensive analysis system and method
JP7240691B1 (en) * 2021-09-08 2023-03-16 山東大学 Data drive active power distribution network abnormal state detection method and system
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
CN116647411A (en) * 2023-07-17 2023-08-25 厦门巴掌互动科技有限公司 Game platform network security monitoring and early warning method
CN116772944A (en) * 2023-08-25 2023-09-19 克拉玛依市燃气有限责任公司 Intelligent monitoring system and method for gas distribution station
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

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113124929A (en) * 2021-04-13 2021-07-16 国网陕西省电力公司铜川供电公司 Transformer substation multi-parameter signal acquisition comprehensive analysis system and method
JP7240691B1 (en) * 2021-09-08 2023-03-16 山東大学 Data drive active power distribution network abnormal state detection method and system
CN116647411A (en) * 2023-07-17 2023-08-25 厦门巴掌互动科技有限公司 Game platform network security monitoring and early warning method
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
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
CN116772944A (en) * 2023-08-25 2023-09-19 克拉玛依市燃气有限责任公司 Intelligent monitoring system and method for gas distribution station

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
明晓航 等: "基于EMD－SAM－LSTM 模型的220kV 变压器顶层油温组合预测研究", 电力大数据, vol. 25, no. 9, 25 September 2022 (2022-09-25) *

Similar Documents

Publication Publication Date Title
CN106597231B (en) GIS fault detection system and method based on Multi-source Information Fusion and deep learning network
CN111898669B (en) Abnormal event early warning system of direct-current submerged arc furnace based on machine learning
CN112713649B (en) Power equipment residual life prediction method based on extreme learning machine
CN109962443B (en) SCD-based protection, overhaul and safety measure automatic generation system and method
CN107843800B (en) Power supply network monitoring method, device and system
CN113763667B (en) Fire disaster early warning and state monitoring device and method based on 5G edge calculation
CN110988592A (en) Electric leakage safety monitoring device and method
CN116740654B (en) Substation operation prevention and control method based on image recognition technology
CN117590223B (en) Online monitoring system and method for circuit breaker
CN108512222A (en) A kind of intelligent substation complex automatic system
CN205911832U (en) Circuit breaker intelligent components
CN117350548B (en) Power distribution equipment potential safety hazard investigation method
CN117612345A (en) Power equipment state monitoring and alarming system and method
CN117110798B (en) Fault detection method and system for intelligent power distribution network
CN103364669B (en) GIS equipment operational condition online test method and system
CN117458710A (en) Remote control misoperation prevention method and system for transformer substation
CN116169778A (en) Processing method and system based on power distribution network anomaly analysis
CN104849654A (en) Method for online monitoring breaker
CN114062911A (en) Breaker state monitoring method and device, computer equipment and storage medium
CN114899944B (en) Communication management machine
KR102604708B1 (en) Switchboard diagnosis system based on artificial intelligence and switchboard diagnosis method based on artificial intelligence
CN116707144B (en) Low-voltage distribution box fault early warning method
CN116467633B (en) Online automatic analysis system and method for power grid faults and protection actions
Carbone et al. A Multiple Model Based Approach for Deep Space Power System Fault Diagnosis
CN115660478B (en) Transformer-based health state monitoring method, device, equipment and storage medium

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