CN113904444A - State prediction method for secondary circuit of direct current voltage divider or current divider of converter station - Google Patents
State prediction method for secondary circuit of direct current voltage divider or current divider of converter station Download PDFInfo
- Publication number
- CN113904444A CN113904444A CN202111163036.8A CN202111163036A CN113904444A CN 113904444 A CN113904444 A CN 113904444A CN 202111163036 A CN202111163036 A CN 202111163036A CN 113904444 A CN113904444 A CN 113904444A
- Authority
- CN
- China
- Prior art keywords
- determining
- divider
- monitoring
- voltage divider
- converter station
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012544 monitoring process Methods 0.000 claims abstract description 220
- 239000011159 matrix material Substances 0.000 claims abstract description 99
- 230000002159 abnormal effect Effects 0.000 claims abstract description 89
- 238000005070 sampling Methods 0.000 claims abstract description 73
- 230000008859 change Effects 0.000 claims description 83
- 230000002354 daily effect Effects 0.000 claims description 46
- 230000003442 weekly effect Effects 0.000 claims description 38
- 238000010606 normalization Methods 0.000 claims description 35
- 238000004364 calculation method Methods 0.000 claims description 33
- 230000003203 everyday effect Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 17
- 230000015654 memory Effects 0.000 claims description 16
- 238000010219 correlation analysis Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 abstract description 9
- 238000012423 maintenance Methods 0.000 abstract description 9
- 238000013024 troubleshooting Methods 0.000 abstract description 5
- 230000005540 biological transmission Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 239000013307 optical fiber Substances 0.000 description 5
- 238000012935 Averaging Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
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]
-
- 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
- H02J13/00006—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 information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
- H02J13/00016—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 information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using a wired telecommunication network or a data transmission bus
- H02J13/00017—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 information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using a wired telecommunication network or a data transmission bus using optical fiber
-
- 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
- Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
- Y04S40/12—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment
- Y04S40/124—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment using wired telecommunication networks or data transmission busses
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Human Computer Interaction (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The application relates to a method and a device for predicting the state of a direct current voltage divider or a secondary circuit of a current divider of a converter station, computer equipment and a storage medium. The method comprises the following steps: according to a preset sampling frequency, sampling a secondary loop of a direct-current voltage divider or a current divider of a current conversion station at regular time to obtain sampling data; determining a monitoring signal according to the sampling data; determining a monitoring quantity matrix of a direct current voltage divider or a secondary circuit of the current divider of the converter station according to the monitoring signal; inputting the monitoring quantity matrix into an associated prediction model, and determining a prediction result; and comparing the prediction result with historical monitoring signals in normal operation, abnormal operation and fault states respectively, and determining the operation state of the secondary circuit of the direct current voltage divider or the shunt of the converter station predicted in real time. By adopting the method, operation and maintenance personnel can master the equipment state information in real time, so that the hidden danger of advanced treatment is realized, the troubleshooting efficiency is improved, and the safe and stable operation of the system is ensured.
Description
Technical Field
The application relates to the field of high-voltage direct current measurement, in particular to a method and a device for predicting the state of a direct current voltage divider or a secondary circuit of the current divider of a converter station, computer equipment and a storage medium.
Background
High-voltage or extra-high-voltage direct current power transmission can realize long-distance power transmission, has the advantages of reducing loss, reducing corridors, saving energy, protecting environment, having high efficiency and the like, and gradually becomes a mainstream power transmission mode. Meanwhile, the high-voltage or extra-high-voltage direct-current transmission system plays a supporting role in safe and stable operation of the main grid frame in the construction of a novel electric power system constructed in China. Meanwhile, the western clean energy can effectively reduce the emission of carbon dioxide through a direct current large channel, and can be vigorously constructed in a future period of time.
The direct current voltage divider or the shunt is key equipment of a high-voltage or extra-high voltage direct current transmission system, consists of primary equipment and secondary equipment together, and provides real and reliable primary current or voltage information for a direct current control protection system. The resistance box, the far-end module, the transmission optical fiber and the measuring device form a direct-current voltage divider or a shunt secondary circuit device, one path of electric signals can be converted into multiple paths of optical signals, then the measured values are sent to the measuring device through the optical fiber, and then the measured values are respectively sent to corresponding direct-current control protection systems. The measuring device is used for receiving digital sampling signals transmitted by data optical fibers of remote modules of each direct current measuring point, preprocessing and checking the sampling data, and then distributing the sampling data to the direct current control protection system through the optical fibers according to related protocols; the function of the remote module (RTU) is to provide laser energy by the measuring device through the energizing fiber. During operation, after the performance of the remote module, the transmission optical fiber or the measuring device is reduced, abnormal phenomena such as high laser driving current and high laser temperature of the measuring device occur, meanwhile, deviation occurs between sampling data of the measuring device and real data, and finally misoperation of a control and protection system can be caused, so that locking of a direct current system is caused.
In the related art, the operation state monitoring of the secondary circuit of the direct current divider or the current divider is only through operation and maintenance experience of a manufacturer, an alarm threshold value is simply set, and when the laser driving current of the measuring device is high and the laser temperature is higher than the threshold value, an alarm signal is generated. According to the field operation and maintenance experience, when the monitoring mode gives an alarm, irreversible performance reduction occurs to equipment corresponding to a secondary circuit of the direct current voltage divider or the current divider, and the equipment develops into a fault in a very short time, so that the secondary circuit is unavailable. Therefore, the state of the secondary circuit of the direct current voltage divider or the current divider before reaching the alarm value cannot be pre-judged in advance by the method, operation and maintenance personnel are informed in advance, advanced treatment hidden dangers are realized, and the safe and stable operation of the system is ensured. Therefore, a method for predicting the state of the dc voltage divider or the secondary circuit of the dc voltage divider in the converter station is urgently needed.
Disclosure of Invention
In view of the above, it is necessary to provide a method, an apparatus, a computer device and a storage medium for predicting the state of a dc voltage divider or a secondary circuit of a dc voltage divider in a converter station.
A method for predicting the state of a secondary loop of a direct current voltage divider or a current divider of a converter station comprises the following steps:
according to a preset sampling frequency, sampling a secondary loop of a direct-current voltage divider or a current divider of a current conversion station at regular time to obtain sampling data;
determining a monitoring signal according to the sampling data;
determining a monitoring quantity matrix of a direct current voltage divider or a secondary circuit of the current divider of the converter station according to the monitoring signal;
inputting the monitoring quantity matrix into an associated prediction model, and determining a prediction result;
and comparing the prediction result with historical monitoring signals in normal operation, abnormal operation and fault states respectively, and determining the operation state of the secondary circuit of the direct current voltage divider or the shunt of the converter station predicted in real time.
In one embodiment, the sampled data includes laser temperature and laser drive current; accordingly, determining a monitoring signal based on the sampled data includes:
determining the change rate of the temperature of the laser in each hour, each day and each week according to the temperature of the laser;
determining the change rate of the laser driving current every hour, every day and every week according to the laser driving current;
the hourly, daily and weekly rates of change in laser temperature and rates of change in laser drive current were used as monitoring signals.
In one embodiment, the monitoring signal comprises hourly, daily and weekly rates of change of the laser temperature, and the matrix of monitoring quantities comprises hourly, daily and weekly matrices of temperature monitoring quantities; correspondingly, according to the monitoring signal, determining a monitoring quantity matrix of a converter station direct current voltage divider or a divider secondary circuit, including:
carrying out mean value normalization calculation according to the temperature change rate of the laser device per hour, and determining a temperature monitoring quantity matrix per hour;
performing mean value normalization calculation according to the daily laser driving temperature change rate, and determining a daily temperature monitoring quantity matrix;
and carrying out mean value normalization calculation according to the temperature change rate of the laser device every week to determine a temperature monitoring quantity matrix every week.
In one embodiment, the monitoring signal comprises hourly, daily and weekly rates of laser drive current change, and the matrix of monitored quantities comprises hourly, daily and weekly matrices of current monitored quantities; correspondingly, according to the monitoring signal, determining a monitoring quantity matrix of a converter station direct current voltage divider or a divider secondary circuit, including:
according to the change rate of the laser driving current per hour, carrying out mean value normalization calculation to determine a current monitoring quantity matrix per hour;
performing mean value normalization calculation according to the change rate of the laser driving current every day, and determining a current monitoring quantity matrix every day;
and performing mean value normalization calculation according to the change rate of the laser driving current of each week to determine a current monitoring quantity matrix of each week.
In one embodiment, inputting the monitoring quantity matrix into the correlation prediction model and determining the prediction result comprises:
inputting half data in a monitoring quantity matrix of an hourly, daily and weekly converter station direct current voltage divider or a divider secondary circuit into a correlation prediction model for training, and determining the trained correlation prediction model;
inputting the other half data in the monitoring quantity matrix of the converter station direct current voltage divider or the divider secondary circuit every hour, every day and every week into the trained associated prediction model to obtain a prediction result.
In one embodiment, the comparing the prediction result with the historical monitoring signals in the normal operation, the abnormal operation and the fault state respectively, and before determining the operation state of the converter station dc voltage divider or the splitter secondary circuit predicted in real time, includes:
determining a historical monitoring signal in a normal operation state according to a direct current voltage divider or a secondary circuit of a current divider of the converter station in the normal operation state;
determining a historical monitoring signal in an abnormal operation state according to a direct current voltage divider or a secondary circuit of a current divider of the converter station in the abnormal operation state;
and determining a historical monitoring signal in the fault alarm state according to the direct current voltage divider or the secondary circuit of the current divider of the converter station in the fault alarm state.
In one embodiment, the comparing the prediction result with the historical monitoring signals in the normal operation, the abnormal operation and the fault state respectively to determine the real-time predicted operation state of the secondary circuit of the direct current voltage divider or the splitter of the converter station includes:
performing correlation analysis on the prediction result according to the historical monitoring signal in the normal operation state to determine a correlation result in the normal operation state;
judging whether the correlation result in the normal operation state is larger than a set normal threshold value or not, and returning to continue monitoring if the correlation result in the normal operation state is smaller than the set normal threshold value;
if the correlation result in the normal operation state is larger than the set normal threshold, performing correlation analysis on the prediction result according to the historical monitoring signal in the abnormal operation state to determine the correlation result in the abnormal operation state;
judging whether the correlation result in the abnormal operation state is greater than a set abnormal threshold value or not, and outputting an abnormal operation signal if the correlation result in the abnormal operation state is less than the set abnormal threshold value;
if the correlation result in the abnormal operation state is larger than the set abnormal threshold, performing correlation analysis on the prediction result according to the historical monitoring signal in the fault state to determine the correlation result in the fault state;
judging whether the correlation result in the fault state is greater than a set fault threshold value or not, and if the correlation result in the fault state is less than the set fault threshold value, outputting a fault early warning signal;
and if the correlation result in the fault state is greater than the set fault threshold value, outputting a fault alarm signal.
A device for predicting the state of a secondary circuit of a dc voltage divider or splitter of a converter station, the device comprising:
the first acquisition module is used for sampling the secondary circuit of the direct-current voltage divider or the current divider of the current conversion station at regular time according to a preset sampling frequency to acquire sampling data;
the first determining module is used for determining a monitoring signal according to the sampling data;
the second determining module is used for determining a monitoring quantity matrix of the direct current voltage divider or the secondary circuit of the current divider of the converter station according to the monitoring signal;
the third determining module is used for inputting the monitoring quantity matrix into the correlation prediction model and determining a prediction result;
and the fourth determination module is used for comparing the prediction result with the historical monitoring signals in normal operation, abnormal operation and fault states respectively and determining the real-time predicted operation state of the direct current voltage divider or the secondary circuit of the current divider of the converter station.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
according to a preset sampling frequency, sampling a secondary loop of a direct-current voltage divider or a current divider of a current conversion station at regular time to obtain sampling data;
determining a monitoring signal according to the sampling data;
determining a monitoring quantity matrix of a direct current voltage divider or a secondary circuit of the current divider of the converter station according to the monitoring signal;
inputting the monitoring quantity matrix into an associated prediction model, and determining a prediction result;
and comparing the prediction result with historical monitoring signals in normal operation, abnormal operation and fault states respectively, and determining the operation state of the secondary circuit of the direct current voltage divider or the shunt of the converter station predicted in real time.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
according to a preset sampling frequency, sampling a secondary loop of a direct-current voltage divider or a current divider of a current conversion station at regular time to obtain sampling data;
determining a monitoring signal according to the sampling data;
determining a monitoring quantity matrix of a direct current voltage divider or a secondary circuit of the current divider of the converter station according to the monitoring signal;
inputting the monitoring quantity matrix into an associated prediction model, and determining a prediction result;
and comparing the prediction result with historical monitoring signals in normal operation, abnormal operation and fault states respectively, and determining the operation state of the secondary circuit of the direct current voltage divider or the shunt of the converter station predicted in real time.
According to the state prediction method and device for the secondary circuit of the direct current voltage divider or the splitter of the converter station, the computer equipment and the storage medium, the direct current voltage divider or the secondary circuit of the splitter of the converter station is sampled at regular time according to the preset sampling frequency, and sampling data are obtained. And determining a monitoring signal according to the sampling data. And determining a monitoring quantity matrix of the direct current voltage divider or the secondary loop of the current divider of the converter station according to the monitoring signal. And inputting the monitoring quantity matrix into the correlation prediction model to determine a prediction result. And comparing the prediction result with historical monitoring signals in normal operation, abnormal operation and fault states respectively, and determining the operation state of the secondary circuit of the direct current voltage divider or the shunt of the converter station predicted in real time.
Compared with the prior art that the alarm threshold value is simply set through operation and maintenance experience of a manufacturer for monitoring the operation state of the secondary circuit of the direct current voltage divider or the current divider, when the laser driving current of the measuring device is high and the laser temperature is higher than the threshold value, an alarm signal is generated, and because the operation state of the secondary circuit of the direct current voltage divider or the current divider can be predicted in real time, operation and maintenance personnel can master the equipment state information in real time, thereby realizing advanced treatment of hidden dangers, further improving the troubleshooting efficiency and ensuring safe and stable operation of the system.
Drawings
Fig. 1 is a schematic view of an application scenario of a state prediction method of a dc voltage divider or a secondary circuit of a current divider of a converter station in an embodiment;
FIG. 2 is a schematic flow chart illustrating a method for predicting the state of a DC voltage divider or a secondary circuit of a converter station according to an embodiment;
FIG. 3 is a schematic diagram of a matrix of monitoring quantities in another embodiment;
FIG. 4 is a diagram illustrating predicted results in yet another embodiment;
FIG. 5 is a block diagram of a device for predicting the state of a DC voltage divider or a secondary circuit of a converter station according to an embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It will be understood that, as used herein, the terms "first," "second," and the like may be used herein to describe various terms, but these terms are not limited by these terms unless otherwise specified. These terms are only used to distinguish one term from another. For example, the third preset threshold and the fourth preset threshold may be the same or different without departing from the scope of the present application.
The method for predicting the state of the direct current voltage divider or the secondary circuit of the current divider of the converter station can be applied to the application environment shown in fig. 1. The terminal 101 performs timing sampling on a direct-current voltage divider or a secondary circuit of a current divider of the current conversion station according to a preset sampling frequency to obtain sampling data; the server 102 determines a monitoring signal according to the sampling data; the server 102 determines a monitoring quantity matrix of a direct current voltage divider or a secondary circuit of the current divider of the converter station according to the monitoring signal; the server 102 inputs the monitoring quantity matrix into the correlation prediction model to determine a prediction result; and the server 102 compares the prediction result with the historical monitoring signals in normal operation, abnormal operation and fault states respectively to determine the real-time predicted operation state of the direct current voltage divider or the secondary circuit of the current divider of the converter station.
Wherein the terminal 101 communicates with the server 102 via a network. The terminal 101 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices, and the server 102 may be implemented by an independent server or a server cluster formed by a plurality of servers.
In an embodiment, as shown in fig. 2, a method for predicting a state of a dc voltage divider or a secondary circuit of a dc voltage divider of a converter station is provided, where the method is applied to a server, and an implementation subject is described as an example of the server, and the method includes the following steps:
201. according to a preset sampling frequency, sampling a secondary loop of a direct-current voltage divider or a current divider of a current conversion station at regular time to obtain sampling data;
202. determining a monitoring signal according to the sampling data;
203. determining a monitoring quantity matrix of a direct current voltage divider or a secondary circuit of the current divider of the converter station according to the monitoring signal;
204. inputting the monitoring quantity matrix into an associated prediction model, and determining a prediction result;
205. and comparing the prediction result with historical monitoring signals in normal operation, abnormal operation and fault states respectively, and determining the operation state of the secondary circuit of the direct current voltage divider or the shunt of the converter station predicted in real time.
In the above step 201, the sampling frequency refers to the time interval required for performing two consecutive samplings in one day, for example, the sampling frequency may be 20 min/time. The sampling data comprises two kinds of data, the sampling time of the two kinds of data is consistent, and the sampling points of the two kinds of data can be multiple, the number and the positions of the sampling points of the two kinds of data are the same, for example, 20 sampling points of one kind of data are respectively at A1, A2, …, A19 and A20; therefore, there are 20 measurement points for the other data, and the corresponding sampling points are also at a1, a2, …, a19, and a 20.
In the step 202, the monitoring signal does not specifically refer to a certain signal, but is a general term for all signals calculated according to the sampling data, and thus may include a plurality of signals. Specifically, different sampled data are respectively calculated to obtain various signals, so that the monitoring signals are determined.
In step 203, since the monitor signal includes a plurality of types of signals, the monitor amount matrix determined from the monitor signal also includes a plurality of types of matrices.
In step 205, the embodiment of the present invention does not specifically limit the obtaining manner of the historical monitoring signal in the normal operation, the abnormal operation, and the fault state, and includes but is not limited to: the acquiring method is the same as the acquiring method of the monitoring signals in the step 202, that is, the historical data corresponding to the normal operation, the abnormal operation and the fault state are acquired, the historical data are analyzed and processed, and the historical monitoring signals corresponding to the normal operation, the abnormal operation and the fault state are determined.
Specifically, the prediction result needs to be compared with the historical monitoring signal in the normal operation state to obtain a first comparison result, whether the prediction result needs to be compared with the historical monitoring signal in the abnormal operation state or not is judged according to the first comparison result, and if the prediction result does not need to be compared, the corresponding operation state is output;
if the prediction result is compared with the historical monitoring signal in the abnormal operation state, a second comparison result is obtained, whether the prediction result needs to be compared with the historical monitoring data in the fault state or not is judged according to the second comparison result, and if the prediction result does not need to be compared, the corresponding operation state is output;
if the predicted result is compared with the historical monitoring signal in the fault state, a third comparison result is obtained, and the corresponding operation state is output according to the third comparison result.
According to the method provided by the embodiment of the invention, the data in the converter station direct current voltage divider or the secondary circuit of the divider is sampled and analyzed to obtain the prediction result, and then the prediction result is compared with the historical monitoring signals in normal operation, abnormal operation and fault states respectively, so that the real-time predicted operation state of the converter station direct current voltage divider or the secondary circuit of the divider can be obtained, and therefore, operation and maintenance personnel can master the system state information in real time, the advanced treatment of hidden dangers is realized, the operation safety of the system is further improved, and the equipment can stably operate.
In one embodiment, the sampled data includes laser temperature and laser drive current; accordingly, determining a monitoring signal based on the sampled data includes:
301. determining the change rate of the temperature of the laser in each hour, each day and each week according to the temperature of the laser;
302. determining the change rate of the laser driving current every hour, every day and every week according to the laser driving current;
303. the hourly, daily and weekly rates of change in laser temperature and rates of change in laser drive current were used as monitoring signals.
Specifically, regarding the manner of calculating the change rate of the laser temperature every hour, every day, and every week, the embodiment of the present invention is not particularly limited thereto, and includes but is not limited to:
firstly, according to all laser temperature data, the change rate of the laser temperature per hour is calculated. And averaging the laser temperature change rates of all the hours in a day, and taking the average value as the laser temperature change rate of the day so as to calculate the laser temperature change rate of each day. And finally, averaging the laser temperature change rates of all days in a week, and taking the average value as the laser temperature change rate of the week so as to calculate the laser temperature change rate of each week.
Specifically, regarding the manner of calculating the change rate of the laser current hourly, daily, and weekly, the embodiment of the present invention is not particularly limited thereto, and includes but is not limited to:
the change rate of the laser current per hour is calculated according to all the laser current data. And averaging the laser current change rates of all the hours in a day, and taking the average value as the laser current change rate of the day so as to calculate the laser current change rate of each day. And finally, averaging the laser current change rates of all the days in a week, and taking the average value as the laser current change rate of the week so as to calculate the laser temperature change rate of each week.
The laser temperature and the sampling points of the laser driving current are in one-to-one correspondence, so the hourly, daily and weekly laser temperature change rates respectively correspond to the hourly, daily and weekly laser driving current change rates.
According to the method provided by the embodiment of the invention, the influence caused by error data can be reduced by calculating the temperature of the laser in the direct current voltage divider or the secondary loop of the current divider of the converter station and the change rate of the driving current, so that the accuracy of the sampled data is improved.
In one embodiment, the monitoring signal includes hourly, daily, and weekly rates of change of laser temperature, and the matrix of monitored quantities includes hourly, daily, and weekly matrices of temperature monitored quantities; correspondingly, according to the monitoring signal, determining a monitoring quantity matrix of a converter station direct current voltage divider or a divider secondary circuit, including:
401. carrying out mean value normalization calculation according to the temperature change rate of the laser device per hour, and determining a temperature monitoring quantity matrix per hour;
402. performing mean value normalization calculation according to the daily laser driving temperature change rate, and determining a daily temperature monitoring quantity matrix;
403. and carrying out mean value normalization calculation according to the temperature change rate of the laser device every week to determine a temperature monitoring quantity matrix every week.
The mean normalization means that the mean of all data is obtained by calculation, and then all data are normalized according to the mean.
Specifically, the hourly, daily and weekly laser temperature change rates are respectively averaged, then normalization is performed according to the respective average values, and finally the normalized values are used for constructing corresponding hourly, daily and weekly temperature monitoring quantity matrixes.
According to the method provided by the embodiment of the invention, the mean value normalization calculation is respectively carried out on the hourly, daily and weekly laser temperature change rates, so that the fluctuation of data can be reduced, the numerical value fluctuation in the constructed monitoring quantity matrix is reduced, and the solving speed of the model can be increased when the monitoring quantity matrix is input into the correlation prediction model.
In one embodiment, the monitoring signal includes hourly, daily, and weekly rates of laser drive current change, and the matrix of monitored quantities includes hourly, daily, and weekly matrices of current monitored quantities; correspondingly, according to the monitoring signal, determining a monitoring quantity matrix of a converter station direct current voltage divider or a divider secondary circuit, including:
501. according to the change rate of the laser driving current per hour, carrying out mean value normalization calculation to determine a current monitoring quantity matrix per hour;
502. performing mean value normalization calculation according to the change rate of the laser driving current every day, and determining a current monitoring quantity matrix every day;
503. and performing mean value normalization calculation according to the change rate of the laser driving current of each week to determine a current monitoring quantity matrix of each week.
Specifically, the hourly, daily and weekly laser driving current change rates are respectively averaged, then normalization is performed according to the respective average values, and finally the normalized values are used for constructing corresponding hourly, daily and weekly current monitoring quantity matrixes.
According to the method provided by the embodiment of the invention, the average value normalization calculation is carried out on the hourly, daily and weekly laser driving current change rates respectively, and then the matrix is constructed by using the calculated values, so that the hourly, daily and weekly current monitoring quantity matrix can be obtained.
In one embodiment, inputting the monitoring quantity matrix into the correlation prediction model and determining the prediction result comprises:
601. inputting half data in a monitoring quantity matrix of an hourly, daily and weekly converter station direct current voltage divider or a divider secondary circuit into a correlation prediction model for training, and determining the trained correlation prediction model;
602. inputting the other half data in the monitoring quantity matrix of the converter station direct current voltage divider or the divider secondary circuit every hour, every day and every week into the trained associated prediction model, and determining the prediction result.
Specifically, any half of data in a monitoring quantity matrix of an hourly, daily and weekly converter station direct current voltage divider or a secondary circuit of the current divider is firstly input into a correlation prediction model, and training is carried out on a cyclic neural network layer of the correlation prediction model to obtain a trained correlation prediction model; and then inputting the rest half data in the monitoring quantity matrix into the trained correlation prediction model, extracting the characteristic parameters of the monitoring quantity matrix through the long-term and short-term memory network, and inputting the characteristic parameters into the recurrent neural network layer to obtain a prediction result.
According to the method provided by the embodiment of the invention, the prediction result is determined through the multidimensional variation incidence relation between the laser temperature and the laser driving current in the secondary circuit of the direct current divider/divider, so that the fault state can be obtained in advance, and the fault troubleshooting efficiency is further improved.
In one embodiment, before comparing the prediction result with historical monitoring signals in normal operation, abnormal operation and fault states respectively and determining the operation state of the converter station direct current voltage divider or the divider secondary circuit predicted in real time, the method includes:
701. determining a historical monitoring signal in a normal operation state according to a direct current voltage divider or a secondary circuit of a current divider of the converter station in the normal operation state;
702. determining a historical monitoring signal in an abnormal operation state according to a direct current voltage divider or a secondary circuit of a current divider of the converter station in the abnormal operation state;
703. and determining a historical monitoring signal in the fault alarm state according to the direct current voltage divider or the secondary circuit of the current divider of the converter station in the fault alarm state.
Specifically, a historical monitoring signal in a normal operation state is obtained according to the laser temperature and the driving current of the converter station direct current voltage divider or the secondary circuit of the current divider in the normal operation state in a past period of time. And acquiring a historical monitoring signal in an abnormal operation state according to the laser temperature and the driving current of the converter station direct current voltage divider or the secondary circuit of the current divider in the abnormal operation state for a period of time. And acquiring a historical monitoring signal in a fault state according to the laser temperature and the driving current of the converter station direct current voltage divider or the secondary circuit of the current divider in the fault state in a past period of time.
For example, the laser temperature and the driving current in the converter station direct current voltage divider or the secondary circuit of the current divider under the normal operation state of 5-10 months in a year are obtained, and data of 20150 sampling points are obtained and processed, so that the historical monitoring signal under the normal operation state is obtained.
For example, the laser temperature and the driving current of the laser in the converter station direct current voltage divider or the secondary circuit of the current divider under the abnormal operation state of 6-9 months in a year are obtained, and data of 1300 sampling points are obtained, and the data are processed to obtain the historical monitoring signal under the normal operation state.
For example, the laser temperature and the driving current of the laser in the direct current voltage divider or the secondary loop of the current divider of the converter station under the condition of three faults in 7-9 months of a year are obtained, and the data of 192 sampling points are obtained by processing the data, so that the historical monitoring signal under the fault condition is obtained.
According to the method provided by the embodiment of the invention, historical data in different states in different time periods are obtained and processed, so that historical monitoring signals in different states are obtained.
In one embodiment, comparing the prediction result with historical monitoring signals in normal operation, abnormal operation and fault state respectively, and determining the operation state of the converter station direct current voltage divider or the secondary circuit of the divider predicted in real time, includes:
801. performing correlation analysis on the prediction result according to the historical monitoring signal in the normal operation state to determine a correlation result in the normal operation state;
802. judging whether the correlation result in the normal operation state is larger than a set normal threshold value or not, and returning to continue monitoring if the correlation result in the normal operation state is smaller than the set normal threshold value;
803. if the correlation result in the normal operation state is larger than the set normal threshold, performing correlation analysis on the prediction result according to the historical monitoring signal in the abnormal operation state to determine the correlation result in the abnormal operation state;
804. judging whether the correlation result in the abnormal operation state is greater than a set abnormal threshold value or not, and outputting an abnormal operation signal if the correlation result in the abnormal operation state is less than the set abnormal threshold value;
805. if the correlation result in the abnormal operation state is larger than the set abnormal threshold, performing correlation analysis on the prediction result according to the historical monitoring signal in the fault state to determine the correlation result in the fault state;
806. judging whether the correlation result in the fault state is greater than a set fault threshold value or not, and if the correlation result in the fault state is less than the set fault threshold value, outputting a fault early warning signal;
807. and if the correlation result in the fault state is greater than the set fault threshold value, outputting a fault alarm signal.
The type of the correlation analysis is not specifically limited in the embodiments of the present invention, and includes but is not limited to: and the correlation analysis, the cosine similarity analysis, the distance similarity analysis, the Euclidean distance similarity analysis and the like of the correlation coefficient are obtained.
According to the method provided by the embodiment of the invention, the problems that the development trend of the abnormal operation state of the secondary circuit of the direct current voltage divider/divider is difficult to predict and the fault threshold value is difficult to set are solved by comparing the prediction result with the historical monitoring signal, so that the fault troubleshooting efficiency of the system can be improved, and the stable operation of the system is promoted.
The following is a specific example:
the method comprises the following steps:
901. acquiring data of normal operation of a converter station direct current voltage divider or a secondary circuit of the current divider in a normal operation state in 8-12 months in a year, wherein 20150 sampling point data are acquired in 8-12 months in total, and processing to obtain a historical monitoring signal in the normal operation state;
902. acquiring data of abnormal operation of the converter station direct current voltage divider or the secondary circuit of the current divider in an abnormal operation state in 9-11 months of a year, wherein 1300 sampling point data are acquired in 9-11 months of the year, and processing the data to obtain a historical monitoring signal in the abnormal operation state;
903. acquiring data under a failure state of three times in 10-12 months in a year on a secondary circuit of a direct current voltage divider or a current divider of a converter station under the failure state, wherein the data is 192 sampling point data, and obtaining a historical monitoring signal under the failure state after processing;
904. starting from 12 months and 1 day in 2020, the sampling frequency is 15 min/min, the sampling points of the laser temperature and the driving current are 65 respectively, and the direct current voltage divider or the current divider secondary circuit of the current switching station is continuously sampled for one month;
905. respectively calculating the hourly, daily and weekly laser temperature change rate and the driving current change rate as monitoring signals;
906. determining a monitoring quantity matrix according to the monitoring signals, as shown in fig. 3;
907. inputting the monitoring quantity matrix into the correlation prediction model, and outputting a prediction result as shown in FIG. 4;
908. and comparing the prediction result with historical monitoring signals in normal operation, abnormal operation and fault states, and predicting the operation state of the secondary circuit of the direct current voltage divider or the shunt of the convertor station in real time.
In combination with the content of the foregoing embodiments, in an embodiment, as shown in fig. 5, there is provided a state prediction apparatus for a dc voltage divider or a secondary circuit of a current divider of a converter station, including: a first obtaining module 510, a first determining module 511, a second determining module 512, a third determining module 513, and a fourth determining module 514, wherein:
the first obtaining module 510 is configured to sample a secondary circuit of a dc voltage divider or a shunt of the commutation station at regular time according to a preset sampling frequency to obtain sampling data;
a first determining module 511, configured to determine a monitoring signal according to the sampling data;
the second determining module 512 is configured to determine, according to the monitoring signal, a monitoring quantity matrix of the direct current voltage divider or the secondary circuit of the current divider of the converter station;
a third determining module 513, configured to input the monitoring quantity matrix into the association prediction model, and determine a prediction result;
and a fourth determining module 514, configured to compare the prediction result with historical monitoring signals in normal operation, abnormal operation, and fault states, respectively, and determine a real-time predicted operation state of the dc voltage divider or the secondary circuit of the splitter of the converter station.
In one embodiment, the state prediction device for the dc voltage divider or the secondary loop of the splitter of the converter station further comprises:
the temperature change rate determining module is used for determining the laser temperature change rate of each hour, each day and each week according to the laser temperature;
the current change rate determining module is used for determining the change rate of the laser driving current every hour, every day and every week according to the laser driving current;
and the monitoring signal determining module is used for taking the hourly, daily and weekly laser temperature change rate and the laser driving current change rate as monitoring signals.
In one embodiment, the state prediction device for the dc voltage divider or the secondary loop of the splitter of the converter station further comprises:
the time temperature matrix determining module is used for performing mean value normalization calculation according to the temperature change rate of the laser device per hour and determining a temperature monitoring quantity matrix per hour;
the daily temperature matrix determining module is used for performing mean value normalization calculation according to the daily laser driving temperature change rate and determining a daily temperature monitoring quantity matrix;
and the weekly temperature matrix determining module is used for performing mean value normalization calculation according to the weekly laser temperature change rate and determining a weekly temperature monitoring quantity matrix.
In one embodiment, the state prediction device for the dc voltage divider or the secondary loop of the splitter of the converter station further comprises:
the time current matrix determining module is used for performing mean value normalization calculation according to the change rate of the laser driving current in each hour and determining a current monitoring quantity matrix in each hour;
the daily current matrix determining module is used for performing mean value normalization calculation according to the daily laser drive current change rate and determining a daily current monitoring quantity matrix;
and the weekly current matrix determining module is used for performing mean value normalization calculation according to the weekly laser driving current change rate and determining a weekly current monitoring quantity matrix.
In one embodiment, the state prediction device for the dc voltage divider or the secondary loop of the splitter of the converter station further comprises:
the training model top removing module is used for inputting half data in the monitoring quantity matrix of the converter station direct current voltage divider or the secondary circuit of the current divider every hour, every day and every week into the correlation prediction model for training, and determining the trained correlation prediction model;
and the prediction result acquisition module is used for inputting the other half of data in the monitoring quantity matrix of the converter station direct current voltage divider or the secondary circuit of the current divider every hour, every day and every week into the trained associated prediction model to acquire a prediction result.
In one embodiment, the state prediction device for the dc voltage divider or the secondary loop of the splitter of the converter station further comprises:
the first signal determining module is used for determining a historical monitoring signal in a normal operation state according to the direct current voltage divider or the secondary circuit of the current divider of the converter station in the normal operation state;
the second signal determining module is used for determining a historical monitoring signal in an abnormal operation state according to the direct current voltage divider or the secondary circuit of the current divider of the converter station in the abnormal operation state;
and the third signal determination module is used for determining historical monitoring signals in the fault alarm state according to the direct current voltage divider or the secondary circuit of the current divider of the converter station in the fault alarm state.
In one embodiment, the state prediction device for the dc voltage divider or the secondary loop of the splitter of the converter station further comprises:
the first result determining module is used for carrying out correlation analysis on the prediction result according to the historical monitoring signal in the normal operation state and determining the correlation result in the normal operation state;
the first output module is used for judging whether the correlation result in the normal running state is larger than a set normal threshold value or not, and if the correlation result in the normal running state is smaller than the set normal threshold value, returning to continue monitoring;
the second result determining module is used for performing relevance analysis on the prediction result according to the historical monitoring signal in the abnormal operation state and determining the relevance result in the abnormal operation state if the relevance result in the normal operation state is larger than a set normal threshold value;
the second output module is used for judging whether the correlation result in the abnormal operation state is greater than a set abnormal threshold value or not, and outputting an abnormal operation signal if the correlation result in the abnormal operation state is less than the set abnormal threshold value;
the third result determining module is used for performing relevance analysis on the prediction result according to the historical monitoring signal in the fault state and determining the relevance result in the fault state if the relevance result in the abnormal operation state is greater than the set abnormal threshold;
the third output module is used for judging whether the correlation result in the fault state is greater than a set fault threshold value or not, and outputting a fault early warning signal if the correlation result in the fault state is less than the set fault threshold value;
and the fourth output module is used for outputting a fault alarm signal if the correlation result in the fault state is greater than the set fault threshold value.
According to the device provided by the embodiment of the invention, the secondary circuit of the direct current voltage divider or the current divider of the current conversion station is sampled at regular time according to the preset sampling frequency, so as to obtain the sampling data. And determining a monitoring signal according to the sampling data. And determining a monitoring quantity matrix of the direct current voltage divider or the secondary loop of the current divider of the converter station according to the monitoring signal. And inputting the monitoring quantity matrix into the correlation prediction model to determine a prediction result. And comparing the prediction result with historical monitoring signals in normal operation, abnormal operation and fault states respectively, and determining the operation state of the secondary circuit of the direct current voltage divider or the shunt of the converter station predicted in real time.
Compared with the prior art that the alarm threshold value is simply set through operation and maintenance experience of a manufacturer for monitoring the operation state of the secondary circuit of the direct current voltage divider or the current divider, when the laser driving current of the measuring device is high and the laser temperature is higher than the threshold value, an alarm signal is generated, and because the operation state of the secondary circuit of the direct current voltage divider or the current divider can be predicted in real time, operation and maintenance personnel can master the equipment state information in real time, thereby realizing advanced treatment of hidden dangers, further improving the troubleshooting efficiency and ensuring safe and stable operation of the system.
For specific limitations of the state prediction device of the converter station dc voltage divider or the splitter secondary circuit, reference may be made to the above limitations of the state prediction method of the converter station dc voltage divider or the splitter secondary circuit, and details are not described herein again. All or part of each module in the state prediction device of the converter station direct current voltage divider or the divider secondary circuit can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store the sampled data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize a method for predicting the state of a direct current divider or a secondary loop of the divider of the converter station.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
according to a preset sampling frequency, sampling a secondary loop of a direct-current voltage divider or a current divider of a current conversion station at regular time to obtain sampling data;
determining a monitoring signal according to the sampling data;
determining a monitoring quantity matrix of a direct current voltage divider or a secondary circuit of the current divider of the converter station according to the monitoring signal;
inputting the monitoring quantity matrix into an associated prediction model, and determining a prediction result;
and comparing the prediction result with historical monitoring signals in normal operation, abnormal operation and fault states respectively, and determining the operation state of the secondary circuit of the direct current voltage divider or the shunt of the converter station predicted in real time.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining the change rate of the temperature of the laser in each hour, each day and each week according to the temperature of the laser;
determining the change rate of the laser driving current every hour, every day and every week according to the laser driving current;
the hourly, daily and weekly rates of change in laser temperature and rates of change in laser drive current were used as monitoring signals.
In one embodiment, the computer program when executed by the processor further performs the steps of:
carrying out mean value normalization calculation according to the temperature change rate of the laser device per hour, and determining a temperature monitoring quantity matrix per hour;
performing mean value normalization calculation according to the daily laser driving temperature change rate, and determining a daily temperature monitoring quantity matrix;
and carrying out mean value normalization calculation according to the temperature change rate of the laser device every week to determine a temperature monitoring quantity matrix every week.
In one embodiment, the computer program when executed by the processor further performs the steps of:
according to the change rate of the laser driving current per hour, carrying out mean value normalization calculation to determine a current monitoring quantity matrix per hour;
performing mean value normalization calculation according to the change rate of the laser driving current every day, and determining a current monitoring quantity matrix every day;
and performing mean value normalization calculation according to the change rate of the laser driving current of each week to determine a current monitoring quantity matrix of each week.
In one embodiment, the computer program when executed by the processor further performs the steps of:
inputting half data in a monitoring quantity matrix of an hourly, daily and weekly converter station direct current voltage divider or a divider secondary circuit into a correlation prediction model for training, and determining the trained correlation prediction model;
inputting the other half data in the monitoring quantity matrix of the converter station direct current voltage divider or the divider secondary circuit every hour, every day and every week into the trained associated prediction model to obtain a prediction result.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a historical monitoring signal in a normal operation state according to a direct current voltage divider or a secondary circuit of a current divider of the converter station in the normal operation state;
determining a historical monitoring signal in an abnormal operation state according to a direct current voltage divider or a secondary circuit of a current divider of the converter station in the abnormal operation state;
and determining a historical monitoring signal in the fault alarm state according to the direct current voltage divider or the secondary circuit of the current divider of the converter station in the fault alarm state.
In one embodiment, the computer program when executed by the processor further performs the steps of:
performing correlation analysis on the prediction result according to the historical monitoring signal in the normal operation state to determine a correlation result in the normal operation state;
judging whether the correlation result in the normal operation state is larger than a set normal threshold value or not, and returning to continue monitoring if the correlation result in the normal operation state is smaller than the set normal threshold value;
if the correlation result in the normal operation state is larger than the set normal threshold, performing correlation analysis on the prediction result according to the historical monitoring signal in the abnormal operation state to determine the correlation result in the abnormal operation state;
judging whether the correlation result in the abnormal operation state is greater than a set abnormal threshold value or not, and outputting an abnormal operation signal if the correlation result in the abnormal operation state is less than the set abnormal threshold value;
if the correlation result in the abnormal operation state is larger than the set abnormal threshold, performing correlation analysis on the prediction result according to the historical monitoring signal in the fault state to determine the correlation result in the fault state;
judging whether the correlation result in the fault state is greater than a set fault threshold value or not, and if the correlation result in the fault state is less than the set fault threshold value, outputting a fault early warning signal;
and if the correlation result in the fault state is greater than the set fault threshold value, outputting a fault alarm signal.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for predicting the state of a secondary loop of a direct current voltage divider or a current divider of a converter station is characterized by comprising the following steps:
according to a preset sampling frequency, sampling the direct current voltage divider or the secondary loop of the current divider of the converter station at regular time to obtain sampling data;
determining a monitoring signal according to the sampling data;
determining a monitoring quantity matrix of the converter station direct current voltage divider or the secondary circuit of the divider according to the monitoring signal;
inputting the monitoring quantity matrix into a correlation prediction model to determine a prediction result;
and comparing the prediction result with historical monitoring signals in normal operation, abnormal operation and fault states respectively, and determining the operation state of the converter station direct current voltage divider or the secondary circuit of the divider predicted in real time.
2. The method of claim 1, wherein the sampled data includes laser temperature and laser drive current; accordingly, the determining a monitoring signal according to the sampling data includes:
determining the change rate of the laser temperature every hour, every day and every week according to the laser temperature;
determining the change rate of the laser driving current every hour, every day and every week according to the laser driving current;
and taking the hourly, daily and weekly laser temperature change rate and laser driving current change rate as the monitoring signals.
3. The method of claim 1, wherein the monitoring signal comprises hourly, daily, and weekly rates of change of laser temperature, and the matrix of monitored quantities comprises hourly, daily, and weekly matrices of temperature monitored quantities; correspondingly, the determining a monitoring quantity matrix of the converter station direct current voltage divider or the divider secondary circuit according to the monitoring signal includes:
carrying out mean value normalization calculation according to the temperature change rate of the laser device per hour, and determining a temperature monitoring quantity matrix per hour;
performing mean value normalization calculation according to the daily laser driving temperature change rate, and determining a daily temperature monitoring quantity matrix;
and carrying out mean value normalization calculation according to the temperature change rate of the laser device every week to determine a temperature monitoring quantity matrix every week.
4. The method of claim 1, wherein the monitoring signal comprises hourly, daily, and weekly rates of laser drive current change, and the matrix of monitoring amounts comprises an hourly, daily, and weekly matrix of current monitoring amounts; correspondingly, the determining a monitoring quantity matrix of the converter station direct current voltage divider or the divider secondary circuit according to the monitoring signal includes:
according to the change rate of the laser driving current per hour, carrying out mean value normalization calculation to determine a current monitoring quantity matrix per hour;
performing mean value normalization calculation according to the change rate of the laser driving current every day, and determining a current monitoring quantity matrix every day;
and performing mean value normalization calculation according to the change rate of the laser driving current of each week to determine a current monitoring quantity matrix of each week.
5. The method of claim 1, wherein inputting the monitoring quantity matrix into a correlation prediction model to determine a prediction result comprises:
inputting half data in the monitoring quantity matrix of the converter station direct current voltage divider or the divider secondary circuit every hour, every day and every week into the correlation prediction model for training, and determining the trained correlation prediction model;
inputting the other half data in the monitoring quantity matrix of the converter station direct current voltage divider or the splitter secondary circuit every hour, every day and every week into the trained associated prediction model to obtain the prediction result.
6. The method according to claim 1, wherein before comparing the prediction results with historical monitoring signals in normal operation, abnormal operation and fault states respectively and determining the operation state of the converter station direct current voltage divider or the divider secondary circuit predicted in real time, the method comprises:
determining a historical monitoring signal in a normal operation state according to the direct current voltage divider or the secondary circuit of the current divider of the converter station in the normal operation state;
determining a historical monitoring signal in an abnormal operation state according to a direct current voltage divider or a secondary circuit of a current divider of the converter station in the abnormal operation state;
and determining a historical monitoring signal in the fault alarm state according to the direct current voltage divider or the secondary circuit of the current divider of the converter station in the fault alarm state.
7. The method according to claim 1, wherein the comparing the prediction result with the historical monitoring signals in normal operation, abnormal operation and fault state respectively to determine the operation state of the converter station dc voltage divider or the secondary circuit of the divider predicted in real time comprises:
performing correlation analysis on the prediction result according to the historical monitoring signal in the normal operation state to determine a correlation result in the normal operation state;
judging whether the correlation result in the normal operation state is larger than a set normal threshold value or not, and returning to continue monitoring if the correlation result in the normal operation state is smaller than the set normal threshold value;
if the correlation result in the normal operation state is larger than a set normal threshold, performing correlation analysis on the prediction result according to the historical monitoring signal in the abnormal operation state to determine the correlation result in the abnormal operation state;
judging whether the correlation result in the abnormal operation state is greater than a set abnormal threshold value or not, and if the correlation result in the abnormal operation state is less than the set abnormal threshold value, outputting an abnormal operation signal;
if the correlation result in the abnormal operation state is larger than a set abnormal threshold value, performing correlation analysis on the prediction result according to the historical monitoring signal in the fault state to determine the correlation result in the fault state;
judging whether the correlation result in the fault state is greater than a set fault threshold value or not, and if the correlation result in the fault state is less than the set fault threshold value, outputting a fault early warning signal;
and if the correlation result in the fault state is greater than a set fault threshold value, outputting a fault alarm signal.
8. A device for predicting the state of a secondary circuit of a dc voltage divider or splitter of a converter station, said device comprising:
the first acquisition module is used for sampling the direct current voltage divider or the secondary circuit of the current divider of the converter station at regular time according to a preset sampling frequency to acquire sampling data;
the first determining module is used for determining a monitoring signal according to the sampling data;
the second determining module is used for determining a monitoring quantity matrix of the direct current voltage divider or the secondary circuit of the current divider of the converter station according to the monitoring signal;
the third determining module is used for inputting the monitoring quantity matrix into an associated prediction model and determining a prediction result;
and the fourth determination module is used for comparing the prediction result with historical monitoring signals in normal operation, abnormal operation and fault states respectively and determining the operation state of the converter station direct current voltage divider or the secondary circuit of the divider predicted in real time.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111163036.8A CN113904444A (en) | 2021-09-30 | 2021-09-30 | State prediction method for secondary circuit of direct current voltage divider or current divider of converter station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111163036.8A CN113904444A (en) | 2021-09-30 | 2021-09-30 | State prediction method for secondary circuit of direct current voltage divider or current divider of converter station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113904444A true CN113904444A (en) | 2022-01-07 |
Family
ID=79190006
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111163036.8A Pending CN113904444A (en) | 2021-09-30 | 2021-09-30 | State prediction method for secondary circuit of direct current voltage divider or current divider of converter station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113904444A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200288A (en) * | 2014-09-18 | 2014-12-10 | 山东大学 | Equipment fault prediction method based on factor-event correlation recognition |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| GB201904860D0 (en) * | 2019-04-05 | 2019-05-22 | Orxa Grid Ltd | Electrical grid monitoring system |
| CN110763929A (en) * | 2019-08-08 | 2020-02-07 | 浙江大学 | Intelligent monitoring and early warning system and method for convertor station equipment |
| CN111931969A (en) * | 2020-03-20 | 2020-11-13 | 中国南方电网有限责任公司超高压输电公司广州局 | Merging unit equipment state prediction method based on time sequence analysis |
-
2021
- 2021-09-30 CN CN202111163036.8A patent/CN113904444A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200288A (en) * | 2014-09-18 | 2014-12-10 | 山东大学 | Equipment fault prediction method based on factor-event correlation recognition |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| GB201904860D0 (en) * | 2019-04-05 | 2019-05-22 | Orxa Grid Ltd | Electrical grid monitoring system |
| CN110763929A (en) * | 2019-08-08 | 2020-02-07 | 浙江大学 | Intelligent monitoring and early warning system and method for convertor station equipment |
| CN111931969A (en) * | 2020-03-20 | 2020-11-13 | 中国南方电网有限责任公司超高压输电公司广州局 | Merging unit equipment state prediction method based on time sequence analysis |
Non-Patent Citations (1)
| Title |
|---|
| 周源等: "基于AI加速模块的换流站控制保护二次回路预警***", 《电气技术》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112162878B (en) | Database fault discovery method and device, electronic equipment and storage medium | |
| CN111143102B (en) | Abnormal data detection method and device, storage medium and electronic equipment | |
| RU2012155276A (en) | DETECTION AND ANALYSIS OF A Malicious ATTACK | |
| US20230336023A1 (en) | Power quality monitoring in a distribution grid | |
| CN110570544A (en) | method, device, equipment and storage medium for identifying faults of aircraft fuel system | |
| CN110472871B (en) | Investigation method for managing line loss abnormal reasons | |
| US20230050490A1 (en) | Systems and Methods for Malicious Attack Detection in Phasor Measurement Unit Data | |
| CN116799927B (en) | Energy storage system management method and energy storage system | |
| CN115529595A (en) | Method, device, equipment and medium for detecting abnormity of log data | |
| CN111309562A (en) | Server failure prediction method, device, equipment and storage medium | |
| CN113992602B (en) | Cable monitoring data uploading method, device, equipment and storage medium | |
| CN115129011A (en) | Industrial resource management method based on edge calculation | |
| CN108845285B (en) | Electric energy metering device detection method and system | |
| CN108647626B (en) | Method and device for determining incidence relation between power quality event and event cause | |
| CN110544031B (en) | Method and device for predicting reliability of electric energy meter, computer equipment and storage medium | |
| CN117031182A (en) | Method and system for detecting abnormal telemetering value of substation terminal | |
| CN113904444A (en) | State prediction method for secondary circuit of direct current voltage divider or current divider of converter station | |
| CN111044100A (en) | Sensor device for electric power metering and control method | |
| EP3312844A1 (en) | Abnormality indication monitoring system | |
| CN112737120B (en) | Regional power grid control report generation method and device and computer equipment | |
| CN113689042B (en) | Fault source prediction method for monitoring node | |
| CN116108394A (en) | Industrial control system flow abnormality detection method, device and medium | |
| CN113311220B (en) | Voltage sag diagnosis method, system, medium and electronic equipment | |
| CN115204487A (en) | Equipment state monitoring method, device, equipment and storage medium | |
| CN114037285A (en) | Distribution network automation application success analysis method and related system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220107 |
|
| RJ01 | Rejection of invention patent application after publication |