CN118395907B - Intelligent terminal for monitoring AC/DC power supply for active/standby station and monitoring method thereof - Google Patents
Intelligent terminal for monitoring AC/DC power supply for active/standby station and monitoring method thereof Download PDFInfo
- Publication number
- CN118395907B CN118395907B CN202410824881.2A CN202410824881A CN118395907B CN 118395907 B CN118395907 B CN 118395907B CN 202410824881 A CN202410824881 A CN 202410824881A CN 118395907 B CN118395907 B CN 118395907B
- Authority
- CN
- China
- Prior art keywords
- data subset
- state
- power supply
- remote signaling
- subset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 17
- 238000012423 maintenance Methods 0.000 claims abstract description 13
- 238000004088 simulation Methods 0.000 claims abstract description 9
- 230000011664 signaling Effects 0.000 claims description 79
- 238000012549 training Methods 0.000 claims description 21
- 238000004891 communication Methods 0.000 claims description 16
- 238000013507 mapping Methods 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 4
- 238000003491 array Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 210000005036 nerve Anatomy 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 description 8
- 238000013461 design Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 241000272814 Anser sp. Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000009423 ventilation Methods 0.000 description 1
Landscapes
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a monitoring and controlling method of an alternating current-direct current power supply for a main-standby station, which comprises the steps of carrying out circuit modeling based on electric simulation software according to the circuit topology of the alternating current-direct current power supply for the main-standby station; setting simulation data according to the electrical simulation software; constructing an operation state judgment model for describing the telemetry data subset and an operation state judgment model for describing the telemetry data subset and the state data subset; transmitting the model to an edge calculation module, and verifying the operation state judgment model for describing the telemetry data subset and the judgment result of the operation state judgment model for describing the telemetry data subset and the state data subset based on the edge calculation module. According to the invention, corresponding solutions are set according to the set different operation scenes, and the control station monitors the equipment switching of the system by using the AC/DC power supply, so that the intelligent and safety performance of the system can be effectively improved, and the operation and maintenance risks are reduced.
Description
Technical Field
The invention belongs to the technical field of power monitoring, and particularly relates to an intelligent terminal for monitoring an alternating current/direct current power supply for a main station and a standby station and a monitoring method thereof.
Background
The transformer substation AC/DC power supply consists of an AC power supply, a DC power supply, an inversion module, a rectification module, a storage battery and a communication module. In order to realize information sharing and interactive operation, each unit needs to be monitored and networked for communication. In normal operation, the alternating current power supply provides stable alternating current power supply for alternating current power utilization devices such as a lighting system, ventilation equipment, monitoring equipment, metering equipment and the like; the direct current power supply is responsible for providing stable direct current power supply for automatic equipment loads such as control, protection and circuit breakers. When a certain loop incoming line power supply fails, the switching of the main power supply and the standby power supply can be realized through the regulation and control of the sectional bus, and the power supply is kept. When the power failure accident occurs in both the main loop and the standby loop, the storage battery is started to provide electric energy for guaranteeing normal operation, and reliable power supply is provided for important alternating current loads such as monitoring, metering, accident lighting and the like through the inversion module.
Currently, a station ac/dc power supply system monitors in real time in a distributed manner. The data monitoring terminal respectively collects a plurality of states in the AC/DC power supply, the inversion module, the rectification module or the storage battery, and sends the states to the monitoring subsystems in an RS485 or local wireless network mode, each monitoring subsystem is connected with the monitoring main system through an Ethernet (IEC 61850/GOOSE communication protocol), and the monitoring main system is connected with the monitoring center through the Ethernet (IEC 61850/MMS communication protocol). The mass monitoring information is transmitted by a rapid and reliable communication mode between layers, and the communication mode is high in cost and still difficult to avoid faults. When the power supply fails, the switching of the main power supply and the standby power supply and the switching of the inversion module all need the instruction of the top monitoring main system or the monitoring host to operate. And the generation of the action instruction depends on multi-dimensional fine granularity monitoring data before and after the fault. Therefore, it is needed to design an ac/dc power monitoring intelligent terminal for a primary/standby station and a monitoring method thereof to solve the above-mentioned problems.
Disclosure of Invention
In order to solve the defects in the prior art, the invention aims to overcome the defects in the prior art and provide a monitoring and controlling method for an alternating current-direct current power supply for a main station and a standby station, which comprises the following steps:
According to the circuit topology of the AC/DC power supply for the active/standby station, carrying out circuit modeling based on electrical simulation software, constructing a relation model of the voltage and the residual electric quantity of the storage battery, and constructing an operation mode and a power relation model of an AC load and a DC load;
setting an inverter, a rectifier and a switch switching logic according to the electrical simulation software, and carrying out numerical simulation to obtain simulation data of alternating current voltage, direct current voltage, storage battery voltage and inverter, rectifier and switch states in the scenes of normal operation of a system, battery operation and maintenance, alternating current faults, direct current faults, battery faults and the like;
Constructing an operation state judgment model for describing the telemetry data subset and an operation state judgment model for describing the telemetry data subset and the state data subset, wherein the input quantity is the values of an alternating current voltage, a direct current voltage, a storage battery voltage, an inverter, a rectifier and a switching state in a time period of 20ms, and the sampling frequency is 1kHz to 5kHz;
Transmitting the model to an edge calculation module, and verifying the operation state judgment model for describing the telemetry data subset and the judgment result of the operation state judgment model for describing the telemetry data subset and the state data subset based on the edge calculation module.
As a further optimization of the above scheme, the model construction method includes the following steps:
s31, setting a data set for constructing a model, and acquiring alternating current voltage, direct current voltage and storage battery voltage based on a sampling frequency of 1kHz to 5kHz, wherein the set is a telemetry data subset; collecting inverter, rectifier and switch states at a sampling frequency of not less than 50Hz, the set being a remote signaling data subset; the operation states of the AC/DC power supply for the active/standby station comprise normal operation, battery operation and maintenance, AC fault, DC fault, battery fault and the like, and are used as state data subsets;
S32, respectively setting 20ms as a period to calculate the characteristic value in the telemetry data subset, the characteristic value of the telemetry data subset and the characteristic value of the state data;
s33, the data disorder is divided into three parts of 6:2:2, namely a training set, a development verification set and a test set, and the training is carried out on the basis of the training set to describe the operation state judgment model of the telemetry data subset and the operation state judgment model of the telemetry data subset and the state data subset.
As a further optimization of the above scheme, the feature value acquisition method of any telemetry data subset is as follows:
Respectively constructing two-dimensional arrays describing the characteristic values of the telemetry data subset and the status data subset, and setting 20ms as a period to perform single acquisition;
Traversing the two-dimensional array, and detecting remote signaling data subset characteristic values and state data subset characteristic values of the array:
if the remote signaling data subset feature value display faults exist in any continuous R periods, deleting the two-dimensional array data of the corresponding periods;
If the state data subset characteristic value display faults exist in any R periods, deleting the two-dimensional array data of the corresponding period.
As a further optimization of the scheme, an operation state judgment model of the telemetry data subset and the remote signaling data subset is constructed:
S331, calculating original weights corresponding to characteristic values in any remote signaling data subsets based on collected station operation sample data:
s332, selecting a training set based on collected station operation sample data, and performing deep nerve training on the selected training set to obtain a prediction state of a remote signaling data subset; acquiring an actual state corresponding to the training set of the remote signaling data subset, and calculating the sum of differences between the actual state and the predicted state of the remote signaling data subset;
S333, constructing a mapping relation between the state number and the original weight based on all the state numbers of the remote signaling data subset:
S334, calculating a state judgment error of the mapping relation in the remote signaling data subset based on the constructed state number and the original weight mapping relation; and calculating the sequence weight corresponding to the characteristic value in the updated remote signaling data subset according to the judgment error.
As a further optimization of the above solution, the operation state judgment model further includes the following:
acquiring sequence weights corresponding to characteristic values in the updated remote signaling data subsets, and calculating sample weights of the remote signaling data subsets acquired in the next period taking 20ms as a period;
wherein, In order to normalize the coefficient of the coefficient,The values of (1) and (1), if the operation state prediction of the remote signaling data subset corresponds to the actual state,Otherwise take-1:
In the above-mentioned method, the step of, The weights are influenced for any subset of telemetry data,The denominator of equation (4) is the duty cycle feedback of the eigenvalue in any of the remote signaling data subsets, which is the average value in the remote signaling data subsets.
As a further optimization of the scheme, based on the constructed state number and original weight mapping relation and the sample weight of the remote signaling data subset, an operation state judgment model for describing the remote signaling data subset and the remote signaling data subset is obtained：
。
As a further optimization of the above scheme, an operation state judgment model of the telemetry data subset and the state data subset is constructed:
As a further optimization of the above scheme, it is provided that For representing the accuracy of the operational state judgment model describing the telemetry data subset and the state data subset:
wherein, Judging model for running stateAccurately judging the corresponding condition of the running state of the state data subset,Is thatThe data error of the non-state data subset is judged as the corresponding condition of the running state of the state data subset,Is thatThe data error of the state data subset is judged as the corresponding condition of the running state of the non-state data subset,Is thatAccurately judging the data of the non-state data subset as the corresponding condition of the running state of the state data subset;
If it is Deleting the characteristic value in the telemetry data subset, the characteristic value of the telemetry data subset and the characteristic value record of the state data subset which are calculated by using the current setting of 20ms as a period, and collecting the characteristic value of the telemetry data subset, the characteristic value of the state data subset and the characteristic value of the telemetry data subset which are set for 20ms as a period in a new round;
If it is Outputting the running state judgment model。
The invention also discloses an intelligent terminal for monitoring the AC/DC power supply for the active/standby station, which comprises the following steps:
The analog quantity input module is used for connecting a voltage transformer of an alternating current bus and a voltage transmitter of a direct current bus, collecting three-phase alternating current voltage analog quantities of an alternating current main power supply and an alternating current standby power supply, and collecting direct current voltage analog quantities of the direct current main power supply and the direct current standby power supply;
The digital quantity input module is used for being connected with the storage battery inspection instrument, collecting digital quantities such as voltage, current, residual capacity (SOC) and the like of the storage battery through the communication interface, and transmitting the digital quantities to the edge calculation module;
The switching value input module is used for connecting the rectifier, the inverter and the switch and collecting the switching feedback states of the rectifier, the inverter and the switch; the switch comprises a line incoming switch, an alternating current bus connecting switch, a direct current bus connecting switch and a storage battery switch of a main power supply and a standby power supply.
The switching value output module is used for connecting the rectifier, the inverter and the switch and controlling the switching of the rectifier, the inverter and the switch;
the edge calculation module is used for being connected with the analog quantity input module, the digital quantity input module, the switching value output module and the communication module;
the communication module is used for connecting the monitoring center and receiving the algorithm model, the configuration parameters and the manual control instruction;
As a further optimization of the scheme, the analog quantity input module converts the input analog quantity into digital quantity and transmits the digital quantity to the edge calculation module; the analog input module uses the chip AD7606 to collect and convert, and the collecting and converting speed is 1kHz to 5kHz.
Compared with the prior art, the invention has the following beneficial effects:
1. According to the invention, through designing the operation state judgment model for describing the remote signaling data subset and the remote sensing data subset and the operation state judgment model for describing the remote sensing data subset and the state data subset, and constructing the learning model through data learning, the operation condition of the whole monitoring system can be judged according to the local operation state of the existing alternating current/direct current power supply for the station, so that corresponding solutions are set according to the set corresponding different operation scenes, the equipment switching of the alternating current/direct current power supply monitoring system for the control station can be effectively improved, the intelligent and safety performance of the system can be effectively improved, and the operation and maintenance risks can be reduced.
2. The invention constructs the characteristic value in the telemetry data subset, the characteristic value of the remote signaling data subset and the characteristic value of the state data, and particularly collects the circuit running state corresponding to the power data at any moment by selecting the power data of the station in the running process of the AC/DC power supply, thereby effectively completing the prediction and judgment of the power data and the circuit running state; in order to further improve the accuracy of the method, the embodiment of the invention also collects and records the characteristic values of the remote signaling data subset, which is specifically expressed as the states of the inverter, the rectifier and the switch.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the accompanying drawings in which:
FIG. 1 is a schematic flow chart of the present invention;
fig. 2 is a schematic structural view of the present invention.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1-2, the embodiment of the invention discloses a method for monitoring and controlling an ac/dc power supply for a master station and a slave station, which comprises the following steps:
S1, carrying out circuit modeling based on electrical simulation software according to the circuit topology of an alternating current/direct current power supply for a main station and a standby station, constructing a relation model of voltage and residual electric quantity of a storage battery, and constructing an operation mode and power relation model of an alternating current load and a direct current load; specifically, modeling based on electrical simulation software, constructing a relation model of voltage and residual electric quantity of a storage battery, and constructing an operation mode and power relation model of alternating current load and direct current load are conventional technical means of research in the industry, and are not described in detail herein;
S2, setting an inverter, a rectifier and a switch switching logic according to the electrical simulation software, and performing numerical simulation to obtain simulation data of alternating current voltage, direct current voltage, storage battery voltage and inverter, rectifier and switch states in the scenes of normal operation of a system, battery operation and maintenance, alternating current faults, direct current faults, battery faults and the like;
Specifically, according to the embodiment of the invention, through simulating the data such as the inverter, the rectifier and the switch switching logic in the operation and maintenance process of the main-standby transformer substation, the simulation data of the AC voltage, the DC voltage, the storage battery voltage, the inverter, the rectifier and the switch state under the scenes such as normal operation, battery operation and maintenance, AC fault, DC fault, battery fault and the like generated by simulation software are correspondingly obtained, so that the simulation data are used for subsequent data processing; the system is an alternating current/direct current power supply monitoring system applied to a main station and a standby station;
S3, constructing an operation state judgment model for describing the telemetry data subset and an operation state judgment model for describing the telemetry data subset and the state data subset, wherein the input quantity is the values of the alternating current voltage, the direct current voltage, the storage battery voltage, the inverter, the rectifier and the switching state in the time period of 20ms, and the sampling frequency is 1kHz to 5kHz;
S4, transmitting the model to an edge calculation module, and verifying a running state judgment model for describing the telemetry data subset and a judgment result of the running state judgment model for describing the telemetry data subset and the state data subset based on the edge calculation module.
Specifically, the method for constructing the model comprises the following steps:
s31, setting a data set for constructing a model, and acquiring alternating current voltage, direct current voltage and storage battery voltage based on a sampling frequency of 1kHz to 5kHz, wherein the set is a telemetry data subset; collecting inverter, rectifier and switch states at a sampling frequency of not less than 50Hz, the set being a remote signaling data subset; the operation states of the AC/DC power supply for the active/standby station comprise normal operation, battery operation and maintenance, AC fault, DC fault, battery fault and the like, and are used as state data subsets;
specifically, based on the application of the invention to the monitoring of the running state of the alternating current/direct current power supply for the station, the embodiment of the invention selects alternating current voltage, direct current voltage and storage battery voltage as telemetry data subsets; selecting an inverter, a rectifier and a switch state to collect statistics, and constructing a remote signaling data subset; the method and the system collect the running states of the AC/DC power supply for the active/standby station, including normal running, battery operation and maintenance, AC fault, DC fault and battery fault, and count and construct a state data subset.
S32, respectively setting 20ms as a period to calculate the characteristic value in the telemetry data subset, the characteristic value of the telemetry data subset and the characteristic value of the state data;
Specifically, the characteristic values in the telemetry data subset of the embodiment of the invention include an effective value of an alternating voltage, an absolute value maximum value of the alternating voltage, an average value of a direct voltage, a maximum value of the direct voltage, a minimum value of the direct voltage, an average value of a storage battery voltage, a maximum value of the storage battery voltage and a minimum value of the storage battery voltage;
The eigenvalue value in the remote signaling data subset of the embodiment of the invention is as follows: the inverter state comprises shutdown, standby, working and fault, which are respectively represented by integers of 0-3, the rectifier state comprises shutdown, standby, working and fault, which are respectively represented by integers of 0-3, and the switch state comprises switching-on, switching-off and fault, which are respectively represented by integers of 0-2;
The characteristic value in the state data subset of the embodiment of the invention is as follows: normal operation, battery operation and maintenance, AC fault, DC fault and battery fault are respectively recorded as integers of 0-4;
The embodiment of the invention constructs the characteristic value in the telemetry data subset, the characteristic value of the telemetry data subset and the characteristic value of the state data, specifically, the power data of the station in the AC/DC power supply operation process is selected, the circuit operation state corresponding to the power data at any moment is acquired, and the prediction and judgment of the power data and the circuit operation state can be effectively completed; in order to further improve the accuracy of the method, the embodiment of the invention also collects and records the characteristic values of the remote signaling data subset, which is specifically expressed as the states of the inverter, the rectifier and the switch.
S33, the data disorder is divided into three parts of 6:2:2, namely a training set, a development verification set and a test set, and the training is carried out on the basis of the training set to describe the operation state judgment model of the telemetry data subset and the operation state judgment model of the telemetry data subset and the state data subset.
It is particularly noted that in the remote signaling and status data subsets, if there are multiple status values for the same device within a 20ms period, the latest status value is characteristic.
Specifically, the method for acquiring the characteristic value of any telemetry data subset is as follows:
Respectively constructing two-dimensional arrays describing the characteristic values of the telemetry data subset and the status data subset, and setting 20ms as a period to perform single acquisition;
Traversing the two-dimensional array, and detecting remote signaling data subset characteristic values and state data subset characteristic values of the array:
if the remote signaling data subset feature value display faults exist in any continuous R periods, deleting the two-dimensional array data of the corresponding periods;
If the state data subset characteristic value display faults exist in any R periods, deleting the two-dimensional array data of the corresponding period.
More specifically, the invention further improves the accuracy and the effectiveness of the telemetry data subset, specifically by constructing a two-dimensional array, the columns of the two-dimensional array represent the telemetry data subset, and the rows of the two-dimensional array represent the telemetry data subset and the status data subset characteristic values; and when the remote signaling data subset characteristic values or the state data subset characteristic values continuously display faults in R periods, deleting the two-dimensional array data of the corresponding periods, namely deleting the corresponding remote signaling data subset characteristic values, and reducing the error rate of the sample data.
Specifically, constructing the operation state judgment model of the telemetry data subset and the telemetry data subset includes the following steps:
S331, calculating original weights corresponding to characteristic values in any remote signaling data subsets based on collected station operation sample data:
s332, selecting a training set based on collected station operation sample data, and performing deep nerve training on the selected training set to obtain a prediction state of a remote signaling data subset; acquiring an actual state corresponding to the training set of the remote signaling data subset, and calculating the sum of differences between the actual state and the predicted state of the remote signaling data subset;
S333, constructing a mapping relation between the state number and the original weight based on all the state numbers of the remote signaling data subset:
S334, calculating a state judgment error of the mapping relation in the remote signaling data subset based on the constructed state number and the original weight mapping relation; and calculating the sequence weight corresponding to the characteristic value in the updated remote signaling data subset according to the judgment error.
Specifically, the running state judgment model further includes the following:
acquiring sequence weights corresponding to characteristic values in the updated remote signaling data subsets, and calculating sample weights of the remote signaling data subsets acquired in the next period taking 20ms as a period;
wherein, In order to normalize the coefficient of the coefficient,The values of (1) and (1), if the operation state prediction of the remote signaling data subset corresponds to the actual state,Otherwise take-1:
In the above-mentioned method, the step of, The weights are influenced for any subset of telemetry data,The denominator of equation (4) is the duty cycle feedback of the eigenvalue in any of the remote signaling data subsets, which is the average value in the remote signaling data subsets.
More specifically, the influence weight of any remote signaling data subset constructed based on the design of the invention can be used for feeding back the importance degree of the characteristic value of any remote signaling data subset in the monitoring and evaluating process for evaluating the active/standby occupied alternating current/direct current power supply, the numerator of the formula (4) represents that the denominator of the formula (4) feeds back the duty ratio condition of the characteristic value in any remote signaling data subset, namelyThe larger the corresponding characteristic value is, the larger the corresponding remote signaling data subset is occupied, and further the larger the influence weight of the corresponding remote signaling data subset is represented, namely, the larger the influence of the corresponding subset data on the running state judgment is represented.
More specifically, in the actual primary-backup type occupied alternating current/direct current power supply monitoring process, the value of the influence weight of the remote signaling data subset mainly depends on the operation working environment, namely different working environments, and the corresponding influence weights are designed to be different; if it isThe value is lower than the defined effective value of the current site working environment, so that the running state judgment result designed by the invention forms a local optimal solution, and the final accuracy judgment of the invention is affected; that is, the invention preferably designsThe method for acquiring the influence weight specifically analyzes different remote signaling data in a corresponding data subset in the operation corresponding to the actual working environment of the current site according to a formula (4), and rapidly acquires and grasps the importance degree of the different remote signaling data by means of any characteristic average value of the remote signaling data and the data subset; meanwhile, the actual duty ratio of any remote signaling data is calculated, a functional relation between the importance of any remote signaling data and the numerical duty ratio of the remote signaling data is constructed, and interference factors forming a local optimal solution are avoided, so that the accuracy of the construction of the operation state judgment model of the remote signaling data subset and the remote signaling data subset is improved.
Specifically, based on the constructed mapping relation between the state number and the original weight and the sample weight of the remote signaling data subset, an operation state judgment model for describing the remote signaling data subset and the remote signaling data subset is obtained：
。
Specifically, an operation state judgment model of the telemetry data subset and the state data subset is constructed:
specifically, it is provided with For representing the accuracy of the operational state judgment model describing the telemetry data subset and the state data subset:
wherein, Judging model for running stateAccurately judging the corresponding condition of the running state of the state data subset,Is thatThe data error of the non-state data subset is judged as the corresponding condition of the running state of the state data subset,Is thatThe data error of the state data subset is judged as the corresponding condition of the running state of the non-state data subset,Is thatAccurately judging the data of the non-state data subset as the corresponding condition of the running state of the state data subset;
If it is Deleting the characteristic value in the telemetry data subset, the characteristic value of the telemetry data subset and the characteristic value record of the state data subset which are calculated by using the current setting of 20ms as a period, and collecting the characteristic value of the telemetry data subset, the characteristic value of the state data subset and the characteristic value of the telemetry data subset which are set for 20ms as a period in a new round;
If it is Outputting the running state judgment model。
According to the invention, through designing the operation state judgment model for describing the remote signaling data subset and the remote sensing data subset and the operation state judgment model for describing the remote sensing data subset and the state data subset, and constructing the learning model through data learning, the operation condition of the whole monitoring system can be judged according to the local operation state of the existing alternating current/direct current power supply for the station, so that corresponding solutions are set according to the set corresponding different operation scenes, the equipment switching of the alternating current/direct current power supply monitoring system for the control station can be effectively improved, the intelligent and safety performance of the system can be effectively improved, and the operation and maintenance risks can be reduced.
The invention also discloses an intelligent terminal for monitoring the AC/DC power supply for the active/standby station, which comprises the following steps:
The analog quantity input module is used for connecting a voltage transformer of an alternating current bus and a voltage transmitter of a direct current bus, collecting three-phase alternating current voltage analog quantities of an alternating current main power supply and an alternating current standby power supply, and collecting direct current voltage analog quantities of the direct current main power supply and the direct current standby power supply;
The digital quantity input module is used for being connected with the storage battery inspection instrument, collecting digital quantities such as voltage, current, residual capacity (SOC) and the like of the storage battery through the communication interface, and transmitting the digital quantities to the edge calculation module; the communication interface comprises RS485, CAN and Ethernet.
The switching value input module is used for connecting the rectifier, the inverter and the switch and collecting the switching feedback states of the rectifier, the inverter and the switch; the switch comprises a line incoming switch, an alternating current bus connecting switch, a direct current bus connecting switch and a storage battery switch of a main power supply and a standby power supply.
The switching value output module is used for connecting the rectifier, the inverter and the switch and controlling the switching of the rectifier, the inverter and the switch; the switch comprises a line incoming switch, a line feeder switch, an alternating current bus connecting switch, a direct current bus connecting switch and a storage battery switch of a main power supply and a standby power supply.
The edge calculation module is used for being connected with the analog quantity input module, the digital quantity input module, the switching value output module and the communication module; according to the input signals, the running state of the system is detected, and a control instruction is generated and output according to the corresponding mode, so that the purpose of controlling the rectifier, the inverter and the switch on site is achieved.
The communication module is used for connecting the monitoring center and receiving the algorithm model, the configuration parameters and the manual control instruction; uploading data such as alternating current voltage, direct current voltage, switching feedback states of a rectifier, an inverter and a switch.
Specifically, the analog quantity input module converts the input analog quantity into digital quantity and transmits the digital quantity to the edge calculation module; the analog input module uses the chip AD7606 to collect and convert, and the collecting and converting speed is 1kHz to 5kHz.
The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the application referred to in the present application is not limited to the specific combinations of the technical features described above, but also covers other technical features formed by any combination of the technical features described above or their equivalents without departing from the inventive concept. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.
Claims (9)
1. The method for monitoring the AC/DC power supply for the active/standby station is characterized by comprising the following steps:
According to the circuit topology of the AC/DC power supply for the active/standby station, carrying out circuit modeling based on electrical simulation software, constructing a relation model of the voltage and the residual electric quantity of the storage battery, and constructing an operation mode and a power relation model of an AC load and a DC load;
the model construction method comprises the following steps:
s31, setting a data set for constructing a model, and acquiring alternating current voltage, direct current voltage and storage battery voltage based on a sampling frequency of 1kHz to 5kHz, wherein the set is a telemetry data subset; collecting inverter, rectifier and switch states at a sampling frequency of not less than 50Hz, the set being a remote signaling data subset; the operation states of the AC/DC power supply for the active/standby station comprise normal operation, battery operation and maintenance, AC fault, DC fault, battery fault and the like, and are used as state data subsets;
s32, respectively setting 20ms as a period to calculate the characteristic value of the telemetry data subset, the characteristic value of the telemetry data subset and the characteristic value of the state data;
s33, the data disorder is divided into three parts of 6:2:2, namely a training set, a development verification set and a test set, and the training is carried out on the basis of the training set to describe an operation state judgment model of the telemetry data subset and an operation state judgment model of the telemetry data subset and the state data subset;
setting an inverter, a rectifier and a switch switching logic according to the electrical simulation software, and carrying out numerical simulation to obtain simulation data of alternating current voltage, direct current voltage, storage battery voltage and inverter, rectifier and switch states in the scenes of normal operation of a system, battery operation and maintenance, alternating current faults, direct current faults, battery faults and the like;
Constructing an operation state judgment model for describing the telemetry data subset and an operation state judgment model for describing the telemetry data subset and the state data subset, wherein the input quantity is the values of an alternating current voltage, a direct current voltage, a storage battery voltage, an inverter, a rectifier and a switching state in a time period of 20ms, and the sampling frequency is 1kHz to 5kHz;
Transmitting the model to an edge calculation module, and verifying the operation state judgment model for describing the telemetry data subset and the judgment result of the operation state judgment model for describing the telemetry data subset and the state data subset based on the edge calculation module.
2. The method for monitoring and controlling a primary-backup ac/dc power supply according to claim 1, wherein the method for acquiring the characteristic value of any telemetry data subset comprises the following steps:
Respectively constructing two-dimensional arrays describing the characteristic values of the telemetry data subset and the status data subset, and setting 20ms as a period to perform single acquisition;
Traversing the two-dimensional array, and detecting remote signaling data subset characteristic values and state data subset characteristic values of the array:
if the remote signaling data subset feature value display faults exist in any continuous R periods, deleting the two-dimensional array data of the corresponding periods;
If the state data subset characteristic value display faults exist in any R periods, deleting the two-dimensional array data of the corresponding period.
3. The method for monitoring and controlling the ac/dc power supply for the active/standby station according to claim 2, wherein an operation state judgment model of the telemetry data subset and the remote data subset is constructed:
S331, calculating original weights corresponding to characteristic values in any remote signaling data subsets based on collected station operation sample data:
；
s332, selecting a training set based on collected station operation sample data, and performing deep nerve training on the selected training set to obtain a prediction state of a remote signaling data subset; acquiring an actual state corresponding to the training set of the remote signaling data subset, and calculating the sum of differences between the actual state and the predicted state of the remote signaling data subset;
S333, constructing a mapping relation between the state number and the original weight based on all the state numbers of the remote signaling data subset:
；
S334, calculating a state judgment error of the mapping relation in the remote signaling data subset based on the constructed state number and the original weight mapping relation; and calculating the sequence weight corresponding to the characteristic value in the updated remote signaling data subset according to the judgment error.
4. The method for monitoring and controlling a primary-backup ac/dc power supply according to claim 3, wherein the operation state judgment model construction further comprises the steps of:
acquiring sequence weights corresponding to characteristic values in the updated remote signaling data subsets, and calculating sample weights of the remote signaling data subsets acquired in the next period taking 20ms as a period;
；
wherein, In order to normalize the coefficient of the coefficient,The values of (1) and (1), if the operation state prediction of the remote signaling data subset corresponds to the actual state,Otherwise take-1:
；
In the above-mentioned method, the step of, The weights are influenced for any subset of telemetry data,The denominator of equation (4) is the duty cycle feedback of the eigenvalue in any of the remote signaling data subsets, which is the average value in the remote signaling data subsets.
5. The method for monitoring and controlling the ac/dc power supply for a primary and a secondary station according to claim 4,
Based on the constructed mapping relation between the state number and the original weight and the sample weight of the remote signaling data subset, acquiring an operation state judgment model for describing the remote signaling data subset and the remote signaling data subset：
。
6. The method for monitoring and controlling ac/dc power supply for primary and secondary stations according to claim 5, wherein an operation state judgment model of a telemetry data subset and a state data subset is constructed:
7. The method for monitoring and controlling the ac/dc power supply for a primary and a secondary station according to claim 6,
Is provided withFor representing the accuracy of the operational state judgment model describing the telemetry data subset and the state data subset:
；
wherein, Judging model for running stateAccurately judging the corresponding condition of the running state of the state data subset,Is thatThe data error of the non-state data subset is judged as the corresponding condition of the running state of the state data subset,Is thatThe data error of the state data subset is judged as the corresponding condition of the running state of the non-state data subset,Is thatAccurately judging the data of the non-state data subset as the corresponding condition of the running state of the state data subset;
If it is Deleting the characteristic value in the telemetry data subset, the characteristic value of the telemetry data subset and the characteristic value record of the state data subset which are calculated by using the current setting of 20ms as a period, and collecting the characteristic value of the telemetry data subset, the characteristic value of the state data subset and the characteristic value of the telemetry data subset which are set for 20ms as a period in a new round;
If it is Outputting the running state judgment model。
8. An ac/dc power supply monitoring intelligent terminal for a primary/standby station employing the monitoring method as claimed in any one of claims 1 to 7, characterized in that the terminal comprises:
The analog quantity input module is used for connecting a voltage transformer of an alternating current bus and a voltage transmitter of a direct current bus, collecting three-phase alternating current voltage analog quantities of an alternating current main power supply and an alternating current standby power supply, and collecting direct current voltage analog quantities of the direct current main power supply and the direct current standby power supply;
The digital quantity input module is used for being connected with the storage battery inspection instrument, collecting digital quantities such as voltage, current, residual capacity (SOC) and the like of the storage battery through the communication interface, and transmitting the digital quantities to the edge calculation module;
the switching value input module is used for connecting the rectifier, the inverter and the switch and collecting the switching feedback states of the rectifier, the inverter and the switch; the switch comprises a wire inlet switch, an alternating current bus connecting switch, a direct current bus connecting switch and a storage battery switch of a main power supply and a standby power supply;
the switching value output module is used for connecting the rectifier, the inverter and the switch and controlling the switching of the rectifier, the inverter and the switch;
the edge calculation module is used for being connected with the analog quantity input module, the digital quantity input module, the switching value output module and the communication module;
The communication module is used for being connected with the monitoring center and receiving the algorithm model, the configuration parameters and the manual control instruction.
9. The intelligent terminal for monitoring ac/dc power supply for a primary/secondary station as set forth in claim 8, wherein,
The analog quantity input module converts the input analog quantity into digital quantity and transmits the digital quantity to the edge calculation module; the analog input module uses the chip AD7606 to collect and convert, and the collecting and converting speed is 1kHz to 5kHz.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410824881.2A CN118395907B (en) | 2024-06-25 | 2024-06-25 | Intelligent terminal for monitoring AC/DC power supply for active/standby station and monitoring method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410824881.2A CN118395907B (en) | 2024-06-25 | 2024-06-25 | Intelligent terminal for monitoring AC/DC power supply for active/standby station and monitoring method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118395907A CN118395907A (en) | 2024-07-26 |
| CN118395907B true CN118395907B (en) | 2024-09-10 |
Family
ID=92007967
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410824881.2A Active CN118395907B (en) | 2024-06-25 | 2024-06-25 | Intelligent terminal for monitoring AC/DC power supply for active/standby station and monitoring method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118395907B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110112824A (en) * | 2019-04-11 | 2019-08-09 | 国网辽宁省电力有限公司电力科学研究院 | A kind of autonomous acquisition of DC power system monitoring data and intelligent management-control method |
| CN115456065A (en) * | 2022-09-05 | 2022-12-09 | 国网上海能源互联网研究院有限公司 | Cloud edge cooperation-based power distribution terminal health state diagnosis method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107942255B (en) * | 2017-11-03 | 2020-04-17 | 智洋创新科技股份有限公司 | Transformer substation storage battery state evaluation method based on data fusion technology |
| CN111665444B (en) * | 2020-07-14 | 2022-12-06 | 国网福建省电力有限公司 | Wiring studying and judging method and storage battery discharging studying and judging method based on communication power supply voltage control |
| CN113346461B (en) * | 2021-06-01 | 2022-02-08 | 南京征途信息技术有限公司 | Automatic power recovery method based on power distribution internet of things gateway |
| CN116317117A (en) * | 2023-02-20 | 2023-06-23 | 国网河北省电力有限公司邯郸市峰峰矿区供电分公司 | Management system of power distribution network |
| CN117913895B (en) * | 2024-01-16 | 2024-10-01 | 重庆大学 | LightGBM-LSTM-based power distribution network topology identification method and device |
-
2024
- 2024-06-25 CN CN202410824881.2A patent/CN118395907B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110112824A (en) * | 2019-04-11 | 2019-08-09 | 国网辽宁省电力有限公司电力科学研究院 | A kind of autonomous acquisition of DC power system monitoring data and intelligent management-control method |
| CN115456065A (en) * | 2022-09-05 | 2022-12-09 | 国网上海能源互联网研究院有限公司 | Cloud edge cooperation-based power distribution terminal health state diagnosis method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118395907A (en) | 2024-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109713793B (en) | Power supply online state evaluation system and method for transformer substation | |
| CN110429714B (en) | Cloud platform intelligent power distribution system based on big data | |
| WO2021217695A1 (en) | Smart data collection and sorting system for smart factory framework-based power supply and distribution grid | |
| CN107463732B (en) | Multi-terminal alternating current-direct current active power distribution network scheduling control simulation system and method | |
| CN113169709A (en) | Solar power generation control system and method based on machine learning | |
| CN104155616A (en) | Photovoltaic system current transformer test platform | |
| CN115395643B (en) | Low-voltage distribution network fault early warning positioning device and system based on full data acquisition and state sensing | |
| CN203135572U (en) | Transformer substation DC device state monitoring system | |
| CN106655516A (en) | Power supply equipment collection device and remote fault diagnosis system | |
| CN115563873A (en) | Digital twin simulation system and method of power network | |
| CN112994097A (en) | High-proportion distributed photovoltaic cooperative control method based on intelligent distribution transformer terminal system | |
| KR20190119207A (en) | An artificial intelligence-based parameter setting value automatic calculation protection relays | |
| CN107063337A (en) | Power-supply device harvester and managing and control system | |
| CN116505656A (en) | Wind-light-storage multifunctional complementary intelligent power utilization system based on 5G Internet of things technology | |
| CN117117820A (en) | Distributed new energy access power distribution network risk assessment and collaborative stabilization method | |
| CN114069860B (en) | Method, device and equipment for determining state of photovoltaic power station and readable storage medium | |
| CN118395907B (en) | Intelligent terminal for monitoring AC/DC power supply for active/standby station and monitoring method thereof | |
| CN114765451A (en) | Photovoltaic power station fault detection method based on fault knowledge graph | |
| CN202059214U (en) | Main intelligent electronic device of transformer intelligent assembly | |
| CN116090665A (en) | Source network lotus stores up integrated management and control system | |
| Zhang et al. | Distributed Architecture of Power Grid Asset Management and Future Research Directions | |
| CN115940416A (en) | Distributed power quality diagnosis method and system | |
| CN206742868U (en) | A kind of intelligent energy storage grid management systems | |
| CN115224743A (en) | Distribution network scheduling management method based on energy interconnection | |
| CN112445167B (en) | Open wisdom energy gateway operating system of interface |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |