CN113013987A - Intelligent automatic power grid monitoring system and working method thereof - Google Patents

Intelligent automatic power grid monitoring system and working method thereof Download PDF

Info

Publication number
CN113013987A
CN113013987A CN202110204675.8A CN202110204675A CN113013987A CN 113013987 A CN113013987 A CN 113013987A CN 202110204675 A CN202110204675 A CN 202110204675A CN 113013987 A CN113013987 A CN 113013987A
Authority
CN
China
Prior art keywords
signal
abnormal
power grid
signals
data processing
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.)
Granted
Application number
CN202110204675.8A
Other languages
Chinese (zh)
Other versions
CN113013987B (en
Inventor
钟秋添
卢晓明
程华新
吴益斌
朱志鑫
王夏菁
曹晶
黄燕帼
李德才
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Fujian Electric Power Co Ltd
Longyan Power Supply Co of State Grid Fujian Electric Power Co Ltd
Original Assignee
State Grid Fujian Electric Power Co Ltd
Longyan Power Supply Co of State Grid Fujian Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Fujian Electric Power Co Ltd, Longyan Power Supply Co of State Grid Fujian Electric Power Co Ltd filed Critical State Grid Fujian Electric Power Co Ltd
Priority to CN202110204675.8A priority Critical patent/CN113013987B/en
Publication of CN113013987A publication Critical patent/CN113013987A/en
Application granted granted Critical
Publication of CN113013987B publication Critical patent/CN113013987B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/16—Electric power substations

Landscapes

  • Engineering & Computer Science (AREA)
  • Power Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Remote Monitoring And Control Of Power-Distribution Networks (AREA)

Abstract

The invention relates to an intelligent automatic monitoring system of a power grid and a working method thereof, wherein the system comprises a data acquisition device, an IES600 system, a data processing device containing a monitoring intelligent algorithm program and a terminal platform; the data acquisition device, the IES600 system, the data processing device and the terminal platform are electrically connected in sequence. The data processing device comprises a fuzzy recognition module, a delay notification module and a self-learning module. The monitoring system can realize automatic signal screening, automatic notification and self-learning according to real-time alarm information, and guarantee safe and stable operation of a power grid.

Description

Intelligent automatic power grid monitoring system and working method thereof
Technical Field
The invention relates to an intelligent automatic monitoring system for a power grid and a working method thereof, belonging to the technical field of power grid monitoring.
Background
With the rapid increase of power consumers and the continuous enlargement of the scale of a power grid, the related data and the signal quantity in the running process of the power grid are exponentially increased, if a monitor still adopts the traditional defect management mode of 'manual monitoring-telephone notification-defect elimination treatment-tracking feedback' when dealing with abnormal signals, under the condition of unchanged personnel configuration, the insufficient bearing capacity is easily generated, the monitoring quality is further reduced, and the frequency of working errors such as missed monitoring, incomplete item handover, untimely defect treatment and the like is caused.
For example, the current grid monitoring operation mode, as shown in fig. 1, works according to the following principle: firstly, signals are sent upwards: the method comprises the steps that when equipment of a transformer substation is in fault or abnormal, an abnormal signal is sent out, and the signal is completely collected and then sent to a monitoring interface of an IES600 system of a dispatching desk; delay 20 s: part of signals are caused by abnormal reasons such as system interference, communication blockage and the like, and are instantaneously restored after the occurrence. In order to filter the interference of the instantaneous reset signal to the monitoring, the SCADA system delays for 20s after receiving the abnormal signal and then displays the signal in a transaction window; third, telephone notification and feedback: the monitor analyzes the signal primarily according to the scheduling rule and the monitoring rule, and informs the operation and maintenance personnel of the unit under the jurisdiction of the equipment according to the actual condition; operation and maintenance or overhaul treatment: and the operation and maintenance personnel check the corresponding interval of the governed transformer substation according to the notice of the monitor. The operation and maintenance personnel are responsible for the abnormity which can be treated on site, and the reason and the treatment condition of the abnormity are reported after the signal is reset; and if the operation and maintenance personnel cannot process the defect, reporting the reason to the monitor and initiating a defect reporting flow by the monitor.
The above mode has two main disadvantages:
one is that the exception notification is not timely. The monitoring post is required to monitor the operation conditions of all devices in the region under jurisdiction, meanwhile, the monitoring post is responsible for remote control operation, emergency handling of accidents and the like, and when various services are busy, a monitor needs to balance the weight and urgency of related work, so that partial abnormal signal notification is not timely, and certain potential safety hazards exist.
Secondly, the efficiency of manual communication is low. Due to the existence of objective factors such as communication equipment defects, personnel quality differences, language accent differences and the like, the time consumption of informing the operation and maintenance personnel of abnormal signals by the monitoring personnel is long, misunderstanding is easily caused, and the abnormal signal handling efficiency is influenced to a certain extent.
Disclosure of Invention
In order to overcome the problems, the invention provides an intelligent automatic monitoring system of a power grid and a working method thereof, wherein the monitoring system can realize automatic signal screening, automatic notification and self-learning according to real-time alarm information, and the safe and stable operation of the power grid is ensured.
The technical scheme of the invention is as follows:
an intelligent automatic monitoring system of a power grid comprises a data acquisition device, an IES600 system, a data processing device containing a monitoring intelligent algorithm program and a terminal platform; the data acquisition device, the IES600 system, the data processing device and the terminal platform are electrically connected in sequence;
the data acquisition device is arranged in the transformer substation, can completely acquire abnormal signals sent by the transformer substation due to equipment faults or abnormity, and sends the abnormal signals to the IES600 system;
the IES600 system receives the abnormal signal from the data acquisition device, delays the abnormal signal by 20s and then uploads the abnormal signal to the data processing device;
after the data processing device distinguishes and screens the abnormal signals, the data processing device carries out operation through a monitoring intelligent algorithm; then automatically selecting to delay and send the notification information to a terminal platform according to the level of the abnormal signal, or selecting to automatically send the notification information to a monitor, and performing manual intervention by the monitor;
and the terminal platform receives the notification information from the data processing device, and after the operation and maintenance personnel read the notification information on the terminal platform, the operation and maintenance personnel perform treatment and feedback.
Further, the data processing device comprises a fuzzy recognition module and a delay notification module;
the fuzzy recognition module is used for matching with a classification database and carrying out distinguishing and screening aiming at the same class part numbers;
and the delay notification module automatically selects delay to send notification information according to the level of the abnormal signal.
Further, the data processing device also comprises a self-learning module;
the self-learning module adopts a self-learning method and records abnormal signals which do not affect the operation of the system but cannot be eliminated by conventional means; the self-learning module automatically records the situations, automatically records the frequent number in the background, and defaults not to send the notification information when the signal appears; when the abnormal signals appear along with other important signals or the total number of the sent signals in a specified time is larger than a specified value, the self-learning module identifies the abnormal signals as stubborn defects, and automatically sends notification information to the terminal platform at the moment; if the signal does not appear after the specified time, the self-learning module can determine the signal as a normal abnormal signal again.
Further, the terminal platform is a mobile terminal APP.
Further, the fuzzy recognition module adopts a fuzzy recognition algorithm to define the similarity Sim of the abnormal signal of the power grid as shown in formula (1):
Figure BDA0002949364340000021
Figure BDA0002949364340000031
in the formula, S is an abnormal signal sequence sent by a data acquisition device, and K is the total number of characters of the abnormal signal sequence; r is a signal classification database, H is the dimension of the database,l is the dimension of the character number storage of the database signals; delta1、Δ2、Δ3The similarity weight of the number of characters, the similarity weight of the position of the character and the similarity weight of the type of the character of the sequence S and R (i) respectively, and the number, the place and the equal are similarity functions of the number, the position and the type of the character respectively;
selecting a maximum sequence R (G) of sim (i), as shown in formula (2):
Figure BDA0002949364340000032
in the formula, RchooseThe signal sequence with the highest similarity to the uploading abnormal signal of the data acquisition device in the signal classification database is provided, and G is the position number of the corresponding signal sequence in the database.
Furthermore, the delay time interval of the delay informing module is set to be N sections according to a step-up mode; the delay algorithm is shown as formula (3):
Figure BDA0002949364340000033
in the formula, N is the occurrence frequency of the alarm signal; t is tiThe ith notification time; Δ tiStep delay of ith time; t is0The observation time for the first signal occurrence; t is1Is a specified first notification time; t ismaxIs the specified maximum observation time.
Further, the self-learning module adopts a self-learning algorithm, and the self-learning algorithm is shown in formula (4):
Figure BDA0002949364340000034
wherein T is the number of days; m is the accumulated value of the alarm times of the alarm signal in the period; t is teMThe retention time of the Mth repeated alarm signal after the defect is eliminated; n isTThe number of alarm times of the signal is T days.
A working method of an intelligent automatic monitoring system of a power grid comprises the following specific steps:
step 1, collecting and uploading abnormal signals;
the data acquisition device completely acquires abnormal signals sent by the transformer substation due to equipment faults or abnormalities and uploads the abnormal signals to the IES600 system;
step 2, delaying an abnormal signal;
the IES600 system delays the abnormal signal for 20s and then uploads the abnormal signal to the data processing device;
step 3, operation and notification of the data processing device;
after the data processing device distinguishes and screens the abnormal signals, the operation is carried out through a monitoring intelligent algorithm; then automatically selecting to delay and send the notification information to a terminal platform according to the level of the abnormal signal, or selecting to automatically send the notification information to a monitor, and performing manual intervention by the monitor;
step 4, operation and maintenance or overhaul treatment;
and the operation and maintenance personnel go to the corresponding interval of the governed transformer substation to dispose according to the notification information on the terminal platform.
Further, the operation and notification of the data processing apparatus in step 3 specifically include the following steps:
step 3.1, through a fuzzy recognition algorithm, matching with the established matching classification database, and carrying out differentiation and screening aiming at the same class part numbers;
step 3.2, automatically selecting delayed sending notification information according to the level of the abnormal signal;
3.3, judging the type of the abnormal signal which does not affect the system operation but cannot be eliminated by a conventional means by a self-learning method; if the abnormal signal appears along with other important signals or the total number of the sent signals in a specified time is larger than a specified value, the abnormal signal is identified as a persistent defect, and a notification message is automatically sent to the terminal platform at the moment; if the signal does not appear after the specified time, the self-learning module can determine the signal as a normal abnormal signal again.
The invention has the following beneficial effects:
1. the monitoring system can realize automatic signal screening, automatic notification and self-learning according to real-time alarm information, and guarantee safe and stable operation of a power grid.
2. The monitoring system is guided by the actual service requirements and defect processing flows of monitoring personnel, functions of monitoring abnormal signals of the power grid, automatic notification, intelligent screening of relevant data and the like are achieved by means of intelligent modules such as fuzzy recognition, intelligent time delay and signal self-learning, the monitoring operation informatization and intelligent control level of the power grid is further improved, and safe and stable operation of the power grid is guaranteed.
3. After the monitoring system is used, the daily workload of monitoring is reduced, the configuration of each value of personnel can be reduced from 3 people to 2 people, the proportion of the personnel is reduced by one third, and the saving of human resources is effectively realized.
Drawings
Fig. 1 is a schematic diagram of an operation mode of power grid monitoring in the prior art.
Fig. 2 is a schematic diagram of an operation mode of the grid monitoring of the present application.
Fig. 3 is a schematic diagram illustrating the compiling of the monitoring signal classification database according to the present application.
Fig. 4 is a schematic diagram illustrating a setting principle of the delay period according to the present application.
Fig. 5 is a flow chart of the delay algorithm of the present application.
FIG. 6 is a flow chart of the self-learning algorithm of the present application.
Detailed Description
The invention is described in detail below with reference to the figures and the specific embodiments.
In order to research and apply a power grid monitoring intelligent algorithm, a set of power grid off-line information base based on a data collection function of an SCADA system is required to be carried, control quantity, measurement value, parameter information and various alarm signal soft message information of field operation equipment are collected, and a safety isolation gateway is arranged to ensure the network safety of power grid information and prevent virus intrusion and illegal attack. When the equipment is abnormal or fails to send out an alarm signal, the system can automatically compare and screen the signal with data in the database, and export the comparison result to a required link. The monitoring signal classification database is shown in fig. 2, and classifies signals of all plant equipment into a general signal library and a special signal label library according to voltage levels, plant names, interval names, equipment models, equipment manufacturers, special labels and other related information, and classifies the signals into types i, ii, iii, iv and v according to the signal classification basis of the power grid monitoring operation rules, and the types i, ii, iii, iv and v respectively correspond to accidents, anomalies, out-of-limits, displacement and notification items.
Referring to fig. 1-6, an intelligent automatic monitoring system for a power grid comprises a data acquisition device, an IES600 system, a data processing device containing a monitoring intelligent algorithm program, and a terminal platform; the data acquisition device, the IES600 system, the data processing device and the terminal platform are electrically connected in sequence;
the data acquisition device is arranged in the transformer substation, can completely acquire abnormal signals sent by the transformer substation due to equipment faults or abnormity, and sends the abnormal signals to the IES600 system;
the IES600 system receives the abnormal signal from the data acquisition device, delays the abnormal signal by 20s and then uploads the abnormal signal to the data processing device;
after the data processing device distinguishes and screens the abnormal signals, the data processing device carries out operation through a monitoring intelligent algorithm; the monitoring intelligent algorithm program automatically selects to delay and send the notification information to the terminal platform according to the operation result and the level of the abnormal signal, or selects to automatically send the notification information to a monitor, and the monitor performs manual intervention;
and the terminal platform receives the notification information from the data processing device, and after the operation and maintenance personnel read the notification information on the terminal platform, the operation and maintenance personnel perform treatment and feedback.
Further, the data processing device comprises a fuzzy recognition module, a delay notification module and a self-learning module.
The fuzzy recognition module is used for matching with a classification database and carrying out differentiation and screening aiming at the same-class part numbers.
Because of differences in manufacturers, models, software versions, protocols and the like of different devices, signal categories and naming specifications are different, and a signal classification library cannot strictly classify all signals. Therefore, the signal screening module needs to be equipped with a set of fuzzy recognition algorithm, and is specially used for distinguishing and screening signals of the same category in cooperation with the signal classification database, and developing a subsequent intelligent notification process.
The fuzzy recognition module adopts a fuzzy recognition algorithm, and defines the similarity Sim of the abnormal signal of the power grid as shown in formula (1):
Figure BDA0002949364340000061
in the formula, S is an abnormal signal sequence sent by a data acquisition device, and K is the total number of characters of the abnormal signal sequence; r is a signal classification database, H is the dimensionality of the database, and L is the dimensionality for storing the character number of the database signals; delta1、Δ2、Δ3The similarity weight of the number of characters, the similarity weight of the position of the character and the similarity weight of the type of the character of the sequence S and R (i) respectively, and the number, the place and the equal are similarity functions of the number, the position and the type of the character respectively;
selecting a maximum sequence R (G) of sim (i), as shown in formula (2):
Figure BDA0002949364340000062
in the formula, RchooseThe signal sequence with the highest similarity to the uploading abnormal signal of the data acquisition device in the signal classification database is provided, and G is the position number of the corresponding signal sequence in the database.
And the delay notification module automatically selects delay to send notification information according to the level of the abnormal signal.
And aiming at the situation that part of signals can be restored after a plurality of minutes, the delay module can automatically select delay to send the notification information according to the signal level.
The delay time interval of the delay informing module is set to be N sections according to a step-up mode; the delay algorithm is shown as formula (3):
Figure BDA0002949364340000071
in the formula, N is the occurrence frequency of the alarm signal; t is tiThe ith notification time; Δ tiStep delay of ith time; t is0The observation time for the first signal occurrence; t is1Is a specified first notification time; t ismaxIs the specified maximum observation time.
As shown in equation (3) and FIG. 5, when a signal appears for the first time, t is delayed first1If the signal is still maintained, the system automatically sends notification information to the terminal platform, otherwise, the notification process is automatically cancelled; second occurrence, delay t2And informing, and so on. Furthermore, tNShould be less than 30 minutes as specified by the schedule operating protocol, and N should be less than 5 times; when N is more than 5 times, the method is defined as frequent signal sending, notification information is automatically sent to a monitor, the monitor right is handed over, and manual intervention is carried out by the monitor.
The self-learning module adopts a self-learning method and records abnormal signals which do not affect the operation of the system but cannot be eliminated by conventional means; the self-learning module automatically records the situations, automatically records the frequent number in the background, and defaults not to send the notification information when the signal appears; when the abnormal signals appear along with other important signals or the total number of the sent signals in a specified time is larger than a specified value, the self-learning module identifies the abnormal signals as stubborn defects, and automatically sends notification information to the terminal platform at the moment; if the signal does not appear after the specified time, the self-learning module can determine the signal as a normal abnormal signal again.
The self-learning module adopts a self-learning algorithm, and the self-learning algorithm is shown as a formula (4):
Figure BDA0002949364340000072
wherein T is the number of days; m is the alarm in the periodSignal alarm times accumulated value; t is teMThe retention time of the Mth repeated alarm signal after the defect is eliminated; n isTThe number of alarm times of the signal is T days.
As shown in formula (4) and fig. 6, the frequent signals caused by familial defects, different equipment protocol differences and other reasons do not affect the system operation, but cannot be eliminated by related means, the signal is kept for more than 30 minutes at times, and the daily frequent number is less than 5 times. The self-learning module automatically records the above situations and automatically records the frequency number in the background, and defaults to not inform the scene when the signal appears. When the related signals appear along with other important signals or the monthly frequent transmission total number is larger than a provincial regulation specified value, the self-learning module identifies the related signals as stubborn defects, and automatically sends notification information to the terminal platform at the moment. If the signal does not appear after the month, the self-learning module can determine the signal as a conventional abnormal signal again.
A working method of an intelligent automatic monitoring system of a power grid comprises the following specific steps:
step 1, collecting and uploading abnormal signals;
the data acquisition device completely acquires abnormal signals sent by the transformer substation due to equipment faults or abnormalities and uploads the abnormal signals to the IES600 system;
step 2, delaying an abnormal signal;
the IES600 system delays the abnormal signal for 20s and then uploads the abnormal signal to the data processing device;
step 3, operation and notification of the data processing device;
after the data processing device distinguishes and screens the abnormal signals, the operation is carried out through a monitoring intelligent algorithm; then automatically selecting to delay and send the notification information to a terminal platform according to the level of the abnormal signal, or selecting to automatically send the notification information to a monitor, and performing manual intervention by the monitor;
after the monitoring intelligent algorithm program intelligently screens the abnormal signals, the monitoring intelligent algorithm program carries out operation (delay, self-learning or manual intervention), notification information is automatically sent to an operation and maintenance personnel mobile terminal APP, and the operation and maintenance personnel carry out treatment feedback according to actual conditions; automatically prompting the monitor to perform manual intervention on the information needing to be intervened by the monitor;
step 3.1, through a fuzzy recognition algorithm, matching with the established matching classification database, and carrying out differentiation and screening aiming at the same class part numbers;
step 3.2, automatically selecting delayed sending notification information according to the level of the abnormal signal;
3.3, judging the type of the abnormal signal which does not affect the system operation but cannot be eliminated by a conventional means by a self-learning method; if the abnormal signal appears along with other important signals or the total number of the sent signals in a specified time is larger than a specified value, the abnormal signal is identified as a persistent defect, and a notification message is automatically sent to the terminal platform at the moment; if the signal does not appear after the specified time, the self-learning module qualitatively determines the signal as a conventional abnormal signal again;
step 4, operation and maintenance or overhaul treatment;
and the operation and maintenance personnel go to the corresponding interval of the governed transformer substation to dispose according to the notification information on the terminal platform. Meanwhile, on the terminal platform (mobile terminal APP), the inspection, treatment processes and conclusions are filled in. The operation and maintenance personnel are responsible for the abnormity which can be treated on site, and the reason and the treatment condition of the abnormity are reported after the signal is reset; and if the operation and maintenance personnel cannot process the defect, reporting the reason to the monitoring and initiating a defect reporting process by the monitoring.
In the prior art, a person who originally monitors a post needs one positive monitoring value (mainly responsible for decision making and monitoring) and two secondary monitoring values (one for operation and recording and the other for monitoring and notification), which are totally three persons. After the intelligent automatic power grid monitoring system works, monitoring and informing work can be carried out through an algorithm program, intelligent replacement of a machine is achieved, a second-position monitoring auxiliary value does not need to be configured, personnel proportion is reduced by one third, and manpower resources are effectively saved.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (9)

1. The utility model provides a power grid intelligence automatic monitoring system which characterized in that: the intelligent monitoring system comprises a data acquisition device, an IES600 system, a data processing device containing a monitoring intelligent algorithm program and a terminal platform; the data acquisition device, the IES600 system, the data processing device and the terminal platform are electrically connected in sequence;
the data acquisition device is arranged in the transformer substation, can completely acquire abnormal signals sent by the transformer substation due to equipment faults or abnormity, and sends the abnormal signals to the IES600 system;
the IES600 system receives the abnormal signal from the data acquisition device, delays the abnormal signal by 20s and then uploads the abnormal signal to the data processing device;
after the data processing device distinguishes and screens the abnormal signals, the data processing device carries out operation through a monitoring intelligent algorithm; then automatically selecting to delay and send the notification information to a terminal platform according to the level of the abnormal signal, or selecting to automatically send the notification information to a monitor, and performing manual intervention by the monitor;
and the terminal platform receives the notification information from the data processing device, and after the operation and maintenance personnel read the notification information on the terminal platform, the operation and maintenance personnel perform treatment and feedback.
2. The intelligent automatic power grid monitoring system according to claim 1, wherein: the data processing device comprises a fuzzy recognition module and a delay notification module;
the fuzzy recognition module is used for matching with a classification database and carrying out distinguishing and screening aiming at the same class part numbers;
and the delay notification module automatically selects delay to send notification information according to the level of the abnormal signal.
3. The intelligent automatic power grid monitoring system according to claim 2, wherein: the data processing device also comprises a self-learning module;
the self-learning module adopts a self-learning method and records abnormal signals which do not affect the operation of the system but cannot be eliminated by conventional means; the self-learning module automatically records the situations, automatically records the frequent number in the background, and defaults not to send the notification information when the signal appears; when the abnormal signals appear along with other important signals or the total number of the sent signals in a specified time is larger than a specified value, the self-learning module identifies the abnormal signals as stubborn defects, and automatically sends notification information to the terminal platform at the moment; if the signal does not appear after the specified time, the self-learning module can determine the signal as a normal abnormal signal again.
4. The intelligent automatic power grid monitoring system according to claim 1, wherein: the terminal platform is a mobile terminal APP.
5. The intelligent automatic power grid monitoring system according to claim 3, wherein: the fuzzy recognition module adopts a fuzzy recognition algorithm, and defines the similarity Sim of the abnormal signal of the power grid as shown in formula (1):
S＝[s1,s2,…,sK-1,sK]
Figure FDA0002949364330000021
in the formula, S is an abnormal signal sequence sent by a data acquisition device, and K is the total number of characters of the abnormal signal sequence; r is a signal classification database, H is the dimensionality of the database, and L is the dimensionality for storing the character number of the database signals; delta1、Δ2、Δ3The similarity weight of the number of characters, the similarity weight of the position of the character and the similarity weight of the type of the character of the sequence S and R (i) respectively, and the number, the place and the equal are similarity functions of the number, the position and the type of the character respectively;
selecting a maximum sequence R (G) of sim (i), as shown in formula (2):
Figure FDA0002949364330000022
in the formula, RchooseThe signal sequence with the highest similarity to the uploading abnormal signal of the data acquisition device in the signal classification database is provided, and G is the position number of the corresponding signal sequence in the database.
6. The intelligent automatic power grid monitoring system according to claim 5, wherein: the delay time interval of the delay informing module is set to be N sections according to a step-up mode; the delay algorithm is shown as formula (3):
Figure FDA0002949364330000023
in the formula, N is the occurrence frequency of the alarm signal; t is tiThe ith notification time; Δ tiStep delay of ith time; t is0The observation time for the first signal occurrence; t is1Is a specified first notification time; t ismaxIs the specified maximum observation time.
7. The intelligent automatic power grid monitoring system according to claim 6, wherein: the self-learning module adopts a self-learning algorithm, and the self-learning algorithm is shown as a formula (4):
Figure FDA0002949364330000031
wherein T is the number of days; m is the accumulated value of the alarm times of the alarm signal in the period; t is teMThe retention time of the Mth repeated alarm signal after the defect is eliminated; n isTThe number of alarm times of the signal is T days.
8. A working method of an intelligent automatic monitoring system of a power grid is characterized in that: the intelligent automatic power grid monitoring system of claim 3 is adopted, and comprises the following specific steps:
step 1, collecting and uploading abnormal signals;
the data acquisition device completely acquires abnormal signals sent by the transformer substation due to equipment faults or abnormalities and uploads the abnormal signals to the IES600 system;
step 2, delaying an abnormal signal;
the IES600 system delays the abnormal signal for 20s and then uploads the abnormal signal to the data processing device;
step 3, operation and notification of the data processing device;
after the data processing device distinguishes and screens the abnormal signals, the operation is carried out through a monitoring intelligent algorithm; then automatically selecting to delay and send the notification information to a terminal platform according to the level of the abnormal signal, or selecting to automatically send the notification information to a monitor, and performing manual intervention by the monitor;
step 4, operation and maintenance or overhaul treatment;
and the operation and maintenance personnel go to the corresponding interval of the governed transformer substation to dispose according to the notification information on the terminal platform.
9. The working method of the intelligent automatic power grid monitoring system according to claim 8, characterized in that: the operation and notification of the data processing device in step 3 specifically include the following steps:
step 3.1, through a fuzzy recognition algorithm, matching with the established matching classification database, and carrying out differentiation and screening aiming at the same class part numbers;
step 3.2, automatically selecting delayed sending notification information according to the level of the abnormal signal;
3.3, judging the type of the abnormal signal which does not affect the system operation but cannot be eliminated by a conventional means by a self-learning method; if the abnormal signal appears along with other important signals or the total number of the sent signals in a specified time is larger than a specified value, the abnormal signal is identified as a persistent defect, and a notification message is automatically sent to the terminal platform at the moment; if the signal does not appear after the specified time, the self-learning module can determine the signal as a normal abnormal signal again.
CN202110204675.8A 2021-02-23 2021-02-23 Intelligent automatic power grid monitoring system and working method thereof Active CN113013987B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110204675.8A CN113013987B (en) 2021-02-23 2021-02-23 Intelligent automatic power grid monitoring system and working method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110204675.8A CN113013987B (en) 2021-02-23 2021-02-23 Intelligent automatic power grid monitoring system and working method thereof

Publications (2)

Publication Number Publication Date
CN113013987A true CN113013987A (en) 2021-06-22
CN113013987B CN113013987B (en) 2022-06-10

Family

ID=76408898

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110204675.8A Active CN113013987B (en) 2021-02-23 2021-02-23 Intelligent automatic power grid monitoring system and working method thereof

Country Status (1)

Country Link
CN (1) CN113013987B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107147213A (en) * 2017-04-28 2017-09-08 国家电网公司 Power network takes place frequently monitoring information intelligent alarm and comprehensive analysis administering method
CN107665309A (en) * 2016-07-27 2018-02-06 展讯通信(天津)有限公司 Security flaw detection method, device and mobile terminal based on fuzz testing
CN108736476A (en) * 2018-07-04 2018-11-02 国电南瑞科技股份有限公司 Power grid self-healing system and method based on match cognization Yu multiple agent hybrid algorithm
CN109739846A (en) * 2018-12-27 2019-05-10 国电南瑞科技股份有限公司 A kind of electric network data mass analysis method
WO2020046286A1 (en) * 2018-08-29 2020-03-05 General Electronic Company Integrated cybersecurity risk assessment and state monitoring for electrical power grid

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107665309A (en) * 2016-07-27 2018-02-06 展讯通信(天津)有限公司 Security flaw detection method, device and mobile terminal based on fuzz testing
CN107147213A (en) * 2017-04-28 2017-09-08 国家电网公司 Power network takes place frequently monitoring information intelligent alarm and comprehensive analysis administering method
CN108736476A (en) * 2018-07-04 2018-11-02 国电南瑞科技股份有限公司 Power grid self-healing system and method based on match cognization Yu multiple agent hybrid algorithm
WO2020046286A1 (en) * 2018-08-29 2020-03-05 General Electronic Company Integrated cybersecurity risk assessment and state monitoring for electrical power grid
CN109739846A (en) * 2018-12-27 2019-05-10 国电南瑞科技股份有限公司 A kind of electric network data mass analysis method

Also Published As

Publication number Publication date
CN113013987B (en) 2022-06-10

Similar Documents

Publication Publication Date Title
CN111768076B (en) Monitoring alarm signal clustering method taking power grid event as center
CN110879327B (en) 10KV line monitoring method by multi-data fusion
CN112666885A (en) Environmental protection equipment monitoring management platform based on industrial internet
CN113193549B (en) System and method for regulating and controlling transaction perception and fault co-processing
CN113409162A (en) Centralized control station equipment monitoring system and control method based on intelligent event processing
CN110349048B (en) Substation multidimensional data operation interactive control platform and fault handling method
CN111600743A (en) Intelligent operation and maintenance system based on big data
CN110751338A (en) Construction and early warning method for heavy overload characteristic model of distribution transformer area
CN115208059A (en) Transformer substation power and environment monitoring alarm processing system and method
CN113013987B (en) Intelligent automatic power grid monitoring system and working method thereof
CN113949155A (en) Panoramic power quality monitoring system with real-time monitoring function
CN117614137A (en) Power distribution network optimization system based on multi-source data fusion
CN117081249A (en) Automatic monitoring management platform for power supply line and line fault identification method
CN114692787B (en) Multi-source data-based three-winding main transformer event analysis processing method and system
CN116468243A (en) Power grid trend early warning method based on monitoring operation data
CN115313662A (en) Distribution automation intelligence auxiliary tool that patrols and examines
CN104979903A (en) Patrol analysis method and device for centralized control center
CN114336979A (en) Power grid accident trip information classification extraction and auxiliary decision method
CN115034943A (en) Intelligent municipal service platform based on AI control
CN114398947A (en) Expert system-based power grid fault automatic classification method and system
CN111245097A (en) Intelligent power grid management and control system and method
CN110706434A (en) Man-machine interactive power transmission line fault monitoring and early warning system
CN109889400A (en) A kind of Enterprise Service Bus trouble analysis system and operation method
CN109450085B (en) Equipment abnormity alarm signal processing system based on scheduling and control integration
CN114844017B (en) Method for shortening average emergency response time of tripping accident of distribution network line

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