CN116523506A - Circuit fault prediction analysis system based on digital twin transformer station technology - Google Patents
Circuit fault prediction analysis system based on digital twin transformer station technology Download PDFInfo
- Publication number
- CN116523506A CN116523506A CN202310557765.4A CN202310557765A CN116523506A CN 116523506 A CN116523506 A CN 116523506A CN 202310557765 A CN202310557765 A CN 202310557765A CN 116523506 A CN116523506 A CN 116523506A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- acquisition
- equipment
- circuit fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 55
- 238000005516 engineering process Methods 0.000 title claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 43
- 230000002159 abnormal effect Effects 0.000 claims abstract description 41
- 238000012423 maintenance Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims description 22
- 230000004044 response Effects 0.000 claims description 21
- 238000004088 simulation Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 230000003044 adaptive effect Effects 0.000 claims description 9
- 238000003032 molecular docking Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000005284 excitation Effects 0.000 claims description 3
- 230000004907 flux Effects 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000002452 interceptive effect Effects 0.000 description 14
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- 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
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention relates to the field of digital twinning, and discloses a circuit fault prediction analysis system based on a digital twinning transformer station technology; the system matches and searches the abnormal data in the database, when the historical processing data of the same category exists, the abnormal data is used as reference data and submitted to the model building unit, the model building unit is helped to analyze and predict fault threats, and the processing scheme is synchronously output, so that a user is helped to quickly know the threat caused by the abnormal data, and the processing scheme is issued in time, so that the circuit fault is solved, the transformer substation is helped to reduce fault loss in time, and the maintenance pressure is relieved.
Description
Technical Field
The invention relates to the technical field of digital twinning, in particular to a circuit fault prediction analysis system based on a digital twinning transformer station technology.
Background
The stable operation of the transformer equipment in the transformer substation is related to the safety of a backbone network and a power distribution network of the whole power grid, so as to realize the perception and control of the state of the transformer equipment, the operation and maintenance inspection of the transformer substation equipment is always one of the key work contents of the power grid, circuit faults are one of the more common faults for the transformer substation, the operation state of the analysis equipment is measured and the defect of the positioning equipment is abnormal in the normal operation work of the transformer substation by utilizing a related detection instrument, wherein the operation and maintenance work is developed from the early manual inspection to the joint operation and maintenance of intelligent equipment such as a high-definition camera, a sensor, a robot and the like;
however, existing circuit fault prediction analysis systems for substations have drawbacks such as:
1. in the prior art, the fault is predicted by a digital twin technology, and the acquisition direction of abnormal data is limited, so that the analysis result is less comprehensive, and when a large number of repeated problems occur, the self-adaptive control of the adjusting equipment and the manual scheduling is difficult to carry out according to the history processing experience, so that the fault is not timely eliminated;
2. early warning measures are difficult to develop in time, the processing modes which can be automatically adjusted and manually adjusted are lack of rapid distinguishing processing, loss caused by faults cannot be restrained in time, and in the subsequent acquisition and monitoring process, equipment with problems is difficult to automatically monitor in an important mode.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects existing in the prior art, the invention provides a circuit fault prediction analysis system based on a digital twin transformer station technology, which can effectively solve the problems in the prior art.
(II) technical scheme
In order to achieve the above object, the present invention is realized by the following technical scheme,
the invention discloses a circuit fault prediction analysis system based on a digital twin transformer station technology, which comprises the following steps:
the main control end is used for controlling the global functional module and the unit in a total way, linking the network of the internet of things, editing and sending control instructions and controlling access rights;
the acquisition unit is used for acquiring each item of monitoring data and converting the monitoring data into a machine-readable language;
the acquisition unit comprises an equipment acquisition module and an environment acquisition module, wherein:
and the equipment acquisition module is used for: the method comprises the steps of being deployed on a site of a specified device to be monitored, feeding back a control state, and reporting operation parameters according to a preset period;
the environment acquisition module is used for: the method comprises the steps of interfacing with the Internet, and submitting weather data and power fluctuation data of an associated area of a current transformer substation area through a preset period;
the storage end is used for constructing a database, storing acquired acquisition data and analysis data, and synchronously backing up the acquired acquisition data and analysis data to the cloud end to support the reading of a local storage medium;
the identification matching module is used for receiving the acquired data submitted by the acquisition unit, and uploading the abnormal data in real time after identification analysis;
the model construction unit is used for constructing a simulation prediction model, running after receiving historical data and real-time abnormal data, carrying out overall analysis, completing operation and maintenance decision, outputting prediction data, and pointing to associated fault equipment to obtain future fluctuation parameters;
the relay analysis module is used for analyzing according to the prediction data, acquiring adjustment parameters of the associated adjustment equipment, planning an adjustment mode and distinguishing a remote automatic adjustment instruction and a manual adjustment instruction;
the remote response module is used for receiving the remote automatic adjustment instruction submitted by the relay analysis module, and opening the control authority of the associated adjustment equipment until the associated adjustment equipment responds;
the data feedback module is used for acquiring the running state data of the adjusting equipment of the remote response module and carrying out real-time feedback;
the early warning processing unit is used for acquiring abnormal data, judging the emergency degree after analysis, acquiring manual adjustment instructions and issuing associated manual scheduling instructions in real time.
Still further, the target device acquired by the device acquisition module includes: converter transformer equipment, camera adjusting equipment and GIS equipment, acquisition parameters of the converter transformer equipment, the camera adjusting equipment and the GIS equipment are respectively as follows:
converter transformer equipment: pressure, oil flow speed and core grounding current;
camera adjusting device: vibration signals, magnetic flux signals, three-phase stator voltages, current signals, excitation voltages, current signals, high-frequency current signals, ultrahigh-frequency signals and temperature signals;
GIS equipment: mechanical state, gas state and temperature index;
the method comprises the steps of acquiring video images acquired in the process, intercepting the images at intervals of frames, searching the positions corresponding to key data from the images through a preprocessing algorithm, positioning, intercepting the key data, removing the rest data, performing binarization processing on the key data, performing image segmentation to obtain single data images, and adjusting the sizes of the digital images through two-dimensional linear interpolation.
Furthermore, the environment acquisition module acquires regional weather data in the current acquisition period, focuses on severe and abnormal weather, and receives voltage fluctuation parameters in a power supply network;
the acquisition process comprises the following steps:
a. acquiring a control instruction, and judging whether registration is performed to acquire data acquisition object information to be acquired;
b. judging whether a parameter is contained in the asynchronous loading process of the data object request access;
c. if the web address of the asynchronously loaded data acquisition object contains parameters, and the target information is accessed under the condition that registration and login are not needed, namely, a dynamic data acquisition mode is selected to be generated according to the data acquisition object request, otherwise, a WebDriver data acquisition mode is adopted;
d. and checking the acquisition result, judging whether the acquired data is complete, continuously acquiring according to preset settings if the acquired data is complete, and restarting acquisition if the acquired data is not complete.
Further, the preset period of the equipment acquisition module and the environment acquisition module is edited by manual definition and remote control of a program.
Further, when the identification matching module identifies the abnormal data, the collecting unit synchronously uploads the operation and maintenance data of the associated equipment, including: real-time working condition state of equipment, maintenance record of equipment and layout position of equipment.
Still further, the operation logic of the identification matching module includes the steps of:
step 1: acquiring data, and judging whether the data exceeds a preset standard threshold value or not;
step 2: judging that the operation is not performed, and continuously operating according to preset settings;
step 3: judging whether the abnormal data exist or not by analyzing and judging whether the abnormal data exist the association history record;
step 4: if the data exists, matching in a database, directly butting after hit, and sending the abnormal data and the similar historical processing data to a simulation prediction model;
and step 5, if the abnormal data does not exist, generating a new record in the database, receiving the problem data, and sending the abnormal data to the simulation prediction model.
Furthermore, the model building unit is interactively connected with a docking module through a wireless network, the docking module is used for acquiring the data writing permission of the model building unit, after triggering, manually edited equipment parameters and environment parameters are provided as training samples of a simulation prediction model, and the calculation formula of the classification capacity index of the model building unit is as follows:
wherein: w represents a classification ability index; n represents the sampling times; a, a j Representing individual features in a feature set; x is x i Representing a single sample in a sample set; n (N) h Represents and x i Nearest neighbors of the same class; n (N) m Represents and x i Nearest neighbors of non-congruent categories.
Furthermore, the data feedback module is connected with the self-adaptive planning module through electric signal communication, the self-adaptive planning module is connected with the acquisition unit through electric signal communication, and the self-adaptive planning module is used for marking related fault equipment according to the operation state data of the adjusting equipment fed back by the data feedback module, and up-regulating the priority and the frequency of acquisition monitoring.
Still further, the early warning processing unit includes hierarchical module, sending module and dispatch module, wherein:
and a grading module: for the received data, determining the emergency degree of the dangerous case;
and a sending module: the method comprises the steps of editing corresponding manual scheduling instructions according to judgment data of a grading module;
and a scheduling module: and the manual scheduling instruction issuing module is used for issuing manual scheduling instructions according to the communication network.
Furthermore, the main control end is in interactive connection with the acquisition unit, the storage end and the early warning processing unit through a wireless network, the acquisition unit is in communication connection with the identification matching module through an electric signal, the identification matching module is in interactive connection with the storage end through the wireless network, the identification matching module is in interactive connection with the model building unit through the wireless network, the model building unit is in interactive connection with the relay analysis module through the wireless network, the relay analysis module is in interactive connection with the remote response module through the wireless network, the remote response module is in interactive connection with the data feedback module through the wireless network, and the early warning processing unit is in interactive connection with the relay analysis module and the data feedback module through the wireless network.
(III) beneficial effects
Compared with the prior art, the technical proposal provided by the invention has the following beneficial effects,
1. through being provided with discernment matching module, through comprehensive acquisition equipment data, weather data and electric wire netting fluctuation data, carry out the investigation of unusually, when the abnormal data appears, match the searching with unusual data in the database, when there is historical processing data of same type, submit it to model building unit as reference data, help model building unit analysis forecast trouble threat, and synchronous output processing scheme, and then help the user to know the threat that abnormal data brought fast, and carry out the time of processing scheme and issue, in order to accelerate the solution of circuit trouble, help fortune dimension maintenance department develop work.
2. The remote control of the remote response module through the relay analysis module enables the part of the problem to be solved through the adjustment of the equipment parameters in the resolution measure when the fault occurs, and the part to be processed manually is directly adjusted through the remote response module in a remote control mode, then the fault loss is timely reduced through the dispatching of the early warning processing unit, the maintenance pressure is reduced, and if the remote response module is not adjusted in place, the data feedback module can also feed back the data to the early warning processing unit, and the manual adjustment is performed again.
3. The self-adaptive planning module is arranged, the self-adaptive planning module receives the adjustment data fed back by the data feedback module, and the equipment fault rate is obtained while the data is backed up to the storage end, so that the priority and the frequency of the acquisition monitoring of the fault equipment are improved.
4. The model building unit is trained by the docking module, so that various abnormal data are provided manually as training samples for the model building unit to simulate various faults and emergency situations, so that operators can be trained and exercised, and the operators can be helped to make correct decisions and take necessary measures.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is evident that the drawings in the following description are only some embodiments of the present invention and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a schematic diagram of a circuit fault prediction analysis system based on a digital twin substation technology in the invention;
FIG. 2 is a flow chart of the operation logic of the identification matching module in the present invention;
FIG. 3 is a schematic flow chart of the acquisition process of the environmental acquisition module in the present invention;
FIG. 4 is an architectural illustration of the present invention;
reference numerals in the figure respectively represent 100 and a main control end; 200. an acquisition unit; 210. an equipment acquisition module; 211. an environment collection module; 300. a storage end; 400. identifying a matching module; 500. a model construction unit; 600. a relay analysis module; 700. a remote response module; 800. a data feedback module; 900. an early warning processing unit; 910. a grading module; 911. a transmitting module; 912. a scheduling module; 1000. an adaptive planning module; 1100. and (5) a docking module.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention is further described below with reference to examples.
Example 1
The circuit fault prediction analysis system based on the digital twin substation technology of the embodiment, as shown in fig. 1 to 4, includes:
the main control end 100 is used for controlling the global functional module and the unit in a total way, linking the network of the internet of things, editing and sending a control instruction, and controlling the access right;
the acquisition unit 200 is used for acquiring each item of monitoring data and converting the monitoring data into a machine-readable language;
the acquisition unit 200 comprises a device acquisition module 210 and an environment acquisition module 211, wherein:
the device acquisition module 210: the method comprises the steps of being deployed on a site of a specified device to be monitored, feeding back a control state, and reporting operation parameters according to a preset period;
the environment acquisition module 211: the method comprises the steps of interfacing with the Internet, and submitting weather data and power fluctuation data of an associated area of a current transformer substation area through a preset period;
the storage end 300 is used for constructing a database, storing acquired acquisition data and analysis data, and synchronously backing up the acquired acquisition data and analysis data to the cloud end to support the reading of a local storage medium;
the recognition matching module 400 is configured to receive the collected data submitted by the collection unit 200, perform recognition analysis, and upload abnormal data in real time;
the model construction unit 500 is used for constructing a simulation prediction model, running after receiving historical data and real-time abnormal data, performing overall analysis, completing operation and maintenance decision, outputting prediction data, and pointing to associated fault equipment to obtain future fluctuation parameters thereof;
the relay analysis module 600 is configured to analyze according to the prediction data, obtain an adjustment parameter of the associated adjustment device, and plan an adjustment mode, and distinguish a remote automatic adjustment instruction from a manual adjustment instruction;
the remote response module 700 is configured to receive the remote automatic adjustment instruction submitted by the relay analysis module 600, and open the control authority of the association adjustment device until the association adjustment device responds;
the data feedback module 800 is configured to obtain operation state data of the adjusting device of the remote response module 700, and perform real-time feedback;
the early warning processing unit 900 is configured to obtain abnormal data, analyze the abnormal data, determine an emergency degree, obtain a manual adjustment instruction, and issue an associated manual scheduling instruction in real time.
The target devices acquired by the device acquisition module 210 include: converter transformer equipment, camera adjusting equipment and GIS equipment, acquisition parameters of the converter transformer equipment, the camera adjusting equipment and the GIS equipment are respectively as follows:
converter transformer equipment: pressure, oil flow speed and core grounding current;
camera adjusting device: vibration signals, magnetic flux signals, three-phase stator voltages, current signals, excitation voltages, current signals, high-frequency current signals, ultrahigh-frequency signals and temperature signals;
GIS equipment: mechanical state, gas state and temperature index;
the method comprises the steps of acquiring video images acquired in the process, intercepting the images at intervals of frames, searching the positions corresponding to key data from the images through a preprocessing algorithm, positioning, intercepting the key data, removing the rest data, performing binarization processing on the key data, performing image segmentation to obtain single data images, and adjusting the sizes of the digital images through two-dimensional linear interpolation.
The environment acquisition module 211 acquires regional weather data in the current acquisition period, focuses on severe and abnormal weather, and receives voltage fluctuation parameters in a power supply network;
the acquisition process comprises the following steps:
a. acquiring a control instruction, and judging whether registration is performed to acquire data acquisition object information to be acquired;
b. judging whether a parameter is contained in the asynchronous loading process of the data object request access;
c. if the web address of the asynchronously loaded data acquisition object contains parameters, and the target information is accessed under the condition that registration and login are not needed, namely, a dynamic data acquisition mode is selected to be generated according to the data acquisition object request, otherwise, a WebDriver data acquisition mode is adopted;
d. and checking the acquisition result, judging whether the acquired data is complete, continuously acquiring according to preset settings if the acquired data is complete, and restarting acquisition if the acquired data is not complete.
The preset period of the device acquisition module 210 and the environment acquisition module 211 is edited by manual definition and remote control of a program.
When the recognition matching module 400 recognizes the abnormal data, the collection unit 200 synchronously uploads the operation and maintenance data of the associated device, including: real-time working condition state of equipment, maintenance record of equipment and layout position of equipment.
The operational logic of the identify matching module 400 includes the steps of:
step 1: acquiring data, and judging whether the data exceeds a preset standard threshold value or not;
step 2: judging that the operation is not performed, and continuously operating according to preset settings;
step 3: judging whether the abnormal data exist or not by analyzing and judging whether the abnormal data exist the association history record;
step 4: if the data exists, matching in a database, directly butting after hit, and sending the abnormal data and the similar historical processing data to a simulation prediction model;
and step 5, if the abnormal data does not exist, generating a new record in the database, receiving the problem data, and sending the abnormal data to the simulation prediction model.
The data feedback module 800 is connected with the adaptive planning module 1000 through electrical signal communication, the adaptive planning module 1000 is connected with the acquisition unit 200 through electrical signal communication, and the adaptive planning module 1000 is used for marking related fault equipment according to the operation state data of the adjusting equipment fed back by the data feedback module 800, and up-regulating the priority and frequency of acquisition monitoring.
The early warning processing unit 900 includes a ranking module 910, a sending module 911, and a scheduling module 912, wherein:
the classification module 910: for the received data, determining the emergency degree of the dangerous case;
the transmission module 911: for editing corresponding manual scheduling instructions for the judgment data of the classification module 910;
scheduling module 912: and the manual scheduling instruction issuing module is used for issuing manual scheduling instructions according to the communication network.
The main control end 100 is in interactive connection with the acquisition unit 200, the storage end 300 and the early warning processing unit 900 through a wireless network, the acquisition unit 200 is in communication connection with the identification matching module 400 through an electric signal, the identification matching module 400 is in interactive connection with the storage end 300 through a wireless network, the identification matching module 400 is in interactive connection with the model building unit 500 through a wireless network, the model building unit 500 is in interactive connection with the relay analysis module 600 through a wireless network, the relay analysis module 600 is in interactive connection with the remote response module 700 through a wireless network, the remote response module 700 is in interactive connection with the data feedback module 800 through a wireless network, and the early warning processing unit 900 is in interactive connection with the relay analysis module 600 and the data feedback module 800 through a wireless network.
Example 2
In this embodiment, the model building unit 500 is interactively connected with a docking module 1100 through a wireless network, the docking module 1100 is used for obtaining the data writing authority of the model building unit 500, after triggering, providing manually edited device parameters and environment parameters, and taking the manually edited device parameters and environment parameters as training samples of a simulation prediction model, and the calculation formula of the classification capability index of the model building unit 500 is as follows:
wherein: w represents a classification ability index; n represents the sampling times; a, a j Representing individual features in a feature set; x is x i Representing a single sample in a sample set; n (N) h Represents and x i Nearest neighbors of the same class; n (N) m Represents and x i Nearest neighbors of non-congruent categories.
In summary, when the system is installed, the main control end 100 is used for overall control, the storage end 300 is used as a data storage end, the acquisition unit 200 is used for acquiring various items of data, the equipment acquisition module 210 is used for acquiring equipment data, the environment acquisition module 211 is used for acquiring the environment data, the recognition matching module 400 is used for judging whether abnormal data exist, the storage end 300 is matched with related historical data, the data are sent to the model construction unit 500 for simulation prediction, fault data and corresponding processing measures are analyzed, the relay analysis module 600 is used for distinguishing the processing measures, the remote response module 700 is used for remote control, the measures requiring manual processing are received by the early warning processing unit 900, the grading module 910 is used for grading the dangerous situations of the fault data, the sending module 912 is used for scheduling manual work, when the remote response module 700 does not respond timely or fails, the data feedback module 800 is used for synchronously feeding back the data to the adaptive planning module 1000 and the early warning processing unit 900, the acquisition priority and the frequency of the fault equipment are adjusted by the adaptive planning module 1000, the early warning processing unit 900 is used for manually scheduling and adjusting the equipment incapable of being adjusted, and all the processing data are sent to the storage end 300 by the early warning processing unit 900 for manual scheduling adjustment;
by arranging the identification matching module 400, performing exception investigation by comprehensively acquiring equipment data, weather data and power grid fluctuation data, matching and searching the exception data in a database when the exception data occurs, submitting the exception data serving as reference data to the model building unit 500 when the history processing data of the same type exists, helping the model building unit 500 to analyze and predict fault threats, synchronously outputting a processing scheme, further helping a user to quickly know the threats caused by the exception data, and performing the timely issuing of the processing scheme so as to accelerate the solution of circuit faults and help an operation and maintenance department to develop work;
the remote control of the remote response module 700 by the relay analysis module 600 enables the part of the problem to be solved by adjusting the equipment parameters in the solution measures to be resolved, and the remote control adjustment is directly performed by the remote response module 700, and the part to be processed manually is scheduled by the early warning processing unit 900, so that the transformer substation can be helped to reduce the fault loss in time, the maintenance pressure is relieved, and if the remote response module 700 is not properly adjusted, the data can be fed back to the early warning processing unit 900 by the data feedback module 800 to be manually adjusted again, the adjustment data fed back by the data feedback module 800 is received by the self-adaptive planning module 1000, the equipment fault rate is obtained while the data is backed up to the storage end 300, the priority and the frequency of the acquisition monitoring of the fault equipment are improved, the model building unit 500 is trained by the docking module 1100, and various abnormal data are provided manually as training samples, so that the model building unit 500 simulates various faults and emergency situations for operators to train and help to guide operators to make correct decisions and take necessary measures.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; while the invention has been described in detail with reference to the foregoing embodiments, it will be appreciated by those skilled in the art that variations may be made in the techniques described in the foregoing embodiments, or equivalents may be substituted for elements thereof; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. Circuit fault prediction analysis system based on digital twin transformer station technology, which is characterized by comprising:
the main control end (100) is used for controlling the global functional module and the unit in a total way, linking the network of the internet of things, editing and sending a control instruction, and controlling the access right;
the acquisition unit (200) is used for acquiring various monitoring data and converting the monitoring data into a machine-readable language;
the acquisition unit (200) comprises a device acquisition module (210) and an environment acquisition module (211), wherein:
device acquisition module (210): the method comprises the steps of being deployed on a site of a specified device to be monitored, feeding back a control state, and reporting operation parameters according to a preset period;
environment acquisition module (211): the method comprises the steps of interfacing with the Internet, and submitting weather data and power fluctuation data of an associated area of a current transformer substation area through a preset period;
the storage end (300) is used for constructing a database, storing acquired acquisition data and analysis data, and synchronously backing up the acquired acquisition data and analysis data to the cloud end to support the reading of a local storage medium;
the identification matching module (400) is used for receiving the acquired data submitted by the acquisition unit (200), and uploading the abnormal data in real time after identification analysis;
the model construction unit (500) is used for constructing a simulation prediction model, running after receiving historical data and real-time abnormal data, carrying out overall analysis, completing operation and maintenance decision, outputting prediction data, and pointing to associated fault equipment to carry out future fluctuation parameters;
the relay analysis module (600) is used for analyzing according to the prediction data, acquiring the adjustment parameters of the associated adjustment equipment, planning an adjustment mode and distinguishing a remote automatic adjustment instruction and a manual adjustment instruction;
the remote response module (700) is used for receiving the remote automatic adjustment instruction submitted by the relay analysis module (600) and opening the control authority of the associated adjustment equipment until the associated adjustment equipment responds;
the data feedback module (800) is used for acquiring the operation state data of the adjusting equipment of the remote response module (700) and carrying out real-time feedback;
and the early warning processing unit (900) is used for acquiring the abnormal data, judging the emergency degree after analysis, acquiring the manual adjustment instruction and issuing the associated manual scheduling instruction in real time.
2. The digital twin substation technology based circuit fault prediction analysis system according to claim 1, wherein the target device acquired by the device acquisition module (210) comprises: converter transformer equipment, camera adjusting equipment and GIS equipment, acquisition parameters of the converter transformer equipment, the camera adjusting equipment and the GIS equipment are respectively as follows:
converter transformer equipment: pressure, oil flow speed and core grounding current;
camera adjusting device: vibration signals, magnetic flux signals, three-phase stator voltages, current signals, excitation voltages, current signals, high-frequency current signals, ultrahigh-frequency signals and temperature signals;
GIS equipment: mechanical state, gas state and temperature index;
the method comprises the steps of acquiring video images acquired in the process, intercepting the images at intervals of frames, searching the positions corresponding to key data from the images through a preprocessing algorithm, positioning, intercepting the key data, removing the rest data, performing binarization processing on the key data, performing image segmentation to obtain single data images, and adjusting the sizes of the digital images through two-dimensional linear interpolation.
3. The digital twin substation technology based circuit fault prediction analysis system according to claim 1, wherein the environment acquisition module (211) acquires regional weather data in a current acquisition period, focuses on severe and abnormal weather, and receives voltage fluctuation parameters in a power supply network;
the acquisition process comprises the following steps:
a. acquiring a control instruction, and judging whether registration is performed to acquire data acquisition object information to be acquired;
b. judging whether a parameter is contained in the asynchronous loading process of the data object request access;
c. if the web address of the asynchronously loaded data acquisition object contains parameters, and the target information is accessed under the condition that registration and login are not needed, namely, a dynamic data acquisition mode is selected to be generated according to the data acquisition object request, otherwise, a WebDriver data acquisition mode is adopted;
d. and checking the acquisition result, judging whether the acquired data is complete, continuously acquiring according to preset settings if the acquired data is complete, and restarting acquisition if the acquired data is not complete.
4. The digital twin substation technology based circuit fault prediction analysis system according to claim 1, wherein the preset period of the equipment collection module (210) and the environment collection module (211) is edited by manual definition and remote control of a program.
5. The digital twin substation technology based circuit fault prediction analysis system according to claim 1, wherein when the identification matching module (400) identifies abnormal data, the collection unit (200) synchronously uploads the operation and maintenance data of the associated device, including: real-time working condition state of equipment, maintenance record of equipment and layout position of equipment.
6. The digital twin substation technology based circuit fault prediction analysis system according to claim 1, wherein the operational logic of the identification matching module (400) comprises the steps of:
step 1: acquiring data, and judging whether the data exceeds a preset standard threshold value or not;
step 2: judging that the operation is not performed, and continuously operating according to preset settings;
step 3: judging whether the abnormal data exist or not by analyzing and judging whether the abnormal data exist the association history record;
step 4: if the data exists, matching in a database, directly butting after hit, and sending the abnormal data and the similar historical processing data to a simulation prediction model;
and step 5, if the abnormal data does not exist, generating a new record in the database, receiving the problem data, and sending the abnormal data to the simulation prediction model.
7. The digital twin substation technology based circuit fault prediction analysis system according to claim 1, wherein the model building unit (500) is interactively connected with a docking module (1100) through a wireless network, the docking module (1100) is used for obtaining data writing permission of the model building unit (500), after triggering, manually edited equipment parameters and environment parameters are provided as training samples of a simulation prediction model, and a calculation formula of a classification capability index of the model building unit (500) is as follows:
wherein: w represents a classification ability index; n represents the sampling times; a, a j Representing individual features in a feature set; x is x i Representing a single sample in a sample set; n (N) h Represents and x i Nearest neighbors of the same class; n (N) m Represents and x i Nearest neighbors of non-congruent categories.
8. The circuit fault prediction analysis system based on the digital twin substation technology according to claim 1, wherein the data feedback module (800) is connected with the adaptive planning module (1000) through electric signal communication, the adaptive planning module (1000) is connected with the acquisition unit (200) through electric signal communication, and the adaptive planning module (1000) is used for marking related fault equipment according to the operation state data of the adjusting equipment fed back by the data feedback module (800) and up-regulating the priority and frequency of acquisition monitoring.
9. The digital twin substation technology based circuit fault prediction analysis system according to claim 1, wherein the pre-alarm processing unit (900) comprises a classification module (910), a transmission module (911) and a scheduling module (912), wherein:
classification module (910): for the received data, determining the emergency degree of the dangerous case;
transmission module (911): the method comprises the steps of editing corresponding manual scheduling instructions according to judgment data of a grading module (910);
scheduling module (912): and the manual scheduling instruction issuing module is used for issuing manual scheduling instructions according to the communication network.
10. The digital twin substation technology circuit fault prediction analysis system according to claim 1, wherein the master control end (100) is interactively connected with the acquisition unit (200), the storage end (300) and the early warning processing unit (900) through a wireless network, the acquisition unit (200) is interactively connected with the identification matching module (400) through an electric signal communication, the identification matching module (400) is interactively connected with the storage end (300) through a wireless network, the identification matching module (400) is interactively connected with the model construction unit (500) through a wireless network, the model construction unit (500) is interactively connected with the relay analysis module (600) through a wireless network, the relay analysis module (600) is interactively connected with the remote response module (700) through a wireless network, the remote response module (700) is interactively connected with the data feedback module (800) through a wireless network, and the early warning processing unit (900) is interactively connected with the relay analysis module (600) and the data feedback module (800) through a wireless network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310557765.4A CN116523506A (en) | 2023-05-17 | 2023-05-17 | Circuit fault prediction analysis system based on digital twin transformer station technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310557765.4A CN116523506A (en) | 2023-05-17 | 2023-05-17 | Circuit fault prediction analysis system based on digital twin transformer station technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116523506A true CN116523506A (en) | 2023-08-01 |
Family
ID=87399329
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310557765.4A Pending CN116523506A (en) | 2023-05-17 | 2023-05-17 | Circuit fault prediction analysis system based on digital twin transformer station technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116523506A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117332359A (en) * | 2023-12-01 | 2024-01-02 | 国网江苏省电力有限公司南通供电分公司 | Power data transmission abnormality detection method and system |
| CN117520787A (en) * | 2024-01-04 | 2024-02-06 | 四川省公路规划勘察设计研究院有限公司 | Digital twinning-based expressway intelligent data fault analysis method and system |
| CN117590149A (en) * | 2023-11-14 | 2024-02-23 | 南方电网调峰调频发电有限公司检修试验分公司 | Fault solution generation method, device and equipment based on big data technology |
| CN117691543A (en) * | 2024-02-04 | 2024-03-12 | 国网安徽省电力有限公司电力科学研究院 | Active single-phase ground fault alarm feedback method and device |
| CN117691543B (en) * | 2024-02-04 | 2024-04-19 | 国网安徽省电力有限公司电力科学研究院 | Active single-phase ground fault alarm feedback method and device |
-
2023
- 2023-05-17 CN CN202310557765.4A patent/CN116523506A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117590149A (en) * | 2023-11-14 | 2024-02-23 | 南方电网调峰调频发电有限公司检修试验分公司 | Fault solution generation method, device and equipment based on big data technology |
| CN117332359A (en) * | 2023-12-01 | 2024-01-02 | 国网江苏省电力有限公司南通供电分公司 | Power data transmission abnormality detection method and system |
| CN117332359B (en) * | 2023-12-01 | 2024-02-09 | 国网江苏省电力有限公司南通供电分公司 | Power data transmission abnormality detection method and system |
| CN117520787A (en) * | 2024-01-04 | 2024-02-06 | 四川省公路规划勘察设计研究院有限公司 | Digital twinning-based expressway intelligent data fault analysis method and system |
| CN117520787B (en) * | 2024-01-04 | 2024-03-19 | 四川省公路规划勘察设计研究院有限公司 | Digital twinning-based expressway intelligent data fault analysis method and system |
| CN117691543A (en) * | 2024-02-04 | 2024-03-12 | 国网安徽省电力有限公司电力科学研究院 | Active single-phase ground fault alarm feedback method and device |
| CN117691543B (en) * | 2024-02-04 | 2024-04-19 | 国网安徽省电力有限公司电力科学研究院 | Active single-phase ground fault alarm feedback method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116523506A (en) | Circuit fault prediction analysis system based on digital twin transformer station technology | |
| CN106710001B (en) | Centralized monitoring simulation system and method based on transformer substation inspection robot | |
| CN113472079B (en) | Power distribution station operation and maintenance monitoring cloud robot system, background processing and operation task method | |
| CN107908175A (en) | A kind of electric system site intelligent operational system | |
| CN111444169A (en) | Transformer substation electrical equipment state monitoring and diagnosis system and method | |
| CN116224925B (en) | Intelligent processing management system | |
| CN111160432A (en) | Automatic classification method and system for panel production defects | |
| CN115423009A (en) | Cloud edge coordination-oriented power equipment fault identification method and system | |
| CN115395646B (en) | Intelligent operation and maintenance system of digital twin traction substation | |
| CN112614130A (en) | Unmanned aerial vehicle power transmission line insulator fault detection method based on 5G transmission and YOLOv3 | |
| CN111045364B (en) | Power environment monitoring system decision-making assisting method based on big data platform | |
| CN117218495A (en) | Risk detection method and system for electric meter box | |
| CN115035328A (en) | Converter image increment automatic machine learning system and establishment training method thereof | |
| CN115297302B (en) | Unmanned system of railway substation | |
| CN115664006B (en) | Intelligent management and control integrated platform for incremental power distribution network | |
| CN115689206A (en) | Intelligent monitoring method for transformer substation infrastructure progress based on deep learning | |
| CN115296193A (en) | Intelligent inspection system and method for transformer substation | |
| Zhao et al. | Working Condition Monitoring System of Substation Robot Based on Video Monitoring | |
| CN116169778A (en) | Processing method and system based on power distribution network anomaly analysis | |
| EP4016408A1 (en) | Maintenance assistance system and maintenance assistance method | |
| CN114912678A (en) | Online automatic detection and early warning method and system for abnormal operation of power grid regulation and control | |
| CN112926401A (en) | Transmission line hardware corrosion detection method and system | |
| EP3706268B1 (en) | Artificial intelligence monitoring system using infrared images to identify hotspots in a switchgear | |
| Yuli et al. | Research and trial application of mobile sensing and interactive diagnostic technology for power cable lines | |
| CN117648659B (en) | Low-voltage distribution transformer energy-saving measurement system and measurement method thereof |
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 |