CN115269928A - Transformer fault prediction method, device, equipment and medium based on digital twinning - Google Patents
Transformer fault prediction method, device, equipment and medium based on digital twinning Download PDFInfo
- Publication number
- CN115269928A CN115269928A CN202210861469.9A CN202210861469A CN115269928A CN 115269928 A CN115269928 A CN 115269928A CN 202210861469 A CN202210861469 A CN 202210861469A CN 115269928 A CN115269928 A CN 115269928A
- Authority
- CN
- China
- Prior art keywords
- transformer
- fault
- digital twin
- fault prediction
- probability
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
- G01R31/1263—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation
- G01R31/1281—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials of solid or fluid materials, e.g. insulation films, bulk material; of semiconductors or LV electronic components or parts; of cable, line or wire insulation of liquids or gases
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/20—Identification of molecular entities, parts thereof or of chemical compositions
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Crystallography & Structural Chemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Spectroscopy & Molecular Physics (AREA)
- General Engineering & Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a transformer fault prediction method, a device, equipment and a medium based on digital twins, wherein the transformer fault prediction method based on the digital twins comprises the following steps: extracting simulated operation characteristics of the transformer based on simulated data of a digital twin model of the transformer; performing fault prediction on the transformer according to the simulated operation characteristics and a preset transformer fault prediction model to generate a fault prediction result; and outputting the fault prediction result through the digital twin model. The method has stronger timeliness for predicting the fault of the transformer based on the simulated data, and simultaneously judges the possible fault of the transformer in all directions through the transformer fault prediction model, the prediction data and the historical data, so that the judgment standard is more flexible, and the more the number of samples in the historical data is, the more accurate the prediction result is, thereby enhancing the operation and maintenance monitoring capability of the transformer and improving the stability of the power system.
Description
Technical Field
The invention belongs to the technical field of state evaluation of transformers, and particularly relates to a transformer fault prediction method, device, equipment and medium based on digital twinning.
Background
The power system is an organic whole and basically consists of power generation, power transmission and power distribution. The transformers are numerous and play an important role in the power transmission end and the power distribution section, once the transformers break down, normal operation of a power grid system is affected, inconvenience is brought to life of people, and safety accidents are caused when the transformers are serious. At present, the common technical means for transformer fault diagnosis comprise a characteristic gas method and a three-ratio method, and the main principle of the method is that 5 characteristic gases (H) generated in transformer oil are used as the basis2、CH4、C2H6、C2H4、C2H2) In a content of C2H2/C2H4、CH4/H2And C2H4/C2H6And determining the corresponding fault type of the transformer in a pre-programmed fault table according to the ratio of each characteristic gas. However, the working principle of the transformer is complex, and the internal connection structures can affect each other, so that the fault diagnosis standard is too absolute. And the diagnosis method is based on the condition that the fault occursThere is also a certain hysteresis in the diagnostic result.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the transformer fault prediction method, the transformer fault prediction device, the transformer fault prediction equipment and the transformer fault prediction medium based on the digital twin are provided to solve the technical problems that the diagnosis of the existing transformer is too absolute and the diagnosis result is delayed based on the working condition after the fault occurs.
The technical scheme of the invention is as follows:
a digital twin based transformer fault prediction method, the method comprising:
extracting the simulation operation characteristics of the transformer based on the simulation data of the digital twin model of the transformer;
performing fault prediction on the transformer according to the simulated operation characteristics and a preset transformer fault prediction model to generate a fault prediction result;
and outputting the fault prediction result through a digital twin model.
The digital twin model comprises map data of the transformer, and the step of extracting the simulated operating characteristics of the transformer comprises: a feature field of an operational feature of the transformer is selected based on the graph data of the transformer.
The step of extracting the simulated operation characteristics of the transformer comprises the following steps:
simulating the operation parameters of the transformer in a preset time period by a digital twin model based on the real-time data of the transformer, and generating simulation data;
and extracting a first operation parameter corresponding to the operation characteristic field in the simulation data as a simulation operation characteristic.
The method for selecting the characteristic field of the operation characteristic of the transformer based on the graph data of the transformer comprises the following steps: acquiring historical data in the digital twin model, wherein the historical data comprises second operation parameters of each node field in the graph data in a preset time period of the transformer under various operation states;
generating dispersion of second operation parameters of multiple operation states, and taking a node field corresponding to the second operation parameter with the dispersion larger than a preset dispersion threshold value as a characteristic field;
or, taking a node field corresponding to the second operation parameter with the divergence degree in the preset ranking as a characteristic field.
The fault prediction result comprises a first fault, a second fault and a third fault, and the step of performing fault prediction on the transformer according to the simulated operation characteristics and a preset transformer fault prediction model to generate the fault prediction result comprises the following steps:
inputting the simulated operation characteristics into a preset transformer fault prediction model, and generating a first probability of a first fault, a second probability of a second fault and a third probability of a third fault when the transformer is in an operation state of the simulated operation characteristics;
and taking the fault type corresponding to the probability with the maximum median of the first probability, the second probability and the third probability as a fault prediction result of the transformer.
The steps of generating a first probability of the first failure, a second probability of the second failure, and a third probability of the third failure comprise:
generating a first probability according to the distribution condition of the simulation operation characteristics in the first fault sample set;
generating a second probability according to the distribution condition of the simulation operation characteristics in the second fault sample set;
generating a third probability according to the distribution condition of the simulation operation characteristics in the third fault sample set;
the transformer fault prediction model includes a first fault sample set, a second fault sample set, and a third fault sample set.
The digital twin model comprises a three-dimensional model of the transformer, and the step of outputting the fault prediction result through the digital twin model comprises the following steps: and outputting the fault detection result at the corresponding position in the three-dimensional model of the transformer.
A digital twin-based transformer fault prediction device includes:
the extraction module is used for extracting the simulation operation characteristics of the transformer based on the simulation data of the digital twin model of the transformer;
the prediction module is used for predicting the fault of the transformer according to the simulation operation characteristics and a preset transformer fault prediction model to generate a fault prediction result;
and the output module is used for outputting the fault prediction result through the digital twin model.
A digital twin-based transformer fault prediction apparatus, comprising: memory, a processor and a digital twin based transformer fault prediction program stored on the memory and executable on the processor, the digital twin based transformer fault prediction program when executed by the processor implementing the steps of the digital twin based transformer fault prediction method according to any of claims 1 to 7.
A computer readable storage medium having stored thereon a digital twin based transformer fault prediction program which when executed by a processor implements the steps of the digital twin based transformer fault prediction method according to any one of claims 1 to 7.
The invention has the beneficial effects that:
the method comprises the steps of extracting the simulation operation characteristics of the transformer based on the simulation data of a digital twin model of the transformer; performing fault prediction on the transformer according to the simulated operation characteristics and a preset transformer fault prediction model to generate a fault prediction result; and outputting the fault prediction result through a digital twin model. Compared with the prior art, the method has stronger timeliness for predicting the fault of the transformer based on the simulated data, and can judge the possible fault of the transformer in all directions through the transformer fault prediction model, the prediction data and the historical data, so that the judgment standard is more flexible, and the more the number of samples in the historical data is, the more the prediction result is accurate, thereby enhancing the operation and maintenance monitoring capability of the transformer and improving the stability of the power system.
The transformer diagnosis method and the transformer diagnosis system solve the technical problems that diagnosis is performed based on working conditions after faults occur, the diagnosis is too absolute, and the diagnosis result is delayed.
Drawings
FIG. 1 is a schematic diagram of an apparatus architecture of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a first embodiment of the method for predicting the failure of the transformer based on the digital twin according to the present invention;
fig. 3 is a schematic diagram of transformer map data of the digital twin-based transformer fault prediction method of the present invention.
Detailed Description
As shown in fig. 1, fig. 1 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention.
The device in the embodiment of the invention can be a PC, and can also be an electronic terminal device with the functions of data receiving, data processing, data sending and the like, such as a cloud service, a smart phone, a tablet personal computer, a portable computer and the like.
As shown in fig. 1, the apparatus may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. The communication bus 1002 is used to implement connection communication among these components. The user interface 1003 may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Optionally, the device may also include a camera, RF (Radio Frequency) circuitry, sensors, audio circuitry, wiFi modules, and so forth. Such as light sensors, motion sensors, and other sensors. Specifically, the light sensor may include an ambient light sensor that may adjust the brightness of the display screen according to the brightness of ambient light, and a proximity sensor that may turn off the display screen and/or the backlight when the mobile terminal is moved to the ear. As one of the motion sensors, the gravity acceleration sensor can detect the magnitude of acceleration in each direction (generally, three axes), detect the magnitude and direction of gravity when the mobile terminal is stationary, and can be used for applications (such as horizontal and vertical screen switching, related games, magnetometer attitude calibration), vibration recognition related functions (such as pedometer and tapping) and the like for recognizing the attitude of the mobile terminal; of course, the mobile terminal may also be configured with other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which are not described herein again.
Those skilled in the art will appreciate that the device configuration shown in fig. 1 is not intended to be limiting and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a digital twin-based transformer failure prediction method.
In the terminal shown in fig. 1, the network interface 1004 is mainly used for connecting to a backend server and performing data communication with the backend server; the user interface 1003 is mainly used for connecting a client (user side) and performing data communication with the client; and processor 1001 may be configured to invoke the digital twin based transformer fault prediction method stored in memory 1005 and perform the following operations:
extracting simulated operation characteristics of the transformer based on simulated data of a digital twin model of the transformer;
performing fault prediction on the transformer according to the simulated operation characteristics and a preset transformer fault prediction model to generate a fault prediction result;
and outputting the fault prediction result through the digital twin model.
Further, processor 1001 may invoke the digital twin based transformer fault prediction method stored in memory 1005, and also perform the following operations:
the digital twin model comprises map data of the transformer, and before the step of extracting simulated operational characteristics of the transformer from the simulated data of the digital twin model based on the transformer, the method comprises:
selecting a feature field of the operational feature of the transformer based on the graph data of the transformer.
Further, processor 1001 may invoke the digital twin based transformer fault prediction method stored in memory 1005, and also perform the following operations:
the step of extracting the simulated operation characteristics of the transformer based on the simulated data of the digital twin model of the transformer comprises the following steps:
simulating the operation parameters of the transformer in a preset time period based on the real-time data of the transformer through the digital twin model, and generating the simulation data;
and extracting a first operation parameter corresponding to the operation characteristic field in the simulation data as the simulation operation characteristic.
Further, processor 1001 may invoke the digital twin based transformer fault prediction method stored in memory 1005, and also perform the following operations:
the step of selecting a characteristic field of the operation characteristic of the transformer based on the graph data of the transformer comprises the following steps:
acquiring historical data in the digital twin model, wherein the historical data comprises second operating parameters of each node field in the graph data within a preset time period under various operating states of the transformer;
generating dispersion of the second operation parameters in multiple operation states, and taking a node field corresponding to the second operation parameter with the dispersion larger than a preset dispersion threshold value as the feature field;
or taking a node field corresponding to the second operation parameter with the dispersion degree at a preset rank as the characteristic field.
Further, processor 1001 may invoke the digital twin based transformer fault prediction method stored in memory 1005 and also perform the following operations:
the fault prediction result comprises a first fault, a second fault and a third fault, and the step of performing fault prediction on the transformer according to the simulated operation characteristics and a preset transformer fault prediction model to generate the fault prediction result comprises the following steps:
inputting the simulated operation characteristics into the preset transformer fault prediction model, and generating a first probability of the transformer generating the first fault, a second probability of the transformer generating the second fault and a third probability of the transformer generating the third fault in the operation state of the simulated operation characteristics;
and taking the fault type corresponding to the probability with the maximum median of the first probability, the second probability and the third probability as the fault prediction result of the transformer.
Further, processor 1001 may invoke the digital twin based transformer fault prediction method stored in memory 1005 and also perform the following operations:
the step of inputting the simulated operation characteristics into the preset transformer fault prediction model to generate a first probability of the transformer having the first fault, a second probability of the transformer having the second fault, and a third probability of the transformer having the third fault in the operation state of the simulated operation characteristics includes:
generating the first probability according to the distribution condition of the simulation operation characteristics in a first fault sample set;
generating the second probability according to the distribution condition of the simulated operation features in a second fault sample set;
generating the third probability according to the distribution condition of the simulation operation characteristics in a third fault sample set;
the preset transformer fault prediction model comprises the first fault sample set, the second fault sample set and the third fault sample set.
Further, processor 1001 may invoke the digital twin based transformer fault prediction method stored in memory 1005, and also perform the following operations:
the digital twin model comprises a three-dimensional model of the transformer, and the step of outputting the fault prediction result through the digital twin model comprises:
and outputting the fault detection result at the corresponding position in the three-dimensional model of the transformer.
Referring to fig. 2, a first embodiment of the digital twin-based transformer fault prediction method of the present invention includes:
step S10, extracting the simulation operation characteristics of the transformer based on the simulation data of the digital twin model of the transformer;
further, the digital twin model comprises map data of the transformer, and before the step of extracting the simulated operation characteristics of the transformer based on the simulated data of the digital twin model of the transformer, the method comprises the following steps: and selecting a characteristic field of the operation characteristic of the transformer based on the graph data of the transformer.
Specifically, before the simulated operation features are extracted, the operation feature field needs to be determined. The graph data is the attributes of the transformer in multiple dimensions, the graph data consists of nodes and edges, the nodes comprise node fields, for example, the graph data of the transformer shown in fig. 3, the primary node field is the transformer, the primary node transformer is connected with each secondary node through the edges, each secondary node corresponds to the description field, and each secondary node is connected with each secondary node through the edges, so that the description of the attributes of the transformer in multiple dimensions is completed. Meanwhile, part of the node fields may correspond to specific values, such as secondary node weather, which may include temperature or humidity of the transformer area, or data measured by each measuring point by the sensor. It should be understood that the above graph data does not limit the node fields in the present embodiment, for example, the node fields may also include each gas dissolved in the transformer oil, and the corresponding values of the fields are the components of the gas. And the characteristic field of the operation characteristic of the transformer can be selected and set by a technician in the node field in the graph data, and a field which is most favorable for fault prediction can be selected as the characteristic field based on historical data.
Further, the step of extracting the simulated operation characteristics of the transformer based on the simulated data of the digital twin model of the transformer comprises: simulating the operation parameters of the transformer in a preset time period based on the real-time data of the transformer through the digital twin model, and generating the simulation data; and extracting a first operation parameter corresponding to the operation characteristic field in the simulation data as the simulation operation characteristic.
Specifically, the digital twin model is based on virtual mapping of a solid transformer, and the digital twin model at least comprises a transformer three-dimensional model and a transformer mechanism model which are built based on the solid transformer. The three-dimensional model of the transformer comprises all components including a solid transformer (oil-immersed), such as: the transformer comprises an iron core, a winding, insulation, a lead (comprising a pressure regulating device, a lead clamping piece and the like), accessories (comprising an oil conservator, an accelerator gate valve and the like), a cooling device (comprising a radiator, a wind exciter, an oil system and the like), a protection device (comprising an explosion-proof valve, a gas relay, a temperature measuring element, a respirator and the like), and a lead outlet device (comprising a sleeve and the like), wherein all component models form a three-dimensional model of the whole transformer. The transformer mechanism model can enable the digital twin model to simulate according to the actual transformer operation condition. And the mechanism model is a mathematical model formed by physical theorems, such as the transformer built based on the structure of the transformer, the law of heating power, the law of electromagnetism, the law of heat transfer and natural environment conditions, and can reflect the change of the properties of the transformer under certain conditions, such as heat, electricity and the like. For example, the change of the temperature of the internal winding or the cooling oil of the transformer can obtain the actual working condition of the transformer through measuring points (sensors) distributed at each position of the physical transformer (such as a transformer coil, a transformer oil tank, a line connected with the transformer and the like), the heat productivity of the transformer can be obtained according to a transformer energy loss formula (or an empirical formula), and meanwhile, a thermodynamic mathematical model can be constructed through the heat dissipation conditions of the transformer, including the internal heat conductivity coefficient of the transformer, the external heat exchange coefficient and the like, so that the heat (temperature) change trend of the transformer in the next period of time can be simulated, and the operation condition of the transformer in the future time can be predicted based on the current working condition. In the embodiment, the analog data generated by the digital twin model is acquired in real time based on each measuring point on the physical transformer, so that the data obtained by the simulation also changes in real time. In addition, after the operation condition of the transformer in a period of time in the future is simulated based on the current real-time condition prediction, because the content of the gas dissolved in the transformer oil is changed based on the transformer condition of the transformer (for example, the content of the gas is changed due to overheating temperature or discharging), the content of the gas dissolved in the transformer oil can also be simulated and predicted based on the predicted transformer condition through a machine learning algorithm. It can be understood that the operation parameters predicted to simulate the operation condition of the transformer for a period of time in the future are simulation data. And extracting a first operation parameter corresponding to the operation characteristic field in the simulation data as the simulation operation characteristic. And if the operation characteristic field is the oil temperature, extracting the specific oil temperature in the simulation data and taking the specific oil temperature as the simulation operation characteristic.
Further, historical data in the digital twin model are obtained, wherein the historical data comprise second operation parameters of each node field in the graph data within a preset time period under multiple operation states of the transformer; generating dispersion of the second operation parameters in multiple operation states, and taking a node field corresponding to the second operation parameter with the dispersion larger than a preset dispersion threshold value as the feature field; or taking a node field corresponding to the second operation parameter with the dispersion degree at a preset rank as the characteristic field.
Specifically, the various operating states of the transformer include a normal state and a fault state, and the fault state may include arc discharge, partial discharge, spark discharge, high temperature overheat, medium temperature overheat, low temperature overheat, high energy discharge, low energy discharge, and the like. And second operation parameters corresponding to each node field of the transformer under each operation state are stored in the digital twin model, and the second operation parameters comprise the temperature, the current, the humidity, the oil temperature, the dissolved gas components in the transformer oil and the like of the transformer. The historical data is stored in the form of sample data, and each fault type is used as a class of sample numberThe data set, for example, the high-energy discharge sample set includes the operation parameter data of the transformer calibrated as the high-energy discharge fault (high-energy discharge fault sample 1, temperature: 72.4 ℃, current: (a-phase 122.5584A, b-phase 125.4882A, c-phase 128.4179A), humidity 65%, oil temperature 69 ℃, dissolved gas component (hydrogen H) in the transformer oil2:12.14, carbon monoxide CO:587.65, methane CH4:4.64 ethylene C2H4:1.16 acetylene C2H2: 0. ethane C2H6: 0. total hydrocarbons THC: 5.8% carbon dioxide, CO2: 1214.33)). For the dispersion, an oil temperature parameter (a second operation parameter includes a parameter) and any three fault samples are taken as an example for explanation, if the fault samples include a partial discharge sample set, a spark discharge sample set and a high-temperature overheating sample set, the average oil temperature of the partial discharge sample set is calculated to be 61 ℃, the average oil temperature of the spark discharge sample set is calculated to be 64 ℃, the oil temperature of the high-temperature overheating sample set is calculated to be 72 ℃, a variance is calculated based on 61, 64 and 72, the variance value is taken as the dispersion of the oil temperature parameter among multiple operation states, the obtained dispersion is compared with a dispersion threshold value, and if the variance value is greater than the variance value, the oil temperature is taken as a characteristic field. In addition, the characteristic fields can also be selected based on the ranking of the dispersion, for example, the temperature dispersion, the current dispersion, the oil temperature dispersion or the gas dispersion and the like are obtained by calculation based on the above mode, ranking is performed according to the dispersion, and the fields of the first three names are selected as the characteristic fields. It should be understood that the node field with greater dispersion has greater ability to distinguish different fault categories, and the dispersion threshold and the dispersion rank can also be set by a technician according to actual situations.
Step S20, carrying out fault prediction on the transformer according to the simulated operation characteristics and a preset transformer fault prediction model to generate a fault prediction result;
further, the fault prediction result includes a first fault, a second fault and a third fault, and the step of performing fault prediction on the transformer according to the simulated operation characteristic and a preset transformer fault prediction model to generate the fault prediction result includes: inputting the simulated operation characteristics into the preset transformer fault prediction model, and generating a first probability of the transformer generating the first fault, a second probability of the transformer generating the second fault and a third probability of the transformer generating the third fault in the operation state of the simulated operation characteristics; and taking the fault type corresponding to the probability with the maximum median of the first probability, the second probability and the third probability as the fault prediction result of the transformer.
Specifically, the failure prediction result includes a first failure, a second failure, and a third failure, which are only used to indicate that there are three failures in the present embodiment, and specifically, the failure type of each failure may also be selected by a technician based on the above example, and in addition, the number of the failure types may also be freely increased or decreased by the technician, for example, a fourth failure, a fifth failure, and the like may be added, or only the first failure and the second failure may be included.
The simulated operation features are first operation parameters corresponding to the feature fields selected in the above example, if the to-be-operated features are respectively temperature C, current M, and gas content N (N may be a ratio of each gas content in a three-ratio method, and there is a mature technique regarding selection or generation of the gas content features, where the specific limitation on the characteristic gas content N is not made), the temperature C, the current M, and the gas content N are input to a preset transformer fault prediction model, and a first probability of the transformer generating a first fault, a second probability of the transformer generating a second fault, and a third probability of the transformer generating a third fault are respectively generated.
Further, generating the first probability according to the distribution condition of the simulation operation characteristics in a first fault sample set; generating the second probability according to the distribution condition of the simulation operation characteristics in a second fault sample set; generating the third probability according to the distribution condition of the simulated operation features in a third fault sample set; the preset transformer fault prediction model comprises the first fault sample set, the second fault sample set and the third fault sample set.
Specifically, the transformer fault prediction model includes a first fault sample set, a second fault sample set, and a third fault sample set, and it can be understood that the first to third fault sample sets may be any three of an arc discharge fault sample set, a partial discharge fault sample set, a spark discharge fault sample set, a high-temperature overheat fault sample set, a medium-temperature overheat fault sample set, a low-temperature overheat fault sample set, a high-energy discharge fault sample set, and a low-energy discharge fault sample set. Taking the first fault sample set as an example for description, if the number of samples in the first fault sample set is 100, the first fault sample set includes 100 samples calibrated as first fault samples, and specific data of each sample is an operation condition of the transformer (such as a temperature, an oil temperature, and a current of the transformer, and at least includes a characteristic field corresponding to a simulated operation characteristic). The further generation mode of the first probability is as follows: obtaining the number of samples (if 13) with the operating condition of the sample being the temperature C (or greater than C-X and less than C + X), the number of samples (if 27) with the current M (or greater than M-X and less than M + X), and the number of samples (if 9) with the gas content N (or greater than N-X and less than N + X), and finding the first probability of (13 +27+ 9)/100 =0.49. Similarly, the second probability is 0.37 and the third probability is 0.52, which are not described herein again. And determining that the value of the third probability is maximum through judgment, and taking the third fault corresponding to the third probability as a fault prediction result of the transformer.
And step S30, outputting the fault prediction result through the digital twin model.
And further, outputting the fault detection result at a corresponding position in the three-dimensional model of the transformer.
Specifically, if the fault detection result is a medium-temperature overheating fault, which may be caused by blockage of an oil passage of the transformer oil tank, the position of the oil passage of the transformer oil tank in the three-dimensional model is highlighted to perform fault alarm.
In the embodiment, the simulation operation characteristics of the transformer are extracted based on the simulation data of the digital twin model of the transformer; performing fault prediction on the transformer according to the simulated operation characteristics and a preset transformer fault prediction model to generate a fault prediction result; and outputting the fault prediction result through the digital twin model. Compared with the prior art, the method has stronger timeliness for predicting the fault of the transformer based on the simulated data, and meanwhile, the fault possibly occurring in the transformer is judged in all directions through the transformer fault prediction model, the prediction data and the historical data, so that the judgment standard is more flexible, and the more the number of samples in the historical data is, the more accurate the prediction result is, thereby enhancing the operation and maintenance monitoring capability of the transformer and improving the stability of a power system.
In addition, the present embodiment also provides a digital twin-based transformer fault prediction apparatus, where the digital twin-based transformer fault prediction apparatus includes:
the extraction module is used for extracting the simulation operation characteristics of the transformer based on the simulation data of the digital twin model of the transformer;
the prediction module is used for predicting the fault of the transformer according to the simulation operation characteristics and a preset transformer fault prediction model to generate a fault prediction result;
and the output module is used for outputting the fault prediction result through the digital twin model.
In addition, the present embodiment also provides a digital twin-based transformer fault prediction apparatus, including: a memory, a processor and a digital twin based transformer fault prediction program stored on the memory and executable on the processor, the digital twin based transformer fault prediction program when executed by the processor implementing the steps of the digital twin based transformer fault prediction method as described above.
Furthermore, the present embodiment also provides a computer readable storage medium, on which a digital twin-based transformer fault prediction program is stored, which when executed by a processor implements the steps of the digital twin-based transformer fault prediction method as described above.
Claims (10)
1. A transformer fault prediction method based on digital twinning is characterized in that: the method comprises the following steps:
extracting the simulation operation characteristics of the transformer based on the simulation data of the digital twin model of the transformer;
performing fault prediction on the transformer according to the simulated operation characteristics and a preset transformer fault prediction model to generate a fault prediction result;
and outputting a fault prediction result through a digital twin model.
2. The method for predicting the fault of the transformer based on the digital twin as claimed in claim 1, wherein: the digital twin model comprises graph data of the transformer, and the step of extracting the simulated operation characteristics of the transformer comprises the following steps: a feature field of an operational feature of the transformer is selected based on the graph data of the transformer.
3. The method for predicting the fault of the transformer based on the digital twin as claimed in claim 1, wherein: the step of extracting the simulated operation characteristics of the transformer comprises the following steps:
simulating the operation parameters of the transformer in a preset time period by a digital twin model based on the real-time data of the transformer, and generating simulation data;
and extracting a first operation parameter corresponding to the operation characteristic field in the simulation data as a simulation operation characteristic.
4. The method for predicting the fault of the transformer based on the digital twin as claimed in claim 2, wherein: the method for selecting the characteristic field of the operation characteristic of the transformer based on the graph data of the transformer comprises the following steps: acquiring historical data in the digital twin model, wherein the historical data comprises second operating parameters of each node field in the graph data in a preset time period under various operating states of the transformer;
generating dispersion of second operation parameters of multiple operation states, and taking a node field corresponding to the second operation parameter with the dispersion larger than a preset dispersion threshold value as a characteristic field;
or, taking a node field corresponding to the second operation parameter with the divergence degree in the preset ranking as a characteristic field.
5. The digital twin-based transformer fault prediction method according to claim 1, characterized in that: the fault prediction result comprises a first fault, a second fault and a third fault, and the step of performing fault prediction on the transformer according to the simulated operation characteristics and a preset transformer fault prediction model to generate the fault prediction result comprises the following steps:
inputting the simulated operation characteristics into a preset transformer fault prediction model, and generating a first probability of a first fault, a second probability of a second fault and a third probability of a third fault when the transformer is in an operation state of the simulated operation characteristics;
and taking the fault type corresponding to the probability with the maximum median of the first probability, the second probability and the third probability as a fault prediction result of the transformer.
6. The method for predicting the fault of the transformer based on the digital twin as claimed in claim 5, wherein: the steps of generating a first probability of a first failure, a second probability of a second failure, and a third probability of a third failure comprise:
generating a first probability according to the distribution condition of the simulation operation characteristics in the first fault sample set;
generating a second probability according to the distribution condition of the simulation operation characteristics in the second fault sample set;
generating a third probability according to the distribution condition of the simulation operation characteristics in the third fault sample set;
the transformer fault prediction model includes a first fault sample set, a second fault sample set, and a third fault sample set.
7. The digital twin-based transformer fault prediction method according to claim 1, characterized in that: the digital twin model comprises a three-dimensional model of the transformer, and the step of outputting the fault prediction result through the digital twin model comprises the following steps: and outputting the fault detection result at the corresponding position in the three-dimensional model of the transformer.
8. A digital twin-based transformer failure prediction apparatus is characterized by comprising:
the extraction module is used for extracting the simulation operation characteristics of the transformer based on the simulation data of the digital twin model of the transformer;
the prediction module is used for predicting the fault of the transformer according to the simulation operation characteristics and a preset transformer fault prediction model to generate a fault prediction result;
and the output module is used for outputting the fault prediction result through the digital twin model.
9. A digital twin-based transformer fault prediction apparatus, characterized by comprising: memory, a processor and a digital twin based transformer fault prediction program stored on the memory and executable on the processor, the digital twin based transformer fault prediction program when executed by the processor implementing the steps of the digital twin based transformer fault prediction method according to any of claims 1 to 7.
10. A computer readable storage medium, characterized in that the readable storage medium has stored thereon a digital twin based transformer fault prediction program, which when executed by a processor implements the steps of the digital twin based transformer fault prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210861469.9A CN115269928B (en) | 2022-07-22 | 2022-07-22 | Transformer fault prediction method, device, equipment and medium based on digital twin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210861469.9A CN115269928B (en) | 2022-07-22 | 2022-07-22 | Transformer fault prediction method, device, equipment and medium based on digital twin |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115269928A true CN115269928A (en) | 2022-11-01 |
| CN115269928B CN115269928B (en) | 2023-07-21 |
Family
ID=83766857
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210861469.9A Active CN115269928B (en) | 2022-07-22 | 2022-07-22 | Transformer fault prediction method, device, equipment and medium based on digital twin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115269928B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116245502A (en) * | 2022-12-26 | 2023-06-09 | 北京国网富达科技发展有限责任公司 | Digital twinning-based virtual-real interaction operation and detection method and system for transformer equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200143795A1 (en) * | 2017-02-10 | 2020-05-07 | Johnson Controls Technology Company | Building system with digital twin based data ingestion and processing |
| CN112418451A (en) * | 2020-11-05 | 2021-02-26 | 武汉大学 | Transformer fault diagnosis positioning system based on digital twinning |
| CN112685949A (en) * | 2020-11-25 | 2021-04-20 | 江苏科技大学 | Transformer health prediction method based on digital twinning |
| CN112684379A (en) * | 2020-11-25 | 2021-04-20 | 江苏科技大学 | Transformer fault diagnosis system and method based on digital twinning |
| CN113902181A (en) * | 2021-09-28 | 2022-01-07 | 国网河北省电力有限公司营销服务中心 | Short-term prediction method and equipment for common variable heavy overload |
| US20220014946A1 (en) * | 2021-09-23 | 2022-01-13 | Intel Corporation | Methods and apparatus for digital twin aided resiliency |
-
2022
- 2022-07-22 CN CN202210861469.9A patent/CN115269928B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200143795A1 (en) * | 2017-02-10 | 2020-05-07 | Johnson Controls Technology Company | Building system with digital twin based data ingestion and processing |
| CN112418451A (en) * | 2020-11-05 | 2021-02-26 | 武汉大学 | Transformer fault diagnosis positioning system based on digital twinning |
| US20220137612A1 (en) * | 2020-11-05 | 2022-05-05 | Wuhan University | Transformer fault diagnosis and positioning system based on digital twin |
| CN112685949A (en) * | 2020-11-25 | 2021-04-20 | 江苏科技大学 | Transformer health prediction method based on digital twinning |
| CN112684379A (en) * | 2020-11-25 | 2021-04-20 | 江苏科技大学 | Transformer fault diagnosis system and method based on digital twinning |
| US20220014946A1 (en) * | 2021-09-23 | 2022-01-13 | Intel Corporation | Methods and apparatus for digital twin aided resiliency |
| CN113902181A (en) * | 2021-09-28 | 2022-01-07 | 国网河北省电力有限公司营销服务中心 | Short-term prediction method and equipment for common variable heavy overload |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116245502A (en) * | 2022-12-26 | 2023-06-09 | 北京国网富达科技发展有限责任公司 | Digital twinning-based virtual-real interaction operation and detection method and system for transformer equipment |
| CN116245502B (en) * | 2022-12-26 | 2023-09-29 | 北京国网富达科技发展有限责任公司 | Digital twinning-based virtual-real interaction operation and detection method and system for transformer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115269928B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102054377B (en) | Remote simulation training system for electrical tests of transformer | |
| CN105074598B (en) | The system and method predicted and diagnosed for transmission and disttrbution Asset State | |
| CN106920432A (en) | The simulation training system and emulation training method of substation equipment maintenance | |
| CN115269928B (en) | Transformer fault prediction method, device, equipment and medium based on digital twin | |
| WO2023130763A1 (en) | Transformer state analysis method and system, device, and storage medium | |
| CN103399241A (en) | Distribution transformer fault diagnosis system and method based on relation between temperature rise and load | |
| CN113009077B (en) | Gas detection method, gas detection device, electronic equipment and storage medium | |
| CN115549314B (en) | Dry-type transformer fault remote early warning system based on Internet of things | |
| CN113591333A (en) | Construction method of GIS (gas insulated switchgear) temperature simulation model based on digital twinning | |
| Liu et al. | The research of OLTC on-line detection system based on embedded and wireless sensor networks | |
| CN115656747A (en) | Transformer defect diagnosis method and device based on heterogeneous data and computer equipment | |
| CN111859802B (en) | Method, system and equipment for calculating steady-state temperature of overhead conductor | |
| Feng et al. | Implementation of a power transformer temperature monitoring system | |
| CN105353233A (en) | Method and device of on-line operation capability detection of transformer | |
| Wenhan et al. | Application of digital twin system in power transformer fault detection | |
| CN218850897U (en) | Natural gas metering and diagnosing system | |
| CN117573861A (en) | Visual display method and device for secondary circuit of intelligent substation | |
| JP7382909B2 (en) | Equipment management device, its control method and program | |
| JP6150553B2 (en) | Driving operation evaluation device, driving operation evaluation method, and driving operation evaluation program | |
| CN117233540B (en) | Metering pipeline fault detection method and system based on deep learning | |
| CN115618747B (en) | Cable hot spot state evaluation method and device | |
| Tiwari et al. | REAL TIME SURGE VOLTAGE CONTROL USING SMART IoT. | |
| CN109636209B (en) | Online risk assessment method for influence of intelligent isolation breaker on power grid based on big data analysis | |
| CN117595216A (en) | Power distribution network wide-area protection method and system based on electrical quantity mutation characterization | |
| CN114239254A (en) | SF6 electrical equipment sound field digital twin model construction method, device and equipment |
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 |