CN115656747A - Transformer defect diagnosis method and device based on heterogeneous data and computer equipment - Google Patents
Transformer defect diagnosis method and device based on heterogeneous data and computer equipment Download PDFInfo
- Publication number
- CN115656747A CN115656747A CN202211687682.9A CN202211687682A CN115656747A CN 115656747 A CN115656747 A CN 115656747A CN 202211687682 A CN202211687682 A CN 202211687682A CN 115656747 A CN115656747 A CN 115656747A
- Authority
- CN
- China
- Prior art keywords
- data
- transformer
- model
- simulation
- defect diagnosis
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 217
- 238000003745 diagnosis Methods 0.000 title claims abstract description 189
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000004088 simulation Methods 0.000 claims abstract description 186
- 238000004590 computer program Methods 0.000 claims abstract description 21
- 238000003860 storage Methods 0.000 claims abstract description 12
- 238000010219 correlation analysis Methods 0.000 claims description 33
- 230000001133 acceleration Effects 0.000 claims description 22
- 238000004804 winding Methods 0.000 claims description 20
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims description 12
- 238000007667 floating Methods 0.000 claims description 11
- 238000004806 packaging method and process Methods 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 4
- 238000011065 in-situ storage Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 description 17
- 239000007789 gas Substances 0.000 description 12
- 239000011159 matrix material Substances 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 238000009413 insulation Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000013021 overheating Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- 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
- Testing Relating To Insulation (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The application relates to a transformer defect diagnosis method and device based on heterogeneous data, computer equipment, storage medium and computer program product. The method comprises the following steps: acquiring a first simulation model for simulating the discharge of the transformer; the first simulation model is used for outputting first simulation discharge data of the transformer; acquiring field sensor data of the transformer, and adjusting model parameters of the first simulation model according to the first simulation discharge data and the field sensor data to obtain a second simulation model; the second simulation model is used for outputting second simulation discharge data of the transformer; the correlation degree of the second simulation discharge data and the field sensor data is greater than that of the first simulation discharge data and the field sensor data; and acquiring field heterogeneous data of the transformer, and inputting the field heterogeneous data and the second simulation discharge data into a pre-trained defect diagnosis model to obtain a defect diagnosis result of the transformer. The method can accurately identify the defects of the transformer.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a transformer defect diagnosis method and apparatus based on heterogeneous data, a computer device, a storage medium, and a computer program product.
Background
The transformer is used as an operation junction device for power transmission and distribution of a power system, and is often influenced by adverse factors such as a manufacturing process, short circuit at a nearby place, overcurrent and overvoltage in the operation process, so that the transformer often has operation defects such as winding overheating, winding loosening deformation, insulation defects between turns and between cakes, and casing defects, and when the transformer fails, the transformer can greatly influence the safe operation of a power grid, and the accurate identification of the defects in the operation process of the transformer is very important.
At present, when the defects of the transformer are identified, a data-driven mode is generally adopted to construct a defect identification model. However, the construction of the defect identification model depends on massive feature data to achieve a good defect identification effect. In fact, various feature data amounts corresponding to different types of defects of the transformer are deficient, and the defect identification model constructed by the commonly adopted single feature cannot accurately identify the defect type of the transformer, so that the defect identification of the transformer is not accurate enough, and the safe operation of the power system cannot be ensured.
Therefore, the defect identification of the transformer is not accurate in the traditional technology.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a transformer defect diagnosis method, apparatus, computer device, computer readable storage medium and computer program product based on heterogeneous data, which can accurately identify transformer defects.
A transformer defect diagnosis method based on heterogeneous data is characterized by comprising the following steps:
acquiring a first simulation model for simulating the discharge of the transformer; the first simulation model is used for outputting first simulation discharge data of the transformer;
acquiring field sensor data of the transformer, and adjusting model parameters of the first simulation model according to the first simulation discharge data and the field sensor data to obtain a second simulation model; the second simulation model is used for outputting second simulation discharge data of the transformer; the correlation degree of the second simulated discharge data and the field sensor data is greater than that of the first simulated discharge data and the field sensor data;
and acquiring field heterogeneous data of the transformer, and inputting the field heterogeneous data and the second simulation discharge data into a pre-trained defect diagnosis model to obtain a defect diagnosis result of the transformer.
In one embodiment, adjusting model parameters of the first simulation model according to the first simulation discharge data and the field sensor data to obtain a second simulation model includes:
performing grey correlation analysis on the first simulated discharge data and the field sensor data to obtain a grey correlation analysis result; the grey correlation analysis result represents the correlation degree between the first simulation discharge data and the field sensor data;
under the condition that the value represented by the gray correlation analysis result is smaller than or equal to a preset threshold value, adjusting model parameters of the first simulation model, and returning to the step of performing gray correlation analysis on the first simulation discharge data and the field sensor data until the value represented by the gray correlation analysis result is larger than the preset threshold value;
and taking the first simulation model after the parameters are adjusted as a second simulation model.
In one embodiment, inputting the field heterogeneous data and the second simulation discharge data into a pre-trained defect diagnosis model to obtain a defect diagnosis result, including:
classifying the field heterogeneous data and the second simulation discharge data to obtain a plurality of characteristic data frames corresponding to the transformer in operation; each characteristic data frame has different operation data types; the operation data type comprises at least one of load condition, oil temperature, winding temperature, vibration characteristics, partial discharge signals, center point grounding current, iron core grounding current and dissolved gas in oil, which are related to the transformer;
and inputting the characteristic data frames corresponding to the operation data types into corresponding pre-trained defect diagnosis models to obtain defect diagnosis results.
In one embodiment, inputting the feature data frame corresponding to each operation data type into a corresponding pre-trained defect diagnosis model to obtain a defect diagnosis result, including:
converting each pre-trained defect diagnosis model from a floating point number structure model into a fixed point number structure model to obtain a quantized defect diagnosis model;
and inputting the characteristic data frames corresponding to the operation data types into the corresponding quantized defect diagnosis model to obtain the defect diagnosis result of the transformer.
In one embodiment, the method is applied to a computer device, the computer device runs at least two acceleration networks established by an FPGA in parallel, and the characteristic data frames corresponding to each running data type are input to a corresponding pre-trained defect diagnosis model to obtain a defect diagnosis result, and the method includes:
inputting the characteristic data frame corresponding to each operation data type into a corresponding acceleration network to obtain a defect diagnosis result returned by the acceleration network;
the acceleration network is used for converting the corresponding pre-trained defect diagnosis model from a floating point number structure model to a fixed point number structure model to obtain a quantized defect diagnosis model; and inputting the corresponding characteristic data frame into the quantized defect diagnosis model to obtain a corresponding defect diagnosis result.
In one embodiment, acquiring in-situ sensor data for a transformer comprises:
acquiring sensor data corresponding to the transformer; the sensor data is data read by a plurality of sensors arranged at the positions of the power system of the transformer; the data of each sensor adopts the same preset data structure;
and packaging the sensor data to obtain field sensor data.
In one embodiment, acquiring field heterogeneous data of a transformer comprises:
collecting heterogeneous data of a transformer at the position of a power system; the heterogeneous data comprises at least one of site monitoring texts, pictures and waveforms;
and according to the acquisition time and the sampling rate corresponding to the heterogeneous data, packaging the heterogeneous data to obtain the on-site heterogeneous data.
A transformer defect diagnosis device based on heterogeneous data is characterized by comprising:
the acquisition module is used for acquiring a first simulation model for simulating the discharge of the transformer; the first simulation model is used for outputting first simulation discharge data of the transformer;
the adjusting module is used for acquiring field sensor data of the transformer, and adjusting model parameters of the first simulation model according to the first simulation discharge data and the field sensor data to obtain a second simulation model; the second simulation model is used for outputting second simulation discharge data of the transformer; the correlation degree of the second simulation discharge data and the field sensor data is greater than that of the first simulation discharge data and the field sensor data;
and the diagnosis module is used for acquiring the field heterogeneous data of the transformer, and inputting the field heterogeneous data and the second simulation discharge data into the pre-trained defect diagnosis model to obtain the defect diagnosis result of the transformer.
A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the above-mentioned method when executing the computer program.
A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program realizes the steps of the above-mentioned method when executed by a processor.
The transformer defect diagnosis method and device based on heterogeneous data, the computer equipment, the storage medium and the computer program product are used for acquiring a first simulation model for simulating transformer discharge; the first simulation model is used for outputting first simulation discharge data of the transformer; acquiring field sensor data of the transformer, and adjusting model parameters of the first simulation model according to the first simulation discharge data and the field sensor data to obtain a second simulation model; acquiring field heterogeneous data of the transformer, and inputting the field heterogeneous data and the second simulation discharge data into a pre-trained defect diagnosis model to obtain a defect diagnosis result of the transformer; therefore, model parameters of the first simulation model are adjusted through field sensor data to obtain a second simulation model, second simulation discharge data output by the second simulation model are closer to a field actual state, subsequent defect diagnosis of the transformer is more accurate, various defects of the transformer are diagnosed through the second simulation discharge data and field heterogeneous data, the defects of the transformer are accurately identified under the condition that characteristic data quantity is small, and defect identification speed is improved.
Drawings
FIG. 1 is a diagram illustrating an exemplary embodiment of a transformer fault diagnosis method;
FIG. 2 is a schematic flow chart illustrating a method for diagnosing defects in a transformer according to an embodiment;
FIG. 3 is a flow diagram of a method for obtaining simulated discharge signature data in one embodiment;
FIG. 4 is a schematic diagram of a transformer fault diagnosis system according to an embodiment;
FIG. 5 is a flow chart illustrating a defect diagnosis of a transformer according to an embodiment;
FIG. 6 is a flow diagram for encapsulating heterogeneous data in one embodiment;
FIG. 7 is a schematic flow chart of a method for diagnosing transformer defects according to another embodiment;
fig. 8 is a block diagram showing a structure of a defect diagnosis apparatus for a transformer according to an embodiment;
FIG. 9 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The transformer defect diagnosis method based on the heterogeneous data provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The server 104 acquires a first simulation model for simulating the discharge of the transformer; the first simulation model is used for outputting first simulation discharge data of the transformer; the server 104 acquires field sensor data of the transformer, and adjusts model parameters of the first simulation model according to the first simulation discharge data and the field sensor data to obtain a second simulation model; the second simulation model is used for outputting second simulation discharge data of the transformer; the correlation degree of the second simulation discharge data and the field sensor data is greater than that of the first simulation discharge data and the field sensor data; the server 104 obtains the field heterogeneous data of the transformer, and inputs the field heterogeneous data and the second simulation discharge data into the pre-trained defect diagnosis model to obtain the defect diagnosis result of the transformer. The server 104 transmits the diagnosis result of the defect of the transformer to the terminal 102. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart car-mounted devices, and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 104 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.
In one embodiment, as shown in fig. 2, a transformer defect diagnosis method based on heterogeneous data is provided, which is described by taking the method as an example applied to the server 104 in fig. 1, and includes the following steps:
step S202, a first simulation model for simulating the discharge of the transformer is obtained; the first simulation model is used for outputting first simulation discharge data of the transformer.
The first simulation model can be a simulation model used for simulating partial discharge characteristics of the transformer in the power system, and the first simulation model can output theoretical partial discharge characteristic data.
The first simulation discharge data can be partial discharge characteristic data such as high-frequency current, ultrahigh frequency and ultrasonic time domain waveform.
In specific implementation, the server obtains a discharge characteristic simulation model for simulating the discharge of the transformer, and outputs initial partial discharge characteristic data through the discharge characteristic simulation model.
For example, the server can obtain a time domain model, a frequency domain model, a typical structure model (including 35kV, 110kV, 220kV, 500kV and 1100 kV) of the transformer and a three-dimensional construction model simulating the discharge characteristic data of the transformer.
Step S204, acquiring field sensor data of the transformer, and adjusting model parameters of the first simulation model according to the first simulation discharge data and the field sensor data to obtain a second simulation model; the second simulation model is used for outputting second simulation discharge data of the transformer; the degree of correlation of the second simulated discharge data with the field sensor data is greater than the degree of correlation of the first simulated discharge data with the field sensor data.
The field sensor data may be data received from a plurality of channel sensors disposed near a transformer in the power system.
Wherein the second simulation model may be a simulation model having a more accurate simulation of the partial discharge characteristics than the first simulation model.
Wherein the second simulated discharge data may be partial discharge characteristic data such as high frequency current, ultrahigh frequency, and ultrasonic time domain waveform similar to the first simulated discharge data.
The degree of correlation may be information for characterizing the degree of similarity or dissimilarity between data factors, among others.
In the concrete implementation, the server acquires sensor data of a plurality of channels of the transformer and encapsulates the sensor data into a data matrix, the server performs grey correlation analysis on the data matrix and first simulated discharge data output by the first simulation model, and when the grey correlation degree of the data matrix and the first simulated discharge data is smaller than a preset threshold, the server adjusts model parameters of the first simulated discharge model until the grey correlation degree of the first simulated discharge data output by the first simulation model and the data matrix reaches the preset threshold, and the server takes the first simulated discharge data as final discharge characteristic data.
For example, the server encapsulates the field N channel sensor data into a data matrix of N rows and M columns, where M represents the data length of each channel sensor data. And the server performs grey correlation analysis on the data result output by the simulation discharge model for simulating the discharge characteristics of the transformer and the data matrix, judges whether the grey correlation degree of the simulation discharge model and the data matrix reaches 85% or more, and adjusts and optimizes the simulation discharge model parameters when the grey correlation degree does not reach 85% until the grey correlation degree of the simulation discharge model and the data matrix reaches 85%.
To facilitate understanding by those skilled in the art, fig. 3 illustratively provides a flow chart of a method of obtaining more accurate simulated discharge signature data. The server obtains a first simulation model through the modeling analysis module 302, obtains field sensor data through the data interface module 304, and performs iterative analysis on the first simulation discharge data output by the first simulation model and the field sensor data through the iterative optimization module 306, wherein the iterative analysis is gray correlation analysis performed through the gray correlation analysis module 308, wherein when the gray correlation degree of the first simulation discharge data and the field sensor data is greater than 85%, iteration is stopped, and the first simulation discharge data output finally is used as second simulation discharge data.
Step S206, acquiring field heterogeneous data of the transformer, and inputting the field heterogeneous data and the second simulation discharge data into a pre-trained defect diagnosis model to obtain a defect diagnosis result; the defect diagnosis result is used for determining defect information of the transformer.
The site heterogeneous data can be site text data and site image data of the position of the transformer in the power system.
The defect diagnosis model can be used for determining whether the characteristic data such as load condition, oil temperature, winding temperature, vibration characteristics, partial discharge signals, central point grounding current, iron core grounding current and dissolved gas exist in the transformer operation process are abnormal or not.
In specific implementation, the server acquires field heterogeneous data of the transformer, such as picture data and text data, and inputs the field heterogeneous data and the second simulated discharge data into the pre-trained defect diagnosis model to obtain a defect diagnosis result of the transformer.
To facilitate understanding of those skilled in the art, fig. 4 exemplarily provides a structural diagram of a transformer defect diagnosis system based on small sample heterogeneous data. The transformer defect diagnosis system 402 is composed of a mechanism analysis module 404, a heterogeneous data interface module 406 and a small sample defect diagnosis model 408. In practical application, the mechanism analysis module 404 obtains simulated discharge data, the heterogeneous data interface module 406 obtains field heterogeneous data, and the small sample defect diagnosis module 408 performs defect diagnosis on the simulated discharge data and the field heterogeneous data to obtain a defect diagnosis result.
The transformer defect diagnosis method and device based on heterogeneous data, the computer equipment, the storage medium and the computer program product are used for acquiring a first simulation model for simulating transformer discharge; the first simulation model is used for outputting first simulation discharge data of the transformer; acquiring field sensor data of the transformer, and adjusting model parameters of the first simulation model according to the first simulation discharge data and the field sensor data to obtain a second simulation model; acquiring field heterogeneous data of the transformer, and inputting the field heterogeneous data and the second simulation discharge data into a pre-trained defect diagnosis model to obtain a defect diagnosis result of the transformer; therefore, model parameters of the first simulation model are adjusted through field sensor data to obtain a second simulation model, second simulation discharge data output by the second simulation model are closer to a field actual state, subsequent defect diagnosis of the transformer is more accurate, various defects of the transformer are diagnosed through the second simulation discharge data and field heterogeneous data, the defects of the transformer are accurately identified under the condition that characteristic data quantity is small, and defect identification speed is improved.
In another embodiment, adjusting model parameters of the first simulation model according to the first simulation discharge data and the field sensor data to obtain a second simulation model, includes: performing grey correlation analysis on the first simulation discharge data and the field sensor data to obtain a grey correlation analysis result; the grey correlation analysis result represents the correlation degree between the first simulation discharge data and the field sensor data; under the condition that the value represented by the gray correlation analysis result is smaller than or equal to a preset threshold value, adjusting model parameters of the first simulation model, and returning to the step of performing gray correlation analysis on the first simulation discharge data and the field sensor data until the value represented by the gray correlation analysis result is larger than the preset threshold value; and taking the first simulation model after the parameters are adjusted as a second simulation model.
In the concrete implementation, the server performs grey correlation analysis on the first simulation discharge data and the field sensor data to obtain a grey correlation analysis result, and under the condition that the grey correlation analysis result is smaller than or equal to a preset threshold, the server adjusts the model parameters of the first simulation model until the grey correlation degree between the first simulation discharge data output by the first simulation model and the field sensor data reaches the preset threshold, and then the server takes the first simulation model reaching the preset threshold as the second simulation model.
According to the technical scheme, the gray correlation analysis is carried out on the first simulation discharge data and the field sensor data output by the first simulation model, and the model parameters of the first simulation model are adjusted according to the gray correlation analysis result, so that the second simulation model is obtained, the discharge characteristic data closer to the field actual condition of the transformer can be output, and the accurate identification of the transformer defects in the follow-up process is facilitated.
In another embodiment, inputting the on-site heterogeneous data and the second simulated discharge data into a pre-trained defect diagnosis model to obtain a defect diagnosis result, including: classifying the field heterogeneous data and the second simulation discharge data to obtain a plurality of characteristic data frames corresponding to the transformer in operation; each characteristic data frame has different operation data types; the operation data type comprises at least one of load condition, oil temperature, winding temperature, vibration characteristics, partial discharge signals, center point grounding current, iron core grounding current and dissolved gas in oil, which are related to the transformer; and inputting the characteristic data frames corresponding to the operation data types into corresponding pre-trained defect diagnosis models to obtain defect diagnosis results.
Wherein the oil temperature may be the temperature of the oil at the top layer of the transformer.
Wherein the winding temperature may be a temperature of a transformer winding.
The vibration characteristics may be characteristics generated by vibration of a winding and a core of the transformer, among others.
The partial discharge signal may refer to a discharge signal generated by discharging the transformer.
The center point grounding current may be a current flowing into the ground by the transformer to achieve an operation requirement state.
The core grounding current may be a current flowing into the ground to ensure safety when the transformer fails.
The gas dissolved in the oil may be gas dissolved in the oil in a molecular state inside the transformer.
In the specific implementation, the server classifies the field heterogeneous data and the second simulated discharge data, classifies the field heterogeneous data and the second simulated discharge data according to load conditions, oil temperature, winding temperature, vibration characteristics, local discharge signals, center point grounding current, iron core grounding current and gas dissolved in oil, inputs load operation data into a pre-trained defect diagnosis model for determining abnormal load information, inputs oil temperature operation data into a pre-trained defect diagnosis model for determining abnormal oil temperature information, inputs winding temperature operation data into a pre-trained defect diagnosis model for determining abnormal winding temperature information, inputs vibration characteristic operation data into a pre-trained defect diagnosis model for determining abnormal vibration characteristic information, inputs local discharge signal operation data into a pre-trained defect diagnosis model for determining abnormal local discharge signal information, inputs center point grounding current operation data into a pre-trained defect diagnosis model for determining abnormal center point grounding current information, inputs iron core grounding current operation data into a pre-trained defect diagnosis model for determining abnormal iron core grounding current information, and inputs gas dissolved in oil into a pre-trained defect diagnosis model for determining abnormal oil information, and obtains the corresponding characteristic diagnosis results of the defect diagnosis models.
According to the technical scheme of the embodiment, the field heterogeneous data and the second simulation discharge data are subjected to framing processing to obtain a plurality of characteristic data frames corresponding to the transformer in operation, the operation data corresponding to each characteristic data frame is input into a pre-trained defect diagnosis model to obtain a defect diagnosis result corresponding to each characteristic data frame, and the defects of the transformer are determined from multiple aspects of load conditions, oil temperatures, winding temperatures, vibration characteristics, partial discharge signals, center point grounding currents, iron core grounding currents and dissolved gases in oil, so that the defect condition of the transformer can be accurately determined, and the accuracy of transformer defect diagnosis is improved.
In another embodiment, inputting the feature data frame corresponding to each operation data type into a corresponding pre-trained defect diagnosis model to obtain a defect diagnosis result, including: converting each pre-trained defect diagnosis model from a floating point number structure model into a fixed point number structure model to obtain a quantized defect diagnosis model; and inputting the characteristic data frame corresponding to each operation data type into the corresponding quantized defect diagnosis model to obtain a defect diagnosis result of the transformer.
The defect diagnosis model after quantization can be a fixed point number result model for determining the defects of the transformer.
The defect diagnosis result may be a result indicating an internal defect condition of the transformer, for example, the defect diagnosis result may be an operation defect indicating that the winding inside the transformer is overheated, the winding is loose and deformed, the insulation defect between turns and between cakes, the casing defect, and the like.
The method comprises the steps that a server converts each pre-trained defect diagnosis model from a floating point number structure model into a fixed point number structure model to obtain a quantized defect diagnosis model, the server inputs load operation data into the quantized defect diagnosis model for determining abnormal load information, inputs oil temperature operation data into the quantized defect diagnosis model for determining abnormal oil temperature information, inputs winding temperature operation data into the quantized defect diagnosis model for determining abnormal winding temperature information, inputs vibration characteristic operation data into the quantized defect diagnosis model for determining abnormal vibration characteristic information, inputs local discharge signal operation data into the quantized defect diagnosis model for determining abnormal local discharge signal information, inputs central point grounding current operation data into the quantized defect diagnosis model for determining abnormal central point grounding current information, inputs iron core grounding current operation data into the quantized defect diagnosis model for determining abnormal iron core grounding current information, inputs dissolved gas operation data into the quantized defect diagnosis model for determining abnormal oil dissolved gas information, and determines a defect diagnosis result of a transformer winding, namely whether defects such as overheating, inter-turn insulation defects, loosening and the like exist in the transformer.
According to the technical scheme, each pre-trained defect diagnosis model is converted from a floating point number structure model to a fixed point number structure model, so that a quantized defect diagnosis model is obtained, and compared with an original defect diagnosis model, the quantized defect diagnosis model has higher data operation speed, can process the characteristic data frame corresponding to each operation data type more quickly, and is beneficial to quickly identifying the defects of the transformer.
In another embodiment, the method is applied to a computer device, the computer device runs at least two acceleration networks established by an FPGA in parallel, and the characteristic data frames corresponding to each running data type are input to a corresponding pre-trained defect diagnosis model to obtain a defect diagnosis result, and the method includes: inputting the characteristic data frame corresponding to each operation data type into a corresponding acceleration network to obtain a defect diagnosis result returned by the acceleration network; the acceleration network is used for converting the corresponding pre-trained defect diagnosis model from a floating point number structure model to a fixed point number structure model to obtain a quantized defect diagnosis model; and inputting the corresponding characteristic data frame into the quantized defect diagnosis model to obtain a corresponding defect diagnosis result.
The FPGA is a field programmable gate array, i.e. a semiconductor device with editable elements, and is a logic gate array element for field programming by a user.
Wherein the acceleration network may be an LSTM recurrent neural network. The acceleration network may convert the defect diagnosis model of the 32-bit floating-point number structure to a defect diagnosis model of the 12-bit fixed-point number structure.
In the specific implementation, the server establishes a plurality of LSTM accelerated neural networks through the FPGA, wherein each LSTM accelerated neural network is responsible for processing a characteristic data frame, the LSTM accelerated neural network can convert a pre-trained defect diagnosis model from a floating point structure model into a fixed point structure model to obtain a quantized defect diagnosis model, and the server inputs each characteristic data frame into the quantized defect diagnosis model in the corresponding LSTM accelerated neural network respectively to obtain a corresponding defect diagnosis result.
To facilitate understanding by those skilled in the art, fig. 5 exemplarily provides a defect diagnosis flowchart of the transformer. The read characteristic data frames are written into a high-speed memory of the diagnosis and analysis unit 504 through the database writing unit 502, and then defect diagnosis is performed on the characteristic data frames through the FPGA-LSTM acceleration network 506, so that a defect diagnosis result is obtained.
According to the technical scheme of the embodiment, the defect results returned by the acceleration network are obtained by inputting the characteristic data frames corresponding to the operation data types into the corresponding acceleration network, wherein the FPGA is utilized to construct a plurality of parallel operation units, and the characteristic data frames are input into the acceleration network in the corresponding parallel operation units, so that the data operation process is realized through hardware, and the defect diagnosis speed of the transformer can be improved.
In another embodiment, acquiring in-situ sensor data for a transformer includes: acquiring sensor data corresponding to the transformer; the sensor data is data read by a plurality of sensors arranged at the positions of the power system of the transformer; the data of each sensor adopts the same preset data structure; and packaging the sensor data to obtain field sensor data.
Wherein each sensor data may be sensor raw waveform data having the same data type.
In the specific implementation, the server acquires original waveform data of a plurality of channel sensors near a transformer in the power system, and then encapsulates the original waveform data of the plurality of channel sensors to obtain field sensor data.
According to the technical scheme, the data of the sensors arranged around the position of the power system of the transformer are obtained, and the data of the sensors are packaged to obtain the data of the field sensors, so that the subsequent acquisition of the discharge characteristic data closer to the actual situation of the field is facilitated, and the accuracy of defect diagnosis of the transformer is improved.
In another embodiment, obtaining field heterogeneous data of a transformer comprises: collecting heterogeneous data of a transformer at the position of a power system; the heterogeneous data comprises at least one of site monitoring texts, pictures and waveforms; and according to the acquisition time and the sampling rate corresponding to the heterogeneous data, packaging the heterogeneous data to obtain the on-site heterogeneous data.
The heterogeneous data refers to data in different data formats, for example, the picture data and the text data have different data formats, and the picture data and the text data may be referred to as heterogeneous data.
The acquisition time can be the time point of data acquisition, each acquired time point corresponds to an M-dimensional data vector, and when the number of the acquisition time points is L, heterogeneous data is packaged into an L-row M-column matrix.
In the specific implementation, the server acquires heterogeneous data such as text data, image data and waveform data of a transformer at the position of a power system, encapsulates the heterogeneous data into a data matrix, and adds acquisition time and sampling rate of various heterogeneous data after the encapsulated data packet, so as to obtain on-site heterogeneous data.
To facilitate understanding by those skilled in the art, fig. 6 illustratively provides a flow chart for encapsulating heterogeneous data. The field heterogeneous data is read through a heterogeneous data interface 602 (corresponding to the heterogeneous data interface module 406 in fig. 4), the field heterogeneous data is cached in a cache space 604 with the size of 10G, the cached heterogeneous data (including field text data, field picture data, field report and other field heterogeneous data of a transformer at the position of an electric power system) is packaged into a uniform M-row and L-column data matrix through a data matrix packaging module 606 according to the acquisition time L, various types of field heterogeneous data are packaged into a uniform-format data packet, and acquisition duration information and sampling rate information of various types of field heterogeneous data are added after the data packet, so that data packaging of the field heterogeneous data is completed.
According to the technical scheme, the heterogeneous data of the transformer at the position of the power system are collected and packaged to obtain the field heterogeneous data, so that various characteristic data generated by different types of defects of the transformer can be obtained, the defect condition of the transformer can be accurately determined, and defect identification of the transformer is facilitated.
In another embodiment, as shown in fig. 7, a transformer defect diagnosis method based on heterogeneous data is provided, which is described by taking the method as an example applied to the server 104 in fig. 1, and includes the following steps:
step S702, acquiring a first simulation model for simulating the discharge of the transformer; the first simulation model is used for outputting first simulation discharge data of the transformer.
Step S704, acquiring field sensor data of the transformer, and adjusting model parameters of the first simulation model according to the first simulation discharge data and the field sensor data to obtain a second simulation model; the second simulation model is used for outputting second simulation discharge data of the transformer; the degree of correlation of the second simulated discharge data with the field sensor data is greater than the degree of correlation of the first simulated discharge data with the field sensor data.
Step S706, acquiring field heterogeneous data of the transformer, and classifying the field heterogeneous data and the second simulation discharge data to obtain a plurality of corresponding characteristic data frames when the transformer operates; each characteristic data frame has different operation data types; the operation data type comprises at least one of load condition, oil temperature, winding temperature, vibration characteristics, partial discharge signal, center point grounding current, iron core grounding current and dissolved gas in oil associated with the transformer.
It should be noted that, the specific limitations of the above steps can be referred to the above specific limitations of a transformer defect diagnosis method based on heterogeneous data.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the application also provides a transformer defect diagnosis device based on heterogeneous data, which is used for realizing the transformer defect diagnosis method based on heterogeneous data. The implementation scheme for solving the problem provided by the apparatus is similar to the implementation scheme described in the method, so specific limitations in one or more transformer defect diagnosis apparatus embodiments based on heterogeneous data provided below may refer to the limitations in the transformer defect diagnosis method based on heterogeneous data, and are not described herein again.
In one embodiment, as shown in fig. 8, there is provided a transformer defect diagnosis apparatus based on heterogeneous data, including:
an obtaining module 802, configured to obtain a first simulation model for simulating transformer discharge; the first simulation model is used for outputting first simulation discharge data of the transformer;
the adjusting module 804 is used for acquiring field sensor data of the transformer, and adjusting model parameters of the first simulation model according to the first simulation discharge data and the field sensor data to obtain a second simulation model; the second simulation model is used for outputting second simulation discharge data of the transformer; the correlation degree of the second simulation discharge data and the field sensor data is greater than that of the first simulation discharge data and the field sensor data;
the diagnosis module 806 is configured to obtain field heterogeneous data of the transformer, and input the field heterogeneous data and the second simulation discharge data to the pre-trained defect diagnosis model to obtain a defect diagnosis result of the transformer.
In one embodiment, the model parameters of the first simulation model are adjusted according to the first simulation discharge data and the field sensor data to obtain a second simulation model, and the adjusting module 804 is specifically configured to perform gray correlation analysis on the first simulation discharge data and the field sensor data to obtain a gray correlation analysis result; the grey correlation analysis result represents the correlation degree between the first simulation discharge data and the field sensor data; under the condition that the value represented by the grey correlation analysis result is smaller than or equal to a preset threshold value, adjusting model parameters of the first simulation model, and returning to the step of carrying out grey correlation analysis on the first simulation discharge data and the field sensor data until the value represented by the grey correlation analysis result is larger than the preset threshold value; and taking the first simulation model after the parameters are adjusted as a second simulation model.
In one embodiment, the on-site heterogeneous data and the second simulation discharge data are input to a pre-trained defect diagnosis model to obtain a defect diagnosis result, and the diagnosis module 806 is specifically configured to classify the on-site heterogeneous data and the second simulation discharge data to obtain a plurality of feature data frames corresponding to the transformer during operation; each characteristic data frame has different operation data types; the operation data type comprises at least one of load condition, oil temperature, winding temperature, vibration characteristics, partial discharge signals, central point grounding current, iron core grounding current and dissolved gas in oil, which are associated with the transformer; and inputting the characteristic data frames corresponding to the operation data types into corresponding pre-trained defect diagnosis models to obtain defect diagnosis results.
In one embodiment, the characteristic data frame corresponding to each operation data type is input to a corresponding pre-trained defect diagnosis model to obtain a defect diagnosis result, and the diagnosis module 806 is specifically configured to convert each pre-trained defect diagnosis model from a floating point structure model to a fixed point structure model to obtain a quantized defect diagnosis model; and inputting the characteristic data frames corresponding to the operation data types into the corresponding quantized defect diagnosis model to obtain the defect diagnosis result of the transformer.
In one embodiment, the method is applied to a computer device, the computer device runs in parallel with at least two acceleration networks established by an FPGA, and the feature data frames corresponding to each running data type are input to the corresponding pre-trained defect diagnosis model to obtain a defect diagnosis result, and the diagnosis module 806 is specifically configured to input the feature data frames corresponding to each running data type to the corresponding acceleration network to obtain a defect diagnosis result returned by the acceleration network; the acceleration network is used for converting the corresponding pre-trained defect diagnosis model from a floating point number structure model to a fixed point number structure model to obtain a quantized defect diagnosis model; and inputting the corresponding characteristic data frame into the quantized defect diagnosis model to obtain a corresponding defect diagnosis result.
In one embodiment, the field sensor data of the transformer is obtained, and the adjusting module 804 is specifically configured to obtain sensor data corresponding to the transformer; the sensor data is data read by a plurality of sensors arranged at the positions of the power system of the transformer; the data of each sensor adopts the same preset data structure; and packaging the sensor data to obtain field sensor data.
In one embodiment, the field heterogeneous data of the transformer is obtained, and the diagnosis module 806 is specifically configured to collect the heterogeneous data of the transformer at the location of the power system; the heterogeneous data comprises at least one of site monitoring texts, pictures and waveforms; and according to the acquisition time and the sampling rate corresponding to the heterogeneous data, packaging the heterogeneous data to obtain the on-site heterogeneous data.
The modules in the transformer defect diagnosis device based on heterogeneous data can be wholly or partially realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing transformer defect diagnosis data based on heterogeneous data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a transformer defect diagnosis method based on heterogeneous data.
It will be appreciated by those skilled in the art that the configuration shown in fig. 9 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, the computer program, when executed by the processor, causing the processor to perform the steps of the above-mentioned transformer defect diagnosis method based on heterogeneous data. Here, the steps of a transformer defect diagnosis method based on heterogeneous data may be steps in a transformer defect diagnosis method based on heterogeneous data according to the above embodiments.
In one embodiment, a computer readable storage medium is provided, which stores a computer program, which when executed by a processor causes the processor to perform the steps of the above-mentioned transformer defect diagnosis method based on heterogeneous data. Here, the steps of a transformer defect diagnosis method based on heterogeneous data may be steps in a transformer defect diagnosis method based on heterogeneous data according to the above embodiments.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, causes the processor to perform the steps of a method for transformer defect diagnosis based on heterogeneous data as described above. Here, the steps of a transformer defect diagnosis method based on heterogeneous data may be steps in a transformer defect diagnosis method based on heterogeneous data according to the above embodiments.
It should be noted that, the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), magnetic Random Access Memory (MRAM), ferroelectric Random Access Memory (FRAM), phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases involved in the embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A transformer defect diagnosis method based on heterogeneous data is characterized by comprising the following steps:
acquiring a first simulation model for simulating the discharge of the transformer; the first simulation model is used for outputting first simulation discharge data of the transformer;
acquiring field sensor data of the transformer, and adjusting model parameters of the first simulation model according to the first simulation discharge data and the field sensor data to obtain a second simulation model; the second simulation model is used for outputting second simulation discharge data of the transformer; the degree of correlation between the second simulated discharge data and the field sensor data is greater than the degree of correlation between the first simulated discharge data and the field sensor data;
and acquiring field heterogeneous data of the transformer, and inputting the field heterogeneous data and the second simulation discharge data into a pre-trained defect diagnosis model to obtain a defect diagnosis result of the transformer.
2. The method of claim 1, wherein said adjusting model parameters of said first simulation model based on said first simulated discharge data and said in-situ sensor data to obtain a second simulation model comprises:
performing grey correlation analysis on the first simulation discharge data and the field sensor data to obtain a grey correlation analysis result; the grey correlation analysis result represents the correlation degree between the first simulation discharge data and the field sensor data;
adjusting model parameters of the first simulation model under the condition that the value represented by the grey correlation analysis result is smaller than or equal to a preset threshold value, and returning to the step of performing grey correlation analysis on the first simulation discharge data and the field sensor data until the value represented by the grey correlation analysis result is larger than the preset threshold value;
and taking the first simulation model after the parameters are adjusted as a second simulation model.
3. The method of claim 1, wherein inputting the on-site heterogeneous data and the second simulated discharge data to a pre-trained defect diagnosis model to obtain a defect diagnosis result comprises:
classifying the field heterogeneous data and the second simulation discharge data to obtain a plurality of corresponding characteristic data frames when the transformer operates; each of the characteristic data frames has a different operational data type; the operation data type comprises at least one of load condition, oil temperature, winding temperature, vibration characteristics, partial discharge signals, center point grounding current, iron core grounding current and dissolved gas in oil, which are related to the transformer;
and inputting the characteristic data frame corresponding to each operation data type into the corresponding pre-trained defect diagnosis model to obtain the defect diagnosis result.
4. The method of claim 3, wherein inputting the feature data frames corresponding to each of the operation data types into the corresponding pre-trained defect diagnosis model to obtain the defect diagnosis result comprises:
converting each pre-trained defect diagnosis model from a floating point number structure model into a fixed point number structure model to obtain a quantized defect diagnosis model;
and inputting the characteristic data frame corresponding to each operation data type into the corresponding quantized defect diagnosis model to obtain a defect diagnosis result of the transformer.
5. The method according to claim 3, applied to a computer device, wherein the computer device runs at least two acceleration networks established by an FPGA in parallel, and the step of inputting the feature data frame corresponding to each running data type into the corresponding pre-trained defect diagnosis model to obtain the defect diagnosis result comprises:
inputting the characteristic data frame corresponding to each operation data type into the corresponding acceleration network to obtain the defect diagnosis result returned by the acceleration network;
the acceleration network is used for converting the corresponding pre-trained defect diagnosis model from a floating point number structure model to a fixed point number structure model to obtain the quantized defect diagnosis model; and inputting the corresponding characteristic data frame into the quantized defect diagnosis model to obtain a corresponding defect diagnosis result.
6. The method of claim 1, wherein said obtaining field sensor data for the transformer comprises:
acquiring sensor data corresponding to the transformer; the sensor data is data read by a plurality of sensors arranged at the position of the power system of the transformer; the data of each sensor adopts the same preset data structure;
and packaging the sensor data to obtain the field sensor data.
7. The method of claim 1, wherein the obtaining field heterogeneous data of the transformer comprises:
collecting heterogeneous data of the transformer at the position of the power system; the heterogeneous data comprises at least one of site monitoring texts, pictures and waveforms;
and according to the acquisition time and the sampling rate corresponding to the heterogeneous data, packaging the heterogeneous data to obtain the on-site heterogeneous data.
8. A transformer defect diagnosis apparatus based on heterogeneous data, the apparatus comprising:
the acquisition module is used for acquiring a first simulation model for simulating the discharge of the transformer; the first simulation model is used for outputting first simulation discharge data of the transformer;
the adjusting module is used for acquiring field sensor data of the transformer, and adjusting model parameters of the first simulation model according to the first simulation discharge data and the field sensor data to obtain a second simulation model; the second simulation model is used for outputting second simulation discharge data of the transformer; the degree of correlation between the second simulated discharge data and the field sensor data is greater than the degree of correlation between the first simulated discharge data and the field sensor data;
and the diagnosis module is used for acquiring the field heterogeneous data of the transformer, and inputting the field heterogeneous data and the second simulation discharge data into a pre-trained defect diagnosis model to obtain a defect diagnosis result of the transformer.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211687682.9A CN115656747A (en) | 2022-12-26 | 2022-12-26 | Transformer defect diagnosis method and device based on heterogeneous data and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211687682.9A CN115656747A (en) | 2022-12-26 | 2022-12-26 | Transformer defect diagnosis method and device based on heterogeneous data and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115656747A true CN115656747A (en) | 2023-01-31 |
Family
ID=85022914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211687682.9A Pending CN115656747A (en) | 2022-12-26 | 2022-12-26 | Transformer defect diagnosis method and device based on heterogeneous data and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115656747A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116342952A (en) * | 2023-03-29 | 2023-06-27 | 北京西清能源科技有限公司 | Transformer bushing abnormality identification method and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111695249A (en) * | 2020-05-29 | 2020-09-22 | 广东省特种设备检测研究院顺德检测院 | Prediction method for heat efficiency of gas-fired boiler |
| CN212207527U (en) * | 2020-03-17 | 2020-12-22 | 西南石油大学 | Transformer on-line monitoring device based on multi-source information fusion |
| CN112162847A (en) * | 2020-08-19 | 2021-01-01 | 中国电力科学研究院有限公司 | Power transformer state sensing and evaluating system and method |
| CN113228056A (en) * | 2019-10-12 | 2021-08-06 | 深圳鲲云信息科技有限公司 | Runtime hardware simulation method, device, equipment and storage medium |
| CN114035013A (en) * | 2021-10-19 | 2022-02-11 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Defect diagnosis method and defect diagnosis device |
| CN114047388A (en) * | 2021-11-05 | 2022-02-15 | 中山市德马汽车零部件有限公司 | Hybrid test optimization method and device for automobile electronic conduction radiation |
| CN114612996A (en) * | 2022-03-31 | 2022-06-10 | 安谋科技（中国）有限公司 | Method for operating neural network model, medium, program product, and electronic device |
| CN114676585A (en) * | 2022-04-08 | 2022-06-28 | 南方电网科学研究院有限责任公司 | Method and device for optimizing control protection real-time digital simulation model of new energy unit |
| CN115327270A (en) * | 2022-08-11 | 2022-11-11 | 宁波力斗智能技术有限公司 | Transformer small sample fault diagnosis system based on data-model driving |
-
2022
- 2022-12-26 CN CN202211687682.9A patent/CN115656747A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113228056A (en) * | 2019-10-12 | 2021-08-06 | 深圳鲲云信息科技有限公司 | Runtime hardware simulation method, device, equipment and storage medium |
| CN212207527U (en) * | 2020-03-17 | 2020-12-22 | 西南石油大学 | Transformer on-line monitoring device based on multi-source information fusion |
| CN111695249A (en) * | 2020-05-29 | 2020-09-22 | 广东省特种设备检测研究院顺德检测院 | Prediction method for heat efficiency of gas-fired boiler |
| CN112162847A (en) * | 2020-08-19 | 2021-01-01 | 中国电力科学研究院有限公司 | Power transformer state sensing and evaluating system and method |
| CN114035013A (en) * | 2021-10-19 | 2022-02-11 | 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） | Defect diagnosis method and defect diagnosis device |
| CN114047388A (en) * | 2021-11-05 | 2022-02-15 | 中山市德马汽车零部件有限公司 | Hybrid test optimization method and device for automobile electronic conduction radiation |
| CN114612996A (en) * | 2022-03-31 | 2022-06-10 | 安谋科技（中国）有限公司 | Method for operating neural network model, medium, program product, and electronic device |
| CN114676585A (en) * | 2022-04-08 | 2022-06-28 | 南方电网科学研究院有限责任公司 | Method and device for optimizing control protection real-time digital simulation model of new energy unit |
| CN115327270A (en) * | 2022-08-11 | 2022-11-11 | 宁波力斗智能技术有限公司 | Transformer small sample fault diagnosis system based on data-model driving |
Non-Patent Citations (1)
| Title |
|---|
| 鲍劲松 等, 华中科学技术大学出版社 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116342952A (en) * | 2023-03-29 | 2023-06-27 | 北京西清能源科技有限公司 | Transformer bushing abnormality identification method and system |
| CN116342952B (en) * | 2023-03-29 | 2024-01-23 | 北京西清能源科技有限公司 | Transformer bushing abnormality identification method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109032829B (en) | Data anomaly detection method and device, computer equipment and storage medium | |
| JP2023501030A (en) | Engine surge failure prediction system and method based on fusion neural network model | |
| CN112818035B (en) | Network fault prediction method, terminal equipment and storage medium | |
| CN111325159B (en) | Fault diagnosis method, device, computer equipment and storage medium | |
| CN116453056A (en) | Target detection model construction method and transformer substation foreign matter intrusion detection method | |
| CN115656747A (en) | Transformer defect diagnosis method and device based on heterogeneous data and computer equipment | |
| US20240255396A1 (en) | Product Reliability Evaluation Method And Apparatus Based On Multi-Stress Coupling Acceleration Model | |
| WO2023226355A1 (en) | Dual-ion battery fault detection method and system based on multi-source perception | |
| CN114325405A (en) | Battery pack consistency analysis method, modeling method, device, equipment and medium | |
| CN111898247A (en) | Landslide displacement prediction method, equipment and storage medium | |
| CN116757062A (en) | Power load frequency characteristic analysis method, device, equipment and storage medium | |
| CN115841046A (en) | Accelerated degradation test data processing method and device based on wiener process | |
| CN114445336A (en) | Distribution equipment defect detection method and device, computer equipment and storage medium | |
| Zou et al. | Double convolutional neural network for fault identification of power distribution network | |
| CN117633592B (en) | Intelligent monitoring disc system of new energy power station | |
| Srikanth et al. | A novel three-dimensional deep learning algorithm for classification of power system faults | |
| CN116885717B (en) | Multistage topology analysis method for power system | |
| CN117332330A (en) | Transformer fault evaluation method and system based on multi-source data graph fusion model | |
| CN111859802A (en) | Method, system and equipment for calculating steady-state temperature of overhead conductor | |
| CN115439721B (en) | Method and device for training classification model of power equipment with few abnormal samples | |
| CN116415510B (en) | Breaker temperature rise prediction method and system based on phase space reconstruction and neural network | |
| CN115422851B (en) | Power system element model calibration method, device, equipment and storage medium | |
| CN115629253A (en) | Transformer insulating sleeve fault diagnosis method and device and computer equipment | |
| CN117009848A (en) | Equipment testing method and device, storage medium and electronic equipment | |
| CN118608867A (en) | Defect identification method, device, equipment and storage medium of power transmission 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230131 |
|
| RJ01 | Rejection of invention patent application after publication |