CN115327286A - Transformer monitoring method and system applied to power station - Google Patents
Transformer monitoring method and system applied to power station Download PDFInfo
- Publication number
- CN115327286A CN115327286A CN202211264006.0A CN202211264006A CN115327286A CN 115327286 A CN115327286 A CN 115327286A CN 202211264006 A CN202211264006 A CN 202211264006A CN 115327286 A CN115327286 A CN 115327286A
- Authority
- CN
- China
- Prior art keywords
- transformer
- data
- analysis model
- state
- data set
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012544 monitoring process Methods 0.000 title claims abstract description 43
- 238000004458 analytical method Methods 0.000 claims abstract description 106
- 238000012549 training Methods 0.000 claims abstract description 28
- 238000013528 artificial neural network Methods 0.000 claims abstract description 23
- 238000012360 testing method Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 13
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 6
- 238000013461 design Methods 0.000 claims description 6
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 3
- OTMSDBZUPAUEDD-UHFFFAOYSA-N Ethane Chemical compound CC OTMSDBZUPAUEDD-UHFFFAOYSA-N 0.000 claims description 3
- VGGSQFUCUMXWEO-UHFFFAOYSA-N Ethene Chemical compound C=C VGGSQFUCUMXWEO-UHFFFAOYSA-N 0.000 claims description 3
- 239000005977 Ethylene Substances 0.000 claims description 3
- HSFWRNGVRCDJHI-UHFFFAOYSA-N alpha-acetylene Natural products C#C HSFWRNGVRCDJHI-UHFFFAOYSA-N 0.000 claims description 3
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 3
- 239000001569 carbon dioxide Substances 0.000 claims description 3
- 229910002091 carbon monoxide Inorganic materials 0.000 claims description 3
- 125000002534 ethynyl group Chemical group [H]C#C* 0.000 claims description 3
- 229930195733 hydrocarbon Natural products 0.000 claims description 3
- 150000002430 hydrocarbons Chemical class 0.000 claims description 3
- 229910052739 hydrogen Inorganic materials 0.000 claims description 3
- 239000001257 hydrogen Substances 0.000 claims description 3
- 125000004435 hydrogen atom Chemical class [H]* 0.000 claims description 3
- 238000010248 power generation Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000004804 winding Methods 0.000 description 5
- 238000004587 chromatography analysis Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 239000004215 Carbon black (E152) Substances 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000003491 array Methods 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
- 238000007405 data analysis Methods 0.000 description 1
- 238000012407 engineering method Methods 0.000 description 1
- 238000013100 final test Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000009666 routine test Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a transformer monitoring method and system applied to a power station, and relates to the technical field of power station monitoring. The method comprises the following steps: acquiring transformer data in multiple aspects, and constructing an offline data set; constructing an initial analysis model based on a Transformer neural network structure according to the data characteristics and the state quantity of the Transformer; training the initial analysis model according to the offline data set to obtain a target fault analysis model; the method comprises the steps of collecting and importing sensor data of multiple dimensions of the transformer into a target fault analysis model in real time, carrying out transformer fault analysis through the fault analysis model, and generating a transformer state analysis result. The invention adopts a method based on a transformer neural network to mine the relevance among different characteristic dimensions, and improves the precision of transformer state monitoring.
Description
Technical Field
The invention relates to the technical field of power station monitoring, in particular to a transformer monitoring method and system applied to a power station.
Background
In the power generation link, the power transformer transmits the power generated by the power plant to the power grid, and the voltage output by the power plant is increased to meet the requirement of rated high voltage of the power transmission grid. The power transformer is the core equipment of the whole power system, if the transformer fails, the hydropower cannot be on the internet normally, and economic losses of different degrees are caused; meanwhile, the transformer fault is a main cause of power grid accidents, and if the transformer fails and is not found in time, the life and property safety of people can be endangered. The transformer is more expensive than other equipment in the power system, and once the transformer breaks down and is not processed in time, the power grid accident is possibly caused, other related equipment is affected, especially expensive electrical equipment, the service life of the equipment is shortened, and the maintenance expense of the equipment is increased. With the gradual application of advanced technologies such as communication technology, computer technology, big data processing technology, etc. in the power system, the power grid is developing towards intellectualization. The power transformer is used as an important element and a valuable asset of a power grid, and under the background of a smart power grid, higher requirements are put on health management of the power transformer, so that the transformer needs to be accurately and effectively monitored.
The current transformer monitoring schemes are mainly divided into the following:
1. judging a single-dimensional threshold value based on experience;
2. traditional feature engineering and machine learning methods represented by SVMs, boost;
3. and a time-series deep neural network represented by RNN.
The existing methods are more characterized in that a machine learning or manual mode is used for judging the importance of relative results of different dimensions, or the relation between characteristic dimensions and time is judged, the analysis of the relevance between different characteristic dimensions is lacked, and the transformer cannot be comprehensively and accurately monitored.
Disclosure of Invention
In order to overcome the above problems or at least partially solve the above problems, embodiments of the present invention provide a transformer monitoring method and system applied to a power station, which use a method based on a transform neural network to mine the correlation between different feature dimensions, so as to improve the accuracy of transformer state monitoring.
The embodiment of the invention is realized by the following steps:
in a first aspect, an embodiment of the present invention provides a transformer monitoring method applied to a power station, including the following steps:
collecting transformer data in multiple aspects, and constructing an offline data set;
constructing an initial analysis model based on a Transformer neural network structure according to the characteristics and the state quantity of the Transformer data;
training the initial analysis model according to the offline data set to obtain a target fault analysis model;
the method comprises the steps of collecting and importing sensor data of multiple dimensions of the transformer into a target fault analysis model in real time, carrying out transformer fault analysis through the fault analysis model, and generating a transformer state analysis result.
In order to solve the problems in the prior art, a targeted analysis model based on a transform neural network structure is constructed according to the characteristics and the state quantity of transformer data, the model is trained based on data in multiple aspects to obtain a fault analysis model with optimal analysis performance, the relevance between different characteristic dimensions is mined based on the fault analysis model and the real-time sensor data of multiple dimensions of the transformer, the state of the transformer is accurately analyzed, and the monitoring precision of the state of the transformer is improved.
In some embodiments of the invention according to the first aspect, the transformer data of the aspects comprises on-line monitoring data, off-line test data and design parameter data.
Based on the first aspect, in some embodiments of the present invention, the method for training the initial analysis model according to the offline data set to obtain the target fault analysis model includes the following steps:
classifying the offline data set to obtain a training data set and a testing data set;
and performing iterative training and testing on the initial analysis model based on the training data set and the testing data set until the testing result reaches the optimal solution to obtain a target fault analysis model.
Based on the first aspect, in some embodiments of the present invention, the initial analysis model based on the Transformer neural network structure includes an algorithm input layer, an encoding processing layer, and a category output layer.
Based on the first aspect, in some embodiments of the invention, the algorithm input layer comprises sensor data for a plurality of dimensions of hydrogen, carbon monoxide, carbon dioxide, methane, ethylene, ethane, acetylene, total hydrocarbons, and corresponding point location temperatures and plant operating time.
Based on the first aspect, in some embodiments of the present invention, the method for generating the transformer state analysis result by performing transformer fault analysis through the fault analysis model includes the following steps:
inputting sensor data of each dimension into a fault analysis model;
after sensor data pass through embedding, adding position information to data of each dimension by adopting a position coding algorithm based on a coding processing layer;
after adding the position information, adding category coding information to the data of each dimensionality based on a coding processing layer;
and sequentially inputting the data added with the position information and the class coding information into an encoder and a decoder, and finally outputting the data on a class output layer to obtain a transformer state analysis result.
Based on the first aspect, in some embodiments of the present invention, the category coding information includes a normal state, an early warning state, a hazard state, and value intervals corresponding to the respective states.
In a second aspect, an embodiment of the present invention provides a transformer monitoring system applied to a power station, including a data set acquisition module, a model construction module, a model training module, and a state analysis module, where:
the data set acquisition module is used for acquiring transformer data in multiple aspects and constructing an offline data set;
the model building module is used for building an initial analysis model based on a Transformer neural network structure according to the data characteristics and the state quantity of the Transformer;
the model training module is used for training the initial analysis model according to the offline data set to obtain a target fault analysis model;
and the state analysis module is used for acquiring and importing the sensor data of the transformer in multiple dimensions into a target fault analysis model in real time, and performing transformer fault analysis through the fault analysis model to generate a transformer state analysis result.
In order to solve the problems in the prior art, the system constructs a targeted analysis model based on a transform neural network structure according to the characteristics and state quantity of transformer data through the cooperation of a plurality of modules such as a data set acquisition module, a model construction module, a model training module and a state analysis module, trains the model based on data in multiple aspects to obtain a fault analysis model with optimal analysis performance, and then mines the relevance among different characteristic dimensions based on the fault analysis model and the real-time sensor data of multiple dimensions of the transformer, so that the state of the transformer is accurately analyzed, and the monitoring precision of the state of the transformer is improved.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a memory for storing one or more programs; a processor. The program or programs, when executed by a processor, implement the method of any of the first aspects as described above.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method according to any one of the first aspect described above.
The embodiment of the invention at least has the following advantages or beneficial effects:
the embodiment of the invention provides a transformer monitoring method and a transformer monitoring system applied to a power station, wherein a targeted fault analysis model based on a transform neural network structure is constructed according to the data characteristics and state quantity of a transformer, and then the relevance among different characteristic dimensions is mined by combining the real-time sensor data of multiple dimensions of the transformer based on the fault analysis model, so that the state of the transformer is accurately analyzed, and the monitoring precision of the state of the transformer is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a flowchart of a transformer monitoring method applied to a power station according to an embodiment of the present invention;
fig. 2 is a structural diagram of an initial analysis model based on a transform neural network structure in a Transformer monitoring method applied to a power station according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating an initial analysis model based on a transform neural network structure in a Transformer monitoring method for a power station according to an embodiment of the present invention;
FIG. 4 is a schematic block diagram of a transformer monitoring system applied to a power station according to an embodiment of the present invention;
fig. 5 is a block diagram of an electronic device according to an embodiment of the present invention.
Description of the reference numerals: 100. a data set acquisition module; 200. a model building module; 300. a model training module; 400. a state analysis module; 101. a memory; 102. a processor; 103. a communication interface.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
In the description of the embodiments of the present invention, "a plurality" represents at least 2.
Example (b):
as shown in fig. 1 to fig. 3, in a first aspect, an embodiment of the present invention provides a transformer monitoring method applied to a power station, including the following steps:
s1, collecting transformer data in multiple aspects, and constructing an offline data set; the transformer data of the aspects include on-line monitoring data, off-line testing data, and design parameter data. The online monitoring data comprises oil chromatogram, iron core grounding current, partial discharge, warm oil level, voltage current and the like, and the offline test data comprises data of sensors such as the oil chromatogram, insulating oil, winding capacitance and dielectric loss, direct current resistance, sleeve capacitance and dielectric loss, winding insulation resistance and the like. The on-line monitoring data also includes operational data such as voltage, current, active power, etc. The off-line test data comprises oil chromatography, insulating oil, winding capacitance and dielectric loss, direct current resistance, sleeve capacitance and dielectric loss, winding insulation resistance and the like. The design parameters include brand, model, date of manufacture, rated capacity, cooling mode, sealing mode, etc. The design parameters include brand, model, date of manufacture, rated capacity, cooling mode, sealing mode, etc.
S2, constructing an initial analysis model based on a Transformer neural network structure according to the data characteristics and the state quantity of the Transformer; the initial analysis model based on the Transformer neural network structure comprises an algorithm input layer, a coding processing layer and a category output layer. The structure of the initial analysis model based on the Transformer neural network structure is shown in fig. 2. The transformer data characteristic refers to a data characteristic of a sensor of the transformer, and is time sequence data, for example, data of an oil chromatographic sensor is once every four hours. The state quantity is an input parameter of the model and comprises online monitoring data, routine test data and design parameter data.
Further, the algorithm input layer comprises sensor data of hydrogen, carbon monoxide, carbon dioxide, methane, ethylene, ethane, acetylene, total hydrocarbon, corresponding point position temperature and multiple dimensions of equipment operation time.
S3, training the initial analysis model according to the offline data set to obtain a target fault analysis model;
further, as shown in fig. 3, the offline data set is classified to obtain a training data set and a testing data set; and performing iterative training and testing on the initial analysis model based on the training data set and the testing data set until the testing result reaches the optimal solution to obtain a target fault analysis model.
In some embodiments of the present invention, a model network structure suitable for current data is designed based on a transformers neural network model, the model is trained through labeled data, then the trained model is tested by using test data, training parameters of the model are adjusted according to a test result, and the model is retrained. And repeating iteration in the mode, finishing training when the final test result reaches an ideal state, and storing the model to be used as a target fault analysis model for real-time data analysis.
And S4, collecting and importing the sensor data of the transformer in multiple dimensions into a target fault analysis model in real time, and performing transformer fault analysis through the fault analysis model to generate a transformer state analysis result. The multi-dimensional sensor data refers to various sensors, such as an oil chromatography sensor, an iron core grounding current sensor, a partial discharge sensor, and the like. The multiple dimensions refer to multiple types, and the correlation among different characteristic dimensions (data acquired by different types of sensors) is mined by adopting a method based on a transformer neural network, so that the transformer state monitoring precision is improved.
Further, comprising: inputting sensor data of each dimension into a fault analysis model; after sensor data pass through embedding, adding position information to data of each dimension by adopting a position coding algorithm based on a coding processing layer; after the position information is added, adding category coding information to the data of each dimension based on a coding processing layer, wherein the category coding information comprises a normal state, an early warning state, a hazard state and value intervals corresponding to each state; and sequentially inputting the data added with the position information and the class coding information into an encoder and a decoder, and finally outputting the data on a class output layer to obtain a transformer state analysis result.
In some embodiments of the invention, sensor data is collected in many dimensions in a transformer monitoring system, such as: the method comprises the steps of online oil chromatography, top oil temperature, offline oil chromatography, insulating oil, winding capacitance and dielectric loss, sleeve capacitance and dielectric loss, partial discharge and the like, and then a self-attention mechanism in a transform neural network is utilized, and a machine actively excavates the correlation which is difficult to observe between dimensionality and dimensionality, so that the purpose of monitoring the state of the transformer is achieved, and accurate transformer state monitoring is achieved. After sensor data passes through embedding, position information is added to each dimension through a position coding algorithm, after the position coding, category coding information is added, and according to the state of a transformer, category coding can be divided into three types: the transformer state is divided into three states of health, sub-health and sick, which respectively correspond to the normality, early warning and damage of the category coding, the sick state represents that the current transformer state is very poor and needs to be detected and maintained immediately, the state of the health indication current transformer is good, the sub-health state is between the sick state and the healthy state and represents that the current transformer can run, but the state change needs to be paid special attention.
In order to solve the problems in the prior art, a targeted analysis model based on a transform neural network structure is constructed according to the data characteristics and state quantity of the transformer, the model is trained based on data in multiple aspects to obtain a fault analysis model with optimal analysis performance, and then the relevance between different characteristic dimensions is mined based on the fault analysis model and the real-time sensor data of multiple dimensions of the transformer, so that the state of the transformer is accurately analyzed, and the monitoring precision of the state of the transformer is improved.
As shown in fig. 4, in a second aspect, an embodiment of the present invention provides a transformer monitoring system applied to a power plant, including a data set acquisition module 100, a model construction module 200, a model training module 300, and a state analysis module 400, where:
the data set acquisition module 100 is configured to acquire transformer data in multiple aspects and construct an offline data set;
the model building module 200 is used for building an initial analysis model based on a Transformer neural network structure according to the data characteristics and the state quantity of the Transformer;
a model training module 300, configured to train the initial analysis model according to the offline data set to obtain a target fault analysis model;
and the state analysis module 400 is configured to collect and import the sensor data of multiple dimensions of the transformer into the target fault analysis model in real time, perform transformer fault analysis through the fault analysis model, and generate a transformer state analysis result.
In order to solve the problems in the prior art, the system constructs a targeted analysis model based on a transform neural network structure according to the characteristics and state quantity of transformer data through the cooperation of a plurality of modules such as a data set acquisition module 100, a model construction module 200, a model training module 300 and a state analysis module 400, trains the model based on data in multiple aspects to obtain a fault analysis model with optimal analysis performance, and then mines the relevance among different characteristic dimensions based on the fault analysis model and the real-time sensor data of the transformer in multiple dimensions, so that the transformer state is accurately analyzed, and the transformer state monitoring precision is improved.
As shown in fig. 5, in a third aspect, an embodiment of the present application provides an electronic device, which includes a memory 101 for storing one or more programs; a processor 102. The one or more programs, when executed by the processor 102, implement the method of any of the first aspects as described above.
Also included is a communication interface 103, and the memory 101, processor 102 and communication interface 103 are electrically connected to each other, directly or indirectly, to enable transfer or interaction of data. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory 101 may be used to store software programs and modules, and the processor 102 executes the software programs and modules stored in the memory 101 to thereby execute various functional applications and data processing. The communication interface 103 may be used for communicating signaling or data with other node devices.
The Memory 101 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like.
The processor 102 may be an integrated circuit chip having signal processing capabilities. The Processor 102 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
In the embodiments provided in the present application, it should be understood that the disclosed method and system and method can be implemented in other ways. The method and system embodiments described above are merely illustrative and, for example, the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, which, when executed by the processor 102, implements the method according to any one of the first aspect described above. The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The present invention has been described in terms of the preferred embodiment, and it is not intended to be limited to the embodiment. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
It will be evident to those skilled in the art that the application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (10)
1. A transformer monitoring method applied to a power station is characterized by comprising the following steps:
acquiring transformer data in multiple aspects, and constructing an offline data set;
constructing an initial analysis model based on a Transformer neural network structure according to the data characteristics and the state quantity of the Transformer;
training the initial analysis model according to the offline data set to obtain a target fault analysis model;
the method comprises the steps of collecting and importing sensor data of multiple dimensions of the transformer into a target fault analysis model in real time, carrying out transformer fault analysis through the fault analysis model, and generating a transformer state analysis result.
2. The transformer monitoring method applied to the power generation station according to claim 1, wherein the transformer data of the plurality of aspects comprises online monitoring data, offline test data and design parameter data.
3. The transformer monitoring method applied to the power station as claimed in claim 1, wherein the method for training the initial analysis model according to the off-line data set to obtain the target fault analysis model comprises the following steps:
classifying the offline data set to obtain a training data set and a testing data set;
and performing iterative training and testing on the initial analysis model based on the training data set and the testing data set until the testing result reaches the optimal solution to obtain a target fault analysis model.
4. The Transformer monitoring method applied to the power generation station, according to claim 1, is characterized in that the initial analysis model based on the transform neural network structure comprises an algorithm input layer, a coding processing layer and a category output layer.
5. The transformer monitoring method applied to the power station as claimed in claim 4, wherein the algorithm input layer comprises sensor data of hydrogen, carbon monoxide, carbon dioxide, methane, ethylene, ethane, acetylene, total hydrocarbons and corresponding point position temperature and equipment operation time in multiple dimensions.
6. The transformer monitoring method applied to the power station as claimed in claim 5, wherein the transformer fault analysis is performed through a fault analysis model, and the method for generating the transformer state analysis result comprises the following steps:
inputting sensor data of each dimension into a fault analysis model;
after sensor data pass through embedding, adding position information to data of each dimension by adopting a position coding algorithm based on a coding processing layer;
after adding the position information, adding category coding information to the data of each dimensionality based on a coding processing layer;
and sequentially inputting the data added with the position information and the class coding information into an encoder and a decoder, and finally outputting the data on a class output layer to obtain a transformer state analysis result.
7. The transformer monitoring method applied to the power station as claimed in claim 6, wherein the category coded information includes a normal state, an early warning state, a hazard state and value intervals corresponding to the respective states.
8. The utility model provides a transformer monitoring system for power station, its characterized in that includes data set acquisition module, model construction module, model training module and state analysis module, wherein:
the data set acquisition module is used for acquiring transformer data in multiple aspects and constructing an offline data set;
the model building module is used for building an initial analysis model based on a Transformer neural network structure according to the data characteristics and the state quantity of the Transformer;
the model training module is used for training the initial analysis model according to the offline data set to obtain a target fault analysis model;
and the state analysis module is used for acquiring and importing the sensor data of the transformer in multiple dimensions into a target fault analysis model in real time, and performing transformer fault analysis through the fault analysis model to generate a transformer state analysis result.
9. An electronic device, comprising:
a memory for storing one or more programs;
a processor;
the one or more programs, when executed by the processor, implement the method of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211264006.0A CN115327286A (en) | 2022-10-17 | 2022-10-17 | Transformer monitoring method and system applied to power station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211264006.0A CN115327286A (en) | 2022-10-17 | 2022-10-17 | Transformer monitoring method and system applied to power station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115327286A true CN115327286A (en) | 2022-11-11 |
Family
ID=83915295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211264006.0A Pending CN115327286A (en) | 2022-10-17 | 2022-10-17 | Transformer monitoring method and system applied to power station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115327286A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116702030A (en) * | 2023-05-31 | 2023-09-05 | 浙江大学 | Blast furnace state monitoring method and device based on sensor reliability analysis |
| CN117630758A (en) * | 2024-01-24 | 2024-03-01 | 国能大渡河检修安装有限公司 | Method and system for monitoring health state of power station transformer |
| CN117668528A (en) * | 2024-02-01 | 2024-03-08 | 成都华泰数智科技有限公司 | Natural gas voltage regulator fault detection method and system based on Internet of things |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113671421A (en) * | 2021-08-24 | 2021-11-19 | 华北电力大学（保定） | Transformer state evaluation and fault early warning method |
| CN114120112A (en) * | 2021-11-22 | 2022-03-01 | 上海交通大学 | Transformer fault automatic detection method based on submersible robot |
| CN114487673A (en) * | 2022-01-25 | 2022-05-13 | 国网冀北电力有限公司 | Power equipment fault detection model based on Transformer and electronic equipment |
| CN115016966A (en) * | 2022-05-31 | 2022-09-06 | 广东电网有限责任公司 | Measurement automation system fault prediction method and device based on Transformer and storage medium |
| CN115186904A (en) * | 2022-07-13 | 2022-10-14 | 清华大学 | Industrial equipment fault prediction method and device based on Transformer |
-
2022
- 2022-10-17 CN CN202211264006.0A patent/CN115327286A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113671421A (en) * | 2021-08-24 | 2021-11-19 | 华北电力大学（保定） | Transformer state evaluation and fault early warning method |
| CN114120112A (en) * | 2021-11-22 | 2022-03-01 | 上海交通大学 | Transformer fault automatic detection method based on submersible robot |
| CN114487673A (en) * | 2022-01-25 | 2022-05-13 | 国网冀北电力有限公司 | Power equipment fault detection model based on Transformer and electronic equipment |
| CN115016966A (en) * | 2022-05-31 | 2022-09-06 | 广东电网有限责任公司 | Measurement automation system fault prediction method and device based on Transformer and storage medium |
| CN115186904A (en) * | 2022-07-13 | 2022-10-14 | 清华大学 | Industrial equipment fault prediction method and device based on Transformer |
Non-Patent Citations (1)
| Title |
|---|
| 苏小盟: "基于神经网络和注意力机制的变压器状态预测和故障诊断研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116702030A (en) * | 2023-05-31 | 2023-09-05 | 浙江大学 | Blast furnace state monitoring method and device based on sensor reliability analysis |
| CN116702030B (en) * | 2023-05-31 | 2024-01-23 | 浙江大学 | Blast furnace state monitoring method and device based on sensor reliability analysis |
| CN117630758A (en) * | 2024-01-24 | 2024-03-01 | 国能大渡河检修安装有限公司 | Method and system for monitoring health state of power station transformer |
| CN117630758B (en) * | 2024-01-24 | 2024-05-03 | 国能大渡河检修安装有限公司 | Method and system for monitoring health state of power station transformer |
| CN117668528A (en) * | 2024-02-01 | 2024-03-08 | 成都华泰数智科技有限公司 | Natural gas voltage regulator fault detection method and system based on Internet of things |
| CN117668528B (en) * | 2024-02-01 | 2024-04-12 | 成都华泰数智科技有限公司 | Natural gas voltage regulator fault detection method and system based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115327286A (en) | Transformer monitoring method and system applied to power station | |
| Ashkezari et al. | Application of fuzzy support vector machine for determining the health index of the insulation system of in-service power transformers | |
| Abu-Siada et al. | A new approach to identify power transformer criticality and asset management decision based on dissolved gas-in-oil analysis | |
| CN113435652B (en) | Primary equipment defect diagnosis and prediction method | |
| CN104535865A (en) | Comprehensive diagnosing method for operation troubles of power transformer based on multiple parameters | |
| CN108680811B (en) | Transformer fault state evaluation method | |
| Wang | Extension neural network for power transformer incipient fault diagnosis | |
| Duraisamy et al. | Neuro fuzzy schemes for fault detection in power transformer | |
| Sharma et al. | Review of artificial intelligence techniques application to dissolved gas analysis on power transformer | |
| CN116300691A (en) | State monitoring method and system for multi-axis linkage numerical control machining | |
| CN111371188A (en) | Real-time early warning system for abnormal power consumption data | |
| CN109100429A (en) | A kind of oil dissolved gas prediction technique of combined prediction residual GM | |
| CN115015683B (en) | Cable production performance test method, device, equipment and storage medium | |
| CN113987294A (en) | CVT (continuously variable transmission) online fault diagnosis method based on genetic optimization GRU (generalized regression Unit) neural network | |
| Luo et al. | Graph convolutional network-based interpretable machine learning scheme in smart grids | |
| Malik et al. | Selection of most relevant input parameters using waikato environment for knowledge analysis for gene expression programming based power transformer fault diagnosis | |
| Wani et al. | Diagnosis of incipient dominant and boundary faults using composite DGA method | |
| CN113435759A (en) | Primary equipment risk intelligent evaluation method based on deep learning | |
| CN116720324A (en) | Traction substation key equipment fault early warning method and system based on prediction model | |
| Dehbozorgi et al. | Decision tree‐based classifiers for root‐cause detection of equipment‐related distribution power system outages | |
| Esmaeili Nezhad et al. | A review of the applications of machine learning in the condition monitoring of transformers | |
| Li et al. | Signal anomaly detection of bridge SHM system based on two-stage deep convolutional neural networks | |
| CN112380763A (en) | System and method for analyzing reliability of in-pile component based on data mining | |
| CN117332330A (en) | Transformer fault evaluation method and system based on multi-source data graph fusion model | |
| CN108681835B (en) | Method for evaluating degradation state of transformer insulating oil |
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: 20221111 |
|
| RJ01 | Rejection of invention patent application after publication |