CN116840764A - Method and system for evaluating comprehensive error state of capacitive voltage transformer - Google Patents
Method and system for evaluating comprehensive error state of capacitive voltage transformer Download PDFInfo
- Publication number
- CN116840764A CN116840764A CN202311062076.2A CN202311062076A CN116840764A CN 116840764 A CN116840764 A CN 116840764A CN 202311062076 A CN202311062076 A CN 202311062076A CN 116840764 A CN116840764 A CN 116840764A
- Authority
- CN
- China
- Prior art keywords
- cvt
- day
- characteristic
- comprehensive
- voltage transformer
- 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 53
- 238000003062 neural network model Methods 0.000 claims abstract description 36
- 238000011156 evaluation Methods 0.000 claims abstract description 34
- 238000001228 spectrum Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 15
- 230000004927 fusion Effects 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 18
- 230000003044 adaptive effect Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 238000003786 synthesis reaction Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 10
- 238000013210 evaluation model Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013145 classification model Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/02—Testing or calibrating of apparatus covered by the other groups of this subclass of auxiliary devices, e.g. of instrument transformers according to prescribed transformation ratio, phase angle, or wattage rating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Power Engineering (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application relates to the technical field of electric power metering on-line monitoring, and provides a method and a system for evaluating the comprehensive error state of a capacitive voltage transformer. Acquiring an online waveform signal of a CVT, and performing slicing processing and signal processing to obtain time-frequency spectrum characteristics; based on the time spectrum characteristics, extracting CVT single day characteristics by adopting a plurality of convolutional neural networks; adding temperature information and humidity information into the CVT single-day characteristic according to a time corresponding relation to construct a CVT single-day comprehensive characteristic; based on the single-day comprehensive characteristics of the CVT, a full connection layer is adopted to obtain a first intermediate characteristic; based on the CVT historical single-day comprehensive characteristics, a two-way long-short-period memory network is adopted to obtain an output result, and a second intermediate characteristic is obtained through a full-connection layer; fusing the first intermediate feature and the second intermediate feature to obtain a fused feature; based on the fusion characteristics, an evaluation result is obtained, and parameters of the self-adaptive neural network model are optimized according to the evaluation result.
Description
Technical Field
The application relates to the technical field of electric power metering on-line monitoring, in particular to a method and a system for evaluating the comprehensive error state of a capacitive voltage transformer.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
As an important component of the electric energy metering device, the accuracy and reliability of the metering performance of the mutual inductor are directly related to fairness and fairness of electric energy trade settlement. The CVT is divided by a series capacitor, then is reduced and isolated by an electromagnetic transformer, and is used as an instrument for converting voltage, and the capacitive voltage transformer can also couple carrier frequency to a power transmission line for long-distance communication, selective line high-frequency protection, remote control and other functions. Compared with the conventional electromagnetic voltage transformer, the capacitive voltage transformer has the advantages of high impact insulation strength, simple manufacture, small volume, light weight and the like, and has a plurality of advantages in economy and safety.
In the actual operation process of the CVT, CVT errors are affected by factors such as the collection principle and the working environment, so that the CVT may be worn in different degrees during long-term operation. Because the power failure of the high-voltage transmission line is difficult, the offline detection of the CVT cannot be carried out frequently, whether the CVT is in a normal running state cannot be judged timely, fair trade settlement of electric energy is affected, and hidden trouble exists.
The prior art adopts CVT off-line data of a certain scene to train a neural network model, and the trained neural network model is directly used for carrying out comprehensive error state evaluation on the CVT on-line data. However, each CVT uses a different scenario, so the trained neural network model cannot be fully adapted to all the scenarios of the CVT, and there is a large error in the evaluation result.
Disclosure of Invention
In order to solve the technical problems in the background art, the application provides a method and a system for evaluating the comprehensive error state of a capacitive voltage transformer, which are used for adaptively adjusting a neural network model by adopting CVT offline data of multiple scenes, so that the prediction precision of the model on CVT data in various scenes is improved.
In order to achieve the above purpose, the present application adopts the following technical scheme:
the first aspect of the application provides a method for evaluating the comprehensive error state of a capacitive voltage transformer.
A method for evaluating the comprehensive error state of a capacitive voltage transformer comprises the following steps:
acquiring a daily real-time acquisition waveform signal, temperature information and humidity information of the CVT, and acquiring a comprehensive error state evaluation result of the capacitive voltage transformer by adopting a trained self-adaptive neural network model;
the training process of the adaptive neural network model comprises the following steps: acquiring a daily real-time acquisition waveform signal of the CVT, and performing slicing processing and signal processing to obtain time spectrum characteristics; based on the time spectrum characteristics, extracting CVT single day characteristics by adopting a plurality of convolutional neural networks; adding temperature information and humidity information into the CVT single-day characteristic according to a time corresponding relation to construct a CVT single-day comprehensive characteristic; based on the single-day comprehensive characteristics of the CVT, a full connection layer is adopted to obtain a first intermediate characteristic; based on the CVT historical single-day comprehensive characteristics, a two-way long-short-period memory network is adopted to obtain an output result, and a second intermediate characteristic is obtained through a full-connection layer; fusing the first intermediate feature and the second intermediate feature to obtain a fused feature; based on the fusion characteristics, an evaluation result is obtained, and parameters of the self-adaptive neural network model are optimized according to the evaluation result.
Further, the slicing process includes: the method comprises the steps of setting the slice length, and slicing the daily real-time acquisition waveform signals of the CVT by the repeated extraction length with the set time length between two adjacent slices.
Further, the process of extracting CVT single day features based on the time-frequency spectrum features using a plurality of convolutional neural networks includes: based on the time spectrum characteristics, a plurality of convolutional neural networks are adopted to obtain a plurality of characteristics; and longitudinally superposing a plurality of features to obtain the single day feature of the CVT.
Further, the process of adding temperature information and humidity information into the CVT single-day characteristic according to the time correspondence, and constructing the CVT single-day comprehensive characteristic includes: calculating a temperature average value and a humidity average value of a certain time period based on a daily temperature curve and a daily humidity curve; and adding the temperature average value and the humidity average value into the CVT single-day characteristic based on the corresponding relation between a certain time period and the time in the CVT single-day characteristic, and constructing the CVT single-day comprehensive characteristic.
Further, the process of fusing the first intermediate feature and the second intermediate feature to obtain the fused feature adopts the following formula:
o i ＝w i1 l i +w i2 r i
wherein o is i Representing the ith dimension component, l, of the fusion feature O i An ith dimension component, r, representing a computed day synthesis feature, L i An ith dimension component, w, representing a calculated day characteristic, R, based on historical operating conditions i1 ,w i2 Respectively representing the ith dimension component l of the calculation day comprehensive characteristics i Is based on the weight of the historical running state and the calculated day characteristic ith dimension component r i Is a weight of (2).
Further, constructing a data set according to the time spectrum characteristics and the state categories corresponding to the time spectrum characteristics; dividing the data set into a training set and a testing set; and training the adaptive neural network model by adopting a training set.
Further, the process of optimizing the parameters of the adaptive neural network model according to the evaluation result includes judging whether the evaluation result is the same as the state type, if not, optimizing the parameters of the adaptive neural network model, and if so, continuing the next iteration training until the iteration times set by iteration to obtain the trained adaptive neural network model.
The second aspect of the application provides a system for evaluating the comprehensive error state of a capacitive voltage transformer.
A capacitive voltage transformer integrated error condition assessment system, comprising:
an online evaluation module configured to: acquiring a daily real-time acquisition waveform signal, temperature information and humidity information of the CVT, and acquiring a comprehensive error state evaluation result of the capacitive voltage transformer by adopting a trained self-adaptive neural network model;
an adaptive neural network model training module configured to: acquiring a daily real-time acquisition waveform signal of the CVT, and performing slicing processing and signal processing to obtain time spectrum characteristics; based on the time spectrum characteristics, extracting CVT single day characteristics by adopting a plurality of convolutional neural networks; adding temperature information and humidity information into the CVT single-day characteristic according to a time corresponding relation to construct a CVT single-day comprehensive characteristic; based on the single-day comprehensive characteristics of the CVT, a full connection layer is adopted to obtain a first intermediate characteristic; based on the CVT historical single-day comprehensive characteristics, a two-way long-short-period memory network is adopted to obtain an output result, and a second intermediate characteristic is obtained through a full-connection layer; fusing the first intermediate feature and the second intermediate feature to obtain a fused feature; based on the fusion characteristics, an evaluation result is obtained, and parameters of the self-adaptive neural network model are optimized according to the evaluation result.
A third aspect of the present application provides a computer-readable storage medium.
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method for evaluating a state of integrated error of a capacitive voltage transformer as described in the first aspect above.
A fourth aspect of the application provides a computer device.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the method for evaluating the integrated error condition of a capacitive voltage transformer as described in the first aspect above when the program is executed.
Compared with the prior art, the application has the beneficial effects that:
according to the application, the self-adaptive adjustment is carried out on the neural network model by adopting the CVT offline waveform signals with multiple scenes, and the self-adaptive neural network model after the self-adaptive adjustment is obtained is used for the real-time prediction of the CVT online waveform signals, so that the prediction precision of the model on the CVT online waveform under various scenes is improved, whether the CVT is in a normal running state or not is judged in time, and the hidden trouble is avoided.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application.
FIG. 1 is a flow chart of a method for evaluating the overall error condition of a capacitive voltage transformer according to the present application;
FIG. 2 is a block diagram of a deep-learned feature extraction model shown in the present application;
fig. 3 is a flow chart illustrating adaptive adjustment of a CVT according to the present application.
Detailed Description
The application will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present application. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
It is noted that the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems according to various embodiments of the present disclosure. It should be noted that 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 logical functions specified in the various embodiments. 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 flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by special purpose hardware-based systems which perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.
Example 1
As shown in fig. 1, this embodiment provides a method for evaluating the comprehensive error state of a capacitive voltage transformer, and this embodiment is illustrated by applying the method to a server, and it can be understood that the method may also be applied to a terminal, and may also be applied to a system and a terminal, and implemented through interaction between the terminal and the server. The server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and can also be a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communication, middleware services, domain name services, security services CDNs, basic cloud computing services such as big data and artificial intelligent platforms and the like. The terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc. The terminal and the server may be directly or indirectly connected through wired or wireless communication, and the present application is not limited herein. In this embodiment, the method includes the steps of:
acquiring a daily real-time acquisition waveform signal, temperature information and humidity information of the CVT, and acquiring a comprehensive error state evaluation result of the capacitive voltage transformer by adopting a trained self-adaptive neural network model;
the training process of the adaptive neural network model comprises the following steps: acquiring a daily real-time acquisition waveform signal of the CVT, and performing slicing processing and signal processing to obtain time spectrum characteristics; based on the time spectrum characteristics, extracting CVT single day characteristics by adopting a plurality of convolutional neural networks; adding temperature information and humidity information into the CVT single-day characteristic according to a time corresponding relation to construct a CVT single-day comprehensive characteristic; based on the single-day comprehensive characteristics of the CVT, a full connection layer is adopted to obtain a first intermediate characteristic; based on the CVT historical single-day comprehensive characteristics, a two-way long-short-period memory network is adopted to obtain an output result, and a second intermediate characteristic is obtained through a full-connection layer; fusing the first intermediate feature and the second intermediate feature to obtain a fused feature; based on the fusion characteristics, an evaluation result is obtained, and parameters of the self-adaptive neural network model are optimized according to the evaluation result.
Step1: and (5) acquisition and preprocessing of a data set.
And acquiring a waveform signal of the CVT on a daily basis from a monitoring device of the CVT transformer, and acquiring a corresponding CVT state on a daily basis according to the result of the CVT on-line monitoring platform. Slicing CVT waveform signal of a single day, wherein slicing rule is as follows, slice length is set to be T(s), and repeated extraction length of deltat exists between two adjacent slicesAn N-segment waveform signal segment is generated. Obtaining a time spectrum S= { S corresponding to each section of waveform signal through corresponding signal processing operation 1 ,s 2 ,…,s N }. The data set d= { X, Y }, any sample D (X, Y), (D e D, X e X, Y e Y) is set as data within any date, characterized by a single time-of-day spectrum, i.e. x=s. The classification state Y is represented by a single day state displayed in the transformer on-line detection system. For a pair ofThe categories should be classified into (normal, abnormal, alarm). Normalizing the constructed data set and taking 7:3 into training set D training And test set D test 。
When the time of the monitoring device acquisition is shorter, and the data volume is insufficient, repeated extracted data exist between the sections, more fragments can be generated, and training is more sufficient. The waveform signal data stores time-dimensional information. After each operation of signal processing, the corresponding relation of time sequence among the slices without repeated sections is weakened, namely the time dimension information is weakened. In order to be able to retain the relevant information, the waveform data is thus subjected to a repeated section slicing process.
Step2: a deep-learning feature extraction model is constructed, as shown in fig. 2.
Step2.1: spectrum { s } at characteristic time of sample data d 1 ,s 2 ,…,s N And respectively inputting the N Convolutional Neural Network (CNN) modules. In each CNN module, after the time spectrum s is processed by multi-layer convolution pooling, the deep features are unfolded by the full connection layer to obtain k-dimensional features q, dim= [1×k ]]. Extracting the features { q } from N modules 1 ,q 2 ,…,q N Longitudinal superposition to obtain CVT single day feature f, dim= [ N x k ]]。
Step2.2: temperature information and humidity information are added. According to the daily temperature and humidity curve, obtaining a time period T D Is a temperature and humidity average value of the air conditioner. Will T D The correspondence with T adds temperature and humidity information to the single day characteristic of the CVT. Then the new single day characteristic f' is
Wherein, the liquid crystal display device comprises a liquid crystal display device,represented as dimension characteristics of the corresponding CNN module input after the ith slice processing,expressed as the mean value of the temperatures of the corresponding time period of the extraction of the ith slice,/i>Represented as the mean value of the humidity extracted for the corresponding time period of the ith slice.
Step3: and constructing a deep learning classification model, and constructing a deep learning characteristic classification model.
Step3.1: extracting CVT characteristics of D days, and F= { F 1 ′,f 2 ′,…,f D ' input it into the Bi-layer Bi-LSTM model for classification training.
Step3.2: by repeating the steps of Step2 and Step3.1, set D is entered Train The feature data x and the tag data y of each sample in (a) are used for model training to obtain a suitable network model.
Step3.3: test set D Test The samples in the model are input into a trained network model to obtain a prediction label y of the corresponding sample predict Will y predict And the actual label y test The comparison yields the accuracy of the scheme.
Step4: the CVT is adaptively adjusted.
Since each CVT uses a different scenario, the model is adaptively adjusted in order to accurately evaluate the overall error status of each CVT, the flow of which is shown in fig. 3.
Step4.1: based on the existing model, performing self-adaptive adjustment on a comprehensive error evaluation model of the CVT to be detected according to historical data of the CVT to be detected, based on the previous model and parameters, performing the following adjustment on the comprehensive error evaluation model of the CVT to be detected, and obtaining a calculation day comprehensive characteristic L= { L through a Dense layer by using the calculation day comprehensive characteristic 1 ,l 2 ,…,l k The method comprises the steps of (1) strengthening the influence of the operation process of the calculation day, and connecting a Dense layer output by Bi-LSTM with a Dense layer to obtain the calculation day characteristic R= { R based on the historical operation state 1 ,r 2 ,…,r k And reinforcing the effect of the stage history data on the calculation day. Will beThe two strong influence components are fused to obtain O, and the specific method comprises the following steps:
o i ＝w i1 l i +w i2 r i
wherein w is i1 Weight, w, representing the i-th dimension component of the computed daily composite feature i2 Weights representing calculated day characteristic ith dimension components based on historical operating conditions
I.e. o= { O 1 ,o 2 ,…,o k }＝{w 11 l 1 +w 12 r 1 ,w 21 l 2 +w 22 r 2 ,…,w k1 l k +w k2 r k }。
Wherein o is i Representing the ith dimension component, l, of the fusion feature O i An ith dimension component, r, representing a computed day synthesis feature, L i An ith dimension component, w, representing a calculated day characteristic, R, based on historical operating conditions i1 ,w i2 Respectively representing the ith dimension component l of the calculation day comprehensive characteristics i Is based on the weight of the historical running state and the calculated day characteristic ith dimension component r i Is a weight of (2).
Finally, the evaluation result is obtained through a softmax function.
The adaptive adjustment designed by the application tests the CVT to be tested to have certain variability through the acquired data of the calculation day, and adds a general result based on the historical running state of the CVT to be tested in order to reduce the influence caused by sudden change of a secondary circuit and the like. And comprehensively judging the operation state of the CVT to be tested. The change condition of the operation state of the CVT to be detected in the operation process is obtained through the dimension of time. Compared with the method for analyzing the operation state of the CVT to be detected only aiming at the date to be detected, the analysis result based on the history can reflect the influence of data mutation caused by the reasons of certain working condition changes in the general weakened real-time data of the CVT to be detected.
Step4.2: according to the process of Step4.1, the historical data of the CVT to be tested is used, and training and adjusting are carried out on the evaluation model of the CVT to be tested according to the pre-constructed overall CVT evaluation model and parameters so as to obtain a model with the highest accuracy.
Step5: and performing online comprehensive error evaluation and classification on the CVT by adopting a deep neural network model.
And acquiring waveform signals, temperature and humidity information in the CVT online monitoring system corresponding to the date to be detected, preprocessing the data, inputting the data into the self-adaptive neural network model, and outputting a classification result of the CVT online comprehensive error evaluation.
Example two
The embodiment provides a system for evaluating the comprehensive error state of a capacitive voltage transformer.
A capacitive voltage transformer integrated error condition assessment system, comprising:
an online evaluation module configured to: acquiring a daily real-time acquisition waveform signal, temperature information and humidity information of the CVT, and acquiring a comprehensive error state evaluation result of the capacitive voltage transformer by adopting a trained self-adaptive neural network model;
an adaptive neural network model training module configured to: acquiring a daily real-time acquisition waveform signal of the CVT, and performing slicing processing and signal processing to obtain time spectrum characteristics; based on the time spectrum characteristics, extracting CVT single day characteristics by adopting a plurality of convolutional neural networks; adding temperature information and humidity information into the CVT single-day characteristic according to a time corresponding relation to construct a CVT single-day comprehensive characteristic; based on the single-day comprehensive characteristics of the CVT, a full connection layer is adopted to obtain a first intermediate characteristic; based on the CVT historical single-day comprehensive characteristics, a two-way long-short-period memory network is adopted to obtain an output result, and a second intermediate characteristic is obtained through a full-connection layer; fusing the first intermediate feature and the second intermediate feature to obtain a fused feature; based on the fusion characteristics, an evaluation result is obtained, and parameters of the self-adaptive neural network model are optimized according to the evaluation result.
It should be noted that the online evaluation module and the adaptive neural network model training module are the same as the examples and application scenarios implemented by the steps in the first embodiment, but are not limited to the disclosure in the first embodiment. It should be noted that the modules described above may be implemented as part of a system in a computer system, such as a set of computer-executable instructions.
Example III
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in the method for evaluating a comprehensive error state of a capacitive voltage transformer according to the above embodiment.
Example IV
The present embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor executes the program to implement the steps in the method for evaluating the integrated error state of the capacitive voltage transformer according to the first embodiment.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random access Memory (Random AccessMemory, RAM), or the like.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. The method for evaluating the comprehensive error state of the capacitive voltage transformer is characterized by comprising the following steps of:
acquiring a daily real-time acquisition waveform signal, temperature information and humidity information of the CVT, and acquiring a comprehensive error state evaluation result of the capacitive voltage transformer by adopting a trained self-adaptive neural network model;
the training process of the adaptive neural network model comprises the following steps: acquiring a daily real-time acquisition waveform signal of the CVT, and performing slicing processing and signal processing to obtain time spectrum characteristics; based on the time spectrum characteristics, extracting CVT single day characteristics by adopting a plurality of convolutional neural networks; adding temperature information and humidity information into the CVT single-day characteristic according to a time corresponding relation to construct a CVT single-day comprehensive characteristic; based on the single-day comprehensive characteristics of the CVT, a full connection layer is adopted to obtain a first intermediate characteristic; based on the CVT historical single-day comprehensive characteristics, a two-way long-short-period memory network is adopted to obtain an output result, and a second intermediate characteristic is obtained through a full-connection layer; fusing the first intermediate feature and the second intermediate feature to obtain a fused feature; based on the fusion characteristics, an evaluation result is obtained, and parameters of the self-adaptive neural network model are optimized according to the evaluation result.
2. The method for evaluating the state of integrated error of a capacitive voltage transformer according to claim 1, wherein the slicing process comprises: the method comprises the steps of setting the slice length, and slicing the daily real-time acquisition waveform signals of the CVT by the repeated extraction length with the set time length between two adjacent slices.
3. The method for evaluating the comprehensive error state of the capacitive voltage transformer according to claim 1, wherein the process of extracting the CVT single day characteristic by using a plurality of convolutional neural networks based on the time-frequency spectrum characteristic comprises: based on the time spectrum characteristics, a plurality of convolutional neural networks are adopted to obtain a plurality of characteristics; and longitudinally superposing a plurality of features to obtain the single day feature of the CVT.
4. The method for evaluating the comprehensive error state of the capacitive voltage transformer according to claim 1, wherein the step of adding temperature information and humidity information to the CVT single-day characteristic according to the time correspondence relationship, and the step of constructing the CVT single-day comprehensive characteristic comprises the steps of: calculating a temperature average value and a humidity average value of a certain time period based on a daily temperature curve and a daily humidity curve; and adding the temperature average value and the humidity average value into the CVT single-day characteristic based on the corresponding relation between a certain time period and the time in the CVT single-day characteristic, and constructing the CVT single-day comprehensive characteristic.
5. The method for evaluating the comprehensive error state of a capacitive voltage transformer according to claim 1, wherein the process of fusing the first intermediate feature and the second intermediate feature to obtain the fused feature uses the following formula:
o i ＝w i1 l i +w i2 r i
wherein o is i Representing the ith dimension component, i, of the fused feature O i An ith dimension component, r, representing a computed day synthesis feature, L i An ith dimension component, w, representing a calculated day characteristic, R, based on historical operating conditions i1 ,w i2 Respectively representing the ith dimension component l of the calculation day comprehensive characteristics i Is based on the weight of the historical running state and the calculated day characteristic ith dimension component r i Is a weight of (2).
6. The method for evaluating the comprehensive error state of the capacitive voltage transformer according to claim 1, wherein the data set is constructed according to the time spectrum characteristics and the state types corresponding to the time spectrum characteristics; dividing the data set into a training set and a testing set; and training the adaptive neural network model by adopting a training set.
7. The method for evaluating the comprehensive error state of the capacitive voltage transformer according to claim 6, wherein the process of optimizing the parameters of the adaptive neural network model according to the evaluation result includes judging whether the evaluation result is the same as the state type, if not, optimizing the parameters of the adaptive neural network model, and if so, continuing the next iteration training until the iteration times of the iteration setting to obtain the trained adaptive neural network model.
8. A capacitive voltage transformer comprehensive error state evaluation system, comprising:
an online evaluation module configured to: acquiring a daily real-time acquisition waveform signal, temperature information and humidity information of the CVT, and acquiring a comprehensive error state evaluation result of the capacitive voltage transformer by adopting a trained self-adaptive neural network model;
an adaptive neural network model training module configured to: acquiring a daily real-time acquisition waveform signal of the CVT, and performing slicing processing and signal processing to obtain time spectrum characteristics; based on the time spectrum characteristics, extracting CVT single day characteristics by adopting a plurality of convolutional neural networks; adding temperature information and humidity information into the CVT single-day characteristic according to a time corresponding relation to construct a CVT single-day comprehensive characteristic; based on the single-day comprehensive characteristics of the CVT, a full connection layer is adopted to obtain a first intermediate characteristic; based on the CVT historical single-day comprehensive characteristics, a two-way long-short-period memory network is adopted to obtain an output result, and a second intermediate characteristic is obtained through a full-connection layer; fusing the first intermediate feature and the second intermediate feature to obtain a fused feature; based on the fusion characteristics, an evaluation result is obtained, and parameters of the self-adaptive neural network model are optimized according to the evaluation result.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method for evaluating the integrated error status of a capacitive voltage transformer according to any one of claims 1-7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method for evaluating the integrated error condition of a capacitive voltage transformer according to any one of claims 1-7 when said program is executed by said processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311062076.2A CN116840764A (en) | 2023-08-22 | 2023-08-22 | Method and system for evaluating comprehensive error state of capacitive voltage transformer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311062076.2A CN116840764A (en) | 2023-08-22 | 2023-08-22 | Method and system for evaluating comprehensive error state of capacitive voltage transformer |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116840764A true CN116840764A (en) | 2023-10-03 |
Family
ID=88160176
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311062076.2A Pending CN116840764A (en) | 2023-08-22 | 2023-08-22 | Method and system for evaluating comprehensive error state of capacitive voltage transformer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116840764A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117849691A (en) * | 2024-03-08 | 2024-04-09 | 国网江西省电力有限公司电力科学研究院 | Multi-dimensional collaborative operation monitoring and early warning system and method for capacitive voltage transformer |
| CN117992741A (en) * | 2024-04-07 | 2024-05-07 | 国网山东省电力公司营销服务中心(计量中心) | CVT error state evaluation method and system based on wide-area phasor measurement data |
-
2023
- 2023-08-22 CN CN202311062076.2A patent/CN116840764A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117849691A (en) * | 2024-03-08 | 2024-04-09 | 国网江西省电力有限公司电力科学研究院 | Multi-dimensional collaborative operation monitoring and early warning system and method for capacitive voltage transformer |
| CN117849691B (en) * | 2024-03-08 | 2024-05-14 | 国网江西省电力有限公司电力科学研究院 | Multi-dimensional collaborative operation monitoring and early warning system and method for capacitive voltage transformer |
| CN117992741A (en) * | 2024-04-07 | 2024-05-07 | 国网山东省电力公司营销服务中心(计量中心) | CVT error state evaluation method and system based on wide-area phasor measurement data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116840764A (en) | Method and system for evaluating comprehensive error state of capacitive voltage transformer | |
| CN112101480B (en) | Multivariate clustering and fused time sequence combined prediction method | |
| EP3637328A1 (en) | Refrigerant leak detection method and device for air conditioner | |
| Saxena et al. | Evaluating prognostics performance for algorithms incorporating uncertainty estimates | |
| CN111539515A (en) | Complex equipment maintenance decision method based on fault prediction | |
| CN113887846B (en) | Out-of-tolerance risk early warning method for capacitive voltage transformer | |
| Edwards et al. | Impact of input uncertainty on failure prognostic algorithms: Extending the remaining useful life of nonlinear systems | |
| CN106656669B (en) | A kind of device parameter abnormality detection system and method based on threshold adaptive setting | |
| CN106682159A (en) | Threshold configuration method | |
| CN114169631B (en) | Oil field power load management and control system based on data analysis | |
| CN107295537A (en) | A kind of method and system for wireless sensor network reliability of testing and assessing | |
| CN103346797A (en) | Real-time compression method for gear fault signals | |
| CN116610998A (en) | Switch cabinet fault diagnosis method and system based on multi-mode data fusion | |
| CN114707772A (en) | Power load prediction method and system based on multi-feature decomposition and fusion | |
| Ismail et al. | Adaptive neural network prediction model for energy consumption | |
| Yao et al. | RUL prediction method for rolling bearing using convolutional denoising autoencoder and bidirectional LSTM | |
| CN114444811A (en) | Aluminum electrolysis mixing data superheat degree prediction method based on attention mechanism | |
| CN113222414B (en) | Model stability evaluation method and device, electronic equipment and storage medium | |
| CN114861969A (en) | LSTM-based electric power system oscillation risk prediction method | |
| CN114760194A (en) | Fault studying and judging method for Internet of things equipment | |
| Wang et al. | Health state assessment of industrial equipment driven by the fusion of digital twin model and intelligent algorithm | |
| CN112560252A (en) | Prediction method for residual life of aircraft engine | |
| Ingle et al. | Evaluation of power transformer state ranking based on grey system theory | |
| CN115456168B (en) | Training method of reinforcement learning model, energy consumption determining method and device | |
| Zheng et al. | Research on predicting remaining useful life of equipment based on health index |
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 |