CN108318810A - High voltage isolator fault determination method and device - Google Patents
High voltage isolator fault determination method and device Download PDFInfo
- Publication number
- CN108318810A CN108318810A CN201711446553.XA CN201711446553A CN108318810A CN 108318810 A CN108318810 A CN 108318810A CN 201711446553 A CN201711446553 A CN 201711446553A CN 108318810 A CN108318810 A CN 108318810A
- Authority
- CN
- China
- Prior art keywords
- current signal
- high voltage
- voltage isolator
- aspect ratio
- motor current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
- G01R31/3271—Testing of circuit interrupters, switches or circuit-breakers of high voltage or medium voltage devices
- G01R31/3275—Fault detection or status indication
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
- G01R31/3271—Testing of circuit interrupters, switches or circuit-breakers of high voltage or medium voltage devices
- G01R31/3272—Apparatus, systems or circuits therefor
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Electric Motors In General (AREA)
Abstract
The invention discloses a kind of high voltage isolator fault determination method and devices.This method includes：Obtain motor current signal, wherein the motor of motor high voltage isolator to be measured in order to control；Aspect ratio pair is carried out according to motor current signal and the current signal of preset different faults state；Aspect ratio to it is successful in the case of, judge high voltage isolator for corresponding malfunction.Through the invention, achieved the effect that improve high voltage isolator detection efficiency.
Description
Technical field
The present invention relates to power domains, in particular to a kind of high voltage isolator fault determination method and device.
Background technology
High voltage isolator is device for switching important in power plant and substation's electrical system, it is ensured that High-Voltage Electrical Appliances
And safety of the device in service work, play isolation voltage, high voltage isolator is opened or closed for operating
Journey has important reference significance.
In the related art, the method by hand inspection is needed to detect whether high voltage isolator breaks down, but
This method is time-consuming and laborious, and efficiency is low.
For the low problem of efficiency when determining high voltage isolator failure in the related technology, not yet propose at present effective
Solution.
Invention content
The main purpose of the present invention is to provide a kind of high voltage isolator fault determination method and devices, to solve high pressure
Efficiency low problem when fault isolating switch.
To achieve the goals above, according to an aspect of the invention, there is provided a kind of high voltage isolator failure determines
Method, this method include：Obtain motor current signal, wherein the motor of motor high voltage isolator to be measured in order to control；Root
Aspect ratio pair is carried out according to the motor current signal and the current signal of preset different faults state；In aspect ratio to success
In the case of, judge the high voltage isolator for corresponding malfunction.
Further, aspect ratio is carried out to including according to the motor current signal and preset normal current signal：It will
The wave character of the wave character of the motor current signal and preset normal current signal carries out aspect ratio pair.
Further, feature is being carried out according to the motor current signal and the current signal of preset different faults state
Before comparison, the method further includes：Obtain the current signal parameter under each malfunction；According to each described malfunction
Under current signal parameter training model, obtain trained model；Wherein, according to the motor current signal and preset
The current signal of different faults state carries out aspect ratio to including：Motor current signal is carried out by the trained model
Identification, obtains recognition result.
Further, the kernel function of the model is radial basis function, after obtaining trained model, the method
Further include：Penalty to model and optimized with the parameter of radial basis function, penalty after being optimized and and
The parameter of radial basis function after optimization；According to after optimization penalty and and optimization after the parameter of radial basis function obtain
Model after optimization.
To achieve the goals above, according to another aspect of the present invention, it is true to additionally provide a kind of high voltage isolator failure
Determine device, which includes：First acquisition unit, for obtaining motor current signal, wherein motor height to be measured in order to control
Press the motor of disconnecting switch；Comparing unit, for the electric current according to the motor current signal and preset different faults state
Signal carries out aspect ratio pair；Judging unit, for aspect ratio to it is successful in the case of, judge the high voltage isolator for pair
The malfunction answered.
Further, the comparing unit is used for：By the wave character of the motor current signal and preset normal electricity
The wave character for flowing signal carries out aspect ratio pair.
Further, described device further includes：Second acquisition unit, for according to the motor current signal and default
Different faults state current signal carry out aspect ratio to before, obtaining the current signal parameter under each malfunction；Instruction
Practice unit, for according to the current signal parameter training model under each described malfunction, obtaining trained model；Its
In, aspect ratio is being carried out to including according to the motor current signal and the current signal of preset different faults state：Pass through
Motor current signal is identified in the trained model, obtains recognition result.
Further, the kernel function of the model is radial basis function, and described device further includes：Optimize unit, is used for
It after obtaining trained model, penalty to model and is optimized with the parameter of radial basis function, after obtaining optimization
Penalty and and optimization after radial basis function parameter；Processing unit, for according to after optimization penalty and and
The parameter of radial basis function after optimization optimized after model.
To achieve the goals above, according to another aspect of the present invention, a kind of storage medium is additionally provided, including storage
Program, wherein equipment where controlling the storage medium when described program is run executes high_voltage isolation of the present invention and opens
Close fault determination method.
To achieve the goals above, according to another aspect of the present invention, a kind of processor is additionally provided, for running journey
Sequence, wherein described program executes high voltage isolator fault determination method of the present invention when running.
The present invention, which passes through, obtains motor current signal, wherein the motor of motor high voltage isolator to be measured in order to control；According to
Motor current signal and the current signal of preset different faults state carry out aspect ratio pair；In aspect ratio to successful situation
Under, high voltage isolator is judged for corresponding malfunction, solves the problems, such as that efficiency is low when high voltage isolator failure, in turn
Achieve the effect that improve high voltage isolator detection efficiency.
Description of the drawings
The attached drawing constituted part of this application is used to provide further understanding of the present invention, schematic reality of the invention
Example and its explanation are applied for explaining the present invention, is not constituted improper limitations of the present invention.In the accompanying drawings：
Fig. 1 is the flow chart of high voltage isolator fault determination method according to a first embodiment of the present invention；
Fig. 2 is the motor current waveform comparison diagram that making process measurement obtains under different conditions；And
Fig. 3 is separating brake current waveform comparison diagram under different conditions according to the ... of the embodiment of the present invention；
Fig. 4 is the schematic diagram of switching current characteristic parameter under different conditions according to the ... of the embodiment of the present invention；
Fig. 5 is the schematic diagram of separating brake current characteristic parameter under different conditions according to the ... of the embodiment of the present invention；
Fig. 6 is a kind of fast trip fitness curve graph of particle group optimizing according to the ... of the embodiment of the present invention；
Fig. 7 is the schematic diagram of combined floodgate testing classification result according to the ... of the embodiment of the present invention；
Fig. 8 is the schematic diagram of combined floodgate testing classification result according to the ... of the embodiment of the present invention；
Fig. 9 is the schematic diagram of high voltage isolator failure determination device according to the ... of the embodiment of the present invention.
Specific implementation mode
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The present invention will be described in detail below with reference to the accompanying drawings and embodiments.
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, technical solutions in the embodiments of the present application are clearly and completely described, it is clear that described embodiment is only
The embodiment of the application part, instead of all the embodiments.Based on the embodiment in the application, ordinary skill people
The every other embodiment that member is obtained without making creative work should all belong to the model of the application protection
It encloses.
It should be noted that term " first " in the description and claims of this application and above-mentioned attached drawing, "
Two " etc. be for distinguishing similar object, without being used to describe specific sequence or precedence.It should be appreciated that using in this way
Data can be interchanged in the appropriate case, so as to embodiments herein described herein.In addition, term " comprising " and " tool
Have " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing series of steps or unit
Process, method, system, product or equipment those of are not necessarily limited to clearly to list step or unit, but may include without clear
It is listing to Chu or for these processes, method, product or equipment intrinsic other steps or unit.
An embodiment of the present invention provides a kind of high voltage isolator fault determination methods.
Fig. 1 is the flow chart of high voltage isolator fault determination method according to a first embodiment of the present invention, such as Fig. 1 institutes
Show, this approach includes the following steps：
Step S102：Obtain motor current signal, wherein the motor of motor high voltage isolator to be measured in order to control；
Step S104：Aspect ratio pair is carried out according to motor current signal and the current signal of preset different faults state；
Step S106：Aspect ratio to it is successful in the case of, judge high voltage isolator for corresponding malfunction.
The embodiment is using obtaining motor current signal, wherein the motor of motor high voltage isolator to be measured in order to control；Root
Aspect ratio pair is carried out according to motor current signal and the current signal of preset different faults state；In aspect ratio to successful situation
Under, high voltage isolator is judged for corresponding malfunction, solves the problems, such as that efficiency is low when high voltage isolator failure, in turn
Achieve the effect that improve high voltage isolator detection efficiency.
High voltage isolator to be measured is driven by motor output shaft, thus by detecting current of electric feature ginseng
Number can determine the malfunction of high voltage isolator, since the current signal of different faults state has its fixed feature, because
And the malfunction of high voltage isolator to be measured can be determined by clicking current characteristic parameter.
Optionally, aspect ratio is carried out to including according to motor current signal and preset normal current signal：By motor electricity
The wave character of the wave character and preset normal current signal that flow signal carries out aspect ratio pair.
Optionally, aspect ratio is being carried out to it according to motor current signal and the current signal of preset different faults state
Before, obtain the current signal parameter under each malfunction；According to the current signal parameter training model under each malfunction,
Obtain trained model；Wherein, spy is being carried out according to motor current signal and the current signal of preset different faults state
Sign compares：Motor current signal is identified by trained model, obtains recognition result.
Optionally, the kernel function of model is radial basis function, after obtaining trained model, to the punishment letter of model
It counts and is optimized with the parameter of radial basis function, the penalty after being optimized and the ginseng with the radial basis function after optimization
Number；According to after optimization penalty and and optimization after radial basis function parameter optimized after model.
The embodiment of the present invention additionally provides a kind of preferred embodiment, with reference to the preferred embodiment to of the invention real
The technical solution for applying example illustrates.
The technical solution of the embodiment of the present invention can solve the problems, such as how to determine the fault type of high voltage isolator.Every
It leaves the characteristic parameter closed in the motor current waveform that different types of machine performance is influenced to be different, same type
Machine performance different faults degree can make characteristic parameter amplitude different.By close a floodgate, separating brake keeps apart powered-down behaviour
Current amplitude is detected during making, the value of the default parameter and electric parameter under normal circumstances of testing result is compared, and is judged
Whether corresponding failure is occurred.
High voltage isolator machine performance detection final purpose be in order to according to detection signal characteristic parameter variation come
Detection and isolation switchs state in which, i.e., occurs or will occur either with or without failure.Common mode identification method has：Manually
Neural network, support vector machine method.The embodiment of the present invention carries out the Classification and Identification of machine performance using algorithm of support vector machine.
1. algorithm of support vector machine
The theoretical foundation of algorithm of support vector machine is Statistical Learning Theory, can be used to handle non-linear, small sample, higher-dimension mould
Many problems such as formula identification.Algorithm of support vector machine (Support Vector Machine, abbreviation SVM) is 1992-1995
What Vapnik et al. was drawn after the abundant Research statistics theories of learning.The algorithm ties up theory with the VC of Statistical Learning Theory
Source, in the case of Finite Samples, the complexity and study accuracy rate of comprehensive constructed model obtain optimal model.Branch
The extension use scope for holding vector machine algorithm is very wide.
Algorithm of support vector machine includes supporting vector classification (Support Vector Classification, abbreviation SVC)
Algorithm and support vector regression (Support Vector Regression, abbreviation SVR) algorithm.What the embodiment of the present invention solved
Problem is support vector cassification problem.SVM changes the thought of the attention reduction dimension of usual method, will be super flat in lower dimensional space
The separated nonlinear problem of two class samples can not be mapped to higher dimensional space by face with kernel function, non-thread in such lower dimensional space
Sex chromosome mosaicism is changing to the linear problem in higher dimensional space, can obtain the hyperplane equation for dividing two class samples.Although supporting
Vector machine is nonlinear problem to be solved in higher dimensional space, but VC dimensions are not high, so over-fitting will not occur, when can
It can also be predicted under certain accuracy rate when being lacked with sample.
This algorithm is a kind of sorting technique based on statistical learning, and core is that sample is mapped directly to using kernel function
High-dimensional feature space, constructs optimum linearity Optimal Separating Hyperplane within this space, and the selection of kernel function is to determine the pass of classifying quality
Key.In use more classification problems can be converted to two classification problems of " one-to-many ", the selection of feature vector is also answered
Properly, for example, using wavelet packet decomposition node greatest coefficient.
Many parameters can all influence the sort feature of support vector machines, it is most important have it is following two:
(1) influence of penalty parameter c
Penalty parameter c is the contradiction for adjusting algorithm complexity and sample misclassification probability, must make machine learning as far as possible
Empiric risk it is small, fiducial range is big, Generalization Ability is strong.The numerical value of c can change with the difference of particular problem, while data
Accuracy (having error free) changes it is also possible that obtaining c values.C values are smaller, illustrate to experience error punish it is small, experience wind can be made
Danger increases and model is simple；If c values are infinity, SVM needs to meet all constraints, for each training sample
Accurate classification is wanted, finally so that Generalization Ability dies down.For any one proper subspace, has more than one c values and make
The Generalization Ability of support vector machines reaches best.When c is more than certain value, SVM can become very complicated, Generalization Ability, experience wind
Danger is constant.
(2) kernel function form, the use of parameter
Kernel function plays a part of porter, and the sample compared with low-dimensional is transported to higher dimensional space, the dimension of proper subspace
Number is directly related to the size of experience error and linear classification face VC ties up attainable maximum.Proper subspace is super with classification
Plane corresponds, and when the dimension of proper subspace is relatively high, obtained optimal classification surface will not be too simple, and empiric risk is small
But fiducial range is big；When the dimension of proper subspace is relatively low, the optimal classification surface of acquisition can be slightly simple, but fiducial range meeting
Become smaller, empiric risk can increase.In the case of both the above, SVM Generalization Abilities are all limited.Each kernel function can have core ginseng
Number, has reacted the distribution situation that sample data is mapped to after high-dimensional feature space indirectly.It is exactly to change indirectly to change nuclear parameter
The ease that data are distributed in high dimensional feature subspace is become, nuclear parameter value is directly related to the accuracy rate of learning training.
Algorithm of support vector machine is initially that linear can timesharing acquisition optimal classification surface (Optimal Hyperplane)
Purpose come out.It says that classifying face is optimal to seek to correctly classify to sample in fact, while making two class samples as far as possible
Away from each other.In embodiments of the present invention, sample is all linear separability, and discriminant function is g (x)=wTX+b, classifying face equation
For wTX+b=0 will make two class samples be satisfied by constraint | g (x) | >=1, and it needs to do normalization transformation to linear discriminant function, | g
(x) |=1 illustrates that the sample is nearest from classifying face.When classifying face meets conditions above, two class samples can be divided completely
Class, supporting vector (Support Vectors) are from the immediate sample of classifying face.The classification gap (Margin) of two class samples
For：
Margin=2/ | | w | |
Known classifying face will thus be become the problem of optimal classification surface found and meet yi(wTx,i+ b) -1 >=0, i=1,
2 ..., n obtain function：
The minimum number got.Define Lagrange functions：
αi>=0 is Lagrange coefficient, and work below is to seek Lagrange functional minimum values to w and b.By glug
Bright day Multiplier Method obtains：
Initial problem just changes the dual problem for convex quadratic programming：
Above formula is the quadratic function mechanism problem under the conditions of an inequality constraints, existence anduniquess optimal solution.If αi *For
Optimal solution, then
Supporting vector is exactly αiThe linear combination of the sample being not zero, supporting vector constitutes the weight coefficient of optimal classification surface
Vector.By constraints αi B can be acquiredi *, the optimal classification function that can be acquired is：
Common kernel function form and existing algorithm have relativeness, predominantly following three classes：
(1) Polynomial kernel function, corresponding SVM is a q rank multinomial grader.It is expressed as：
K(x,xi)=[(xTxi)+1]q
(2) RBF kernel functions, corresponding SVM is a kind of radial basis function classifiers, is expressed as：
(3) S-shaped kernel function, SVM are exactly two layers of perceptron neural network, and algorithm will automatically determine the hidden node of network
The weights of number, network.It is expressed as：K(x,xi)=tanh (v (xTxi)+c)
Different kernel functions can be selected according to the difference that data analysis requires, RBF kernel function abilities are stronger, in engineering
Using more.
2. high voltage isolator machine performance diagnoses
Failure is set by experiment, the characteristic parameters such as extraction characteristic time, electric current, angle, final purpose to be achieved is just
It is the machine performance identified by the classification of these characteristic parameters is handled residing for high voltage isolator.High voltage isolator
Operating mechanism is driven by motor output shaft, motor output torque drive transmission shaft and it is a series of be in intermediate ring
The machine driving bar of section, it is final to drive the rotation porcelain vase rotation of disconnecting switch three-phase.The action whole process of high voltage isolator
Power resources are all the torque of motor output, under the precondition that motor power is stablized, motor output torque size
It is closely related with current of electric, that is, motor current signal can largely reflect during isolator operation
The size of the moment of resistance (i.e. between transmission mechanism, the torque etc. of rotation porcelain vase rotary course and dynamic/static contact when being in contact).
In view of motor current signal survival is during entire isolator operation, and compared to fracture signal and angle
The characteristic parameter spent contained by signal is more, and the variation of these parameters is more apparent, is more suitably applied to the inspection of disconnecting switch state
In survey.Fig. 2 is the motor current waveform comparison diagram that making process measurement obtains under different conditions, as shown in Fig. 2, in parallel zone
It is current amplitudes normal, that B phases bite, position of closing a floodgate, limit delay are under four kinds of different conditions from top to down.
The motor current signal measured under high voltage isolator normal mechanical state is the intrinsic spy of the model disconnecting switch
Sign, is compared as the standard under other machine performances.If the machine performance of high voltage isolator changes, electronic
Machine output is bound to be affected, and then can be reflected in above motor current waveform, and motor current signal waveform at this moment
More normal machine performance centainly changes.If the machine performance of high voltage isolator is unknown, but there is mechanical normal condition
Under motor current waveform library can be as a contrast, so that it may with by measuring motor current signal at this time, and with normal shape
Motor current waveform under state compares, and the machine residing for current disconnecting switch then can be judged according to the difference on waveform
Tool state.
Have to the characteristic parameter of motor current signal when the double-fracture disconnecting switch mechanical property of the embodiment of the present invention
It is described, examine these parameters closely again here, Fig. 3 is separating brake current waveform pair under different conditions according to the ... of the embodiment of the present invention
Than figure, as shown in figure 3, being followed successively by normal, B phases bite, position of closing a floodgate, limit delay from top to bottom under four kinds of different conditions
Current amplitude, it can be found that situation of change of each parameter in different disconnecting switch machine performances is different.
Fig. 4 is the schematic diagram of switching current characteristic parameter under different conditions according to the ... of the embodiment of the present invention, as shown in figure 4,
In high voltage isolator making process, it is I4 to change most apparent characteristic parameter compared to normal condition when bite occurs for B phases, i.e.,
When there is bite generation, the moment of resistance between dynamic/static contact obviously increases, and the output torque of motor also accordingly increases, and is reflected in
It is the increase of current amplitude in motor current waveform.Current amplitude increase is characteristic parameter I4, rather than characteristic parameter I3 and
Current amplitude at I2 or other positions, this is because T3 moment dynamic/static contacts just contact, the output of motor before this
The operation of torque and disconnecting switch does not have difference with normal condition, and the T3-T5 moment is then moving contact reeve static contact fingertip
Interior process, due to the presence of bite so that entirely the current of electric amplitude during this increases.
Fig. 5 is the schematic diagram of separating brake current characteristic parameter under different conditions according to the ... of the embodiment of the present invention, as shown in figure 5,
High voltage isolator closed a floodgate, and to change more apparent characteristic parameter compared to normal condition be the T3 moment for position, and this feature parameter subtracts
Small more apparent, i.e. moving contact and fixed contact of isolating switch time of contact shifts to an earlier date, and time of contact extends.And such defect type reflection
It is separating brake delay in separating brake process, i.e. rigid separation moment of dynamic/static contact during separating brake is delayed.
The characteristic parameter that high voltage isolator limit switch acts delayed impact is the T5 moment, this is because limit switch
Effect is cut-out motor power, at the time of showing that as current of electric becomes zero in motor current waveform.The work of limit switch
With determining that survival time of current of electric increases when limit switch action is lagged, and to motor electricity before this
Stream signal waveform does not influence, it is simply that the action of limit switch only influences the cut-out moment of current of electric.
The above analysis is it can be seen that disconnecting switch is in the motor current waveform that different types of machine performance is influenced
Characteristic parameter be different, same type machine performance different faults degree can make characteristic parameter amplitude different.
Due to analyze above only qualitatively description, do not embody specifically, thus the embodiment of the present invention using support to
Amount machine method carries out Classification and Identification.The input data of this method is the characteristic parameter extracted during current of electric divide-shut brake
And class indication (1,2,3,4 etc.；Each number represents a kind of machine performance), output is then classification results.Supporting vector
The identification process of machine method is will to measure the first half of the data under each obtained state as training sample, later half conduct
Test sample.The embodiment of the present invention selects radial basis function as kernel function, this is because compared to Polynomial kernel function and
Sigmoid functions, only 1 parameter, model is relatively simple, the less-restrictive of logarithm.Support vector machines needs to select opposite
The parameter σ of preferable penalty parameter c and Radial basis kernel function promotes the classification performance of support vector machines, and the present embodiment selects
Particle group optimizing method carries out the optimizing of two parameters.
Particle swarm optimization algorithm is a kind of Swarm Intelligence Algorithm of simulation birds predation, is sought by iteration to realize
Excellent, iterative process, particle update the position and speed of oneself by tracking individual extreme value and global extremum each time.Specifically
For, it is exactly that this method generates a group particle at random in solution space, each particle is a solution of solution space, by
Object function determines the fitness of each particle.Each particle moves in solution space, and population follows current optimal grain
Son carries out obtaining optimal solution by generation search.Fig. 6 is a kind of fast trip fitness curve of particle group optimizing according to the ... of the embodiment of the present invention
Figure, as shown in fig. 6, the optimizing result of penalty factor c and kernel functional parameter σ, the g in figure is kernel functional parameter σ.It is best suitable
Response is close to 100, and average fitness is about 80.
After the selection that have passed through certain algebraically, it is 35.7806 and core letter to have obtained best penalty factor parameter c
Number parameter σ is 0.8525.Then parameter value is applied in the classification of support vector machines, Fig. 7 is according to the ... of the embodiment of the present invention
The schematic diagram of combined floodgate testing classification result, Fig. 8 are the schematic diagrames of combined floodgate testing classification result according to the ... of the embodiment of the present invention, are such as schemed
Shown, what axis of abscissas represented is test sample, ordinate representative sample generic, wherein ' 1 ' represents normal condition, ' 2 '
B phase bite states are represented, ' 3 ' represent position state of closing a floodgate, and ' 4 ' represent limit switch delay voltage.Great circle represents the test
The practical generic of sample, and small circle then represents the classification results of the test sample.Open a sluice gate and combined floodgate red circle with blue
It is correct that circle all overlaps representative classification.
The embodiment of the present invention realizes the correct knowledge to high voltage isolator machine performance using the method for support vector machines
Not, it was demonstrated that motor current signal can be detected as the machine performance of high voltage isolator.
The technical solution of the embodiment of the present invention can approach the fault type for how determining high voltage isolator.Disconnecting switch
Characteristic parameter in the motor current waveform that different types of machine performance is influenced is different, same type mechanical-like
State different faults degree can make characteristic parameter amplitude different.Pass through the electrically operated process of disconnecting switch in combined floodgate, separating brake
The value of the default parameter and electric parameter under normal circumstances of testing result is compared, judges whether to send out by middle detection current amplitude
Raw corresponding failure.
It should be noted that step shown in the flowchart of the accompanying drawings can be in such as a group of computer-executable instructions
It is executed in computer system, although also, logical order is shown in flow charts, and it in some cases, can be with not
The sequence being same as herein executes shown or described step.
An embodiment of the present invention provides a kind of high voltage isolator failure determination device, which can be used for executing this hair
The high voltage isolator fault determination method of bright embodiment.
Fig. 9 is the schematic diagram of high voltage isolator failure determination device according to the ... of the embodiment of the present invention, as shown in figure 9, should
Device includes：
First acquisition unit 10, for obtaining motor current signal, wherein motor high voltage isolator to be measured in order to control
Motor；
Comparing unit 20, for carrying out feature according to motor current signal and the current signal of preset different faults state
It compares；
Judging unit 30, for aspect ratio to it is successful in the case of, judge high voltage isolator for corresponding failure shape
State.
The embodiment uses first acquisition unit 10, for obtaining motor current signal, wherein motor height to be measured in order to control
Press the motor of disconnecting switch；Comparing unit 20, for being believed according to motor current signal and the electric current of preset different faults state
Number carry out aspect ratio pair；Judging unit 30, for aspect ratio to it is successful in the case of, judge high voltage isolator to be corresponding
Malfunction solves the problems, such as that efficiency is low when high voltage isolator failure, and then has reached the detection of raising high voltage isolator
The effect of efficiency.
Optionally, comparing unit 20 is used for：By the wave character of motor current signal and preset normal current signal
Wave character carries out aspect ratio pair.
Optionally, which further includes：Second acquisition unit, for according to motor current signal and preset Bu Tong event
The current signal of barrier state carries out aspect ratio to before, obtaining the current signal parameter under each malfunction；Training unit is used
According to the current signal parameter training model under each malfunction, trained model is obtained；Wherein, according to motor electricity
The current signal for flowing signal and preset different faults state carries out aspect ratio to including：By trained model to motor electricity
Stream signal is identified, and obtains recognition result.
Optionally, the kernel function of model is radial basis function, which further includes：Optimize unit, for being trained
After good model, penalty to model and optimized with the parameter of radial basis function, the punishment letter after being optimized
Parameter several and with the radial basis function after optimization；Processing unit, for according to after optimization penalty and and optimization after
The parameter of radial basis function optimized after model.
The high voltage isolator failure determination device includes processor and memory, above-mentioned first acquisition unit, comparison
Unit, judging unit etc. are used as program unit storage in memory, are executed by processor stored in memory above-mentioned
Program unit realizes corresponding function.
Include kernel in processor, is gone in memory to transfer corresponding program unit by kernel.Kernel can be arranged one
Or more, improve high voltage isolator detection efficiency by adjusting kernel parameter.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, if read-only memory (ROM) or flash memory (flash RAM), memory include at least one deposit
Store up chip.
An embodiment of the present invention provides a kind of storage mediums, are stored thereon with program, real when which is executed by processor
The existing high voltage isolator fault determination method.
An embodiment of the present invention provides a kind of processor, the processor is for running program, wherein described program is run
High voltage isolator fault determination method described in Shi Zhihang.
An embodiment of the present invention provides a kind of equipment, equipment include processor, memory and storage on a memory and can
The program run on a processor, processor realize following steps when executing program：Obtain motor current signal, wherein motor
The motor of high voltage isolator to be measured in order to control；According to motor current signal and the current signal of preset different faults state into
Row aspect ratio pair；Aspect ratio to it is successful in the case of, judge high voltage isolator for corresponding malfunction.Herein sets
Standby can be server, PC, PAD, mobile phone etc..
Present invention also provides a kind of computer program products, when being executed on data processing equipment, are adapted for carrying out just
The program of beginningization there are as below methods step：Obtain motor current signal, wherein the electricity of motor high voltage isolator to be measured in order to control
Machine；Aspect ratio pair is carried out according to motor current signal and the current signal of preset different faults state；In aspect ratio to success
In the case of, judge high voltage isolator for corresponding malfunction.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, the application can be used in one or more wherein include computer usable program code computer
The computer program production implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application is with reference to method, the flow of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that can be realized by computer program instructions every first-class in flowchart and/or the block diagram
The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided
Instruct the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine so that the instruction executed by computer or the processor of other programmable data processing devices is generated for real
The device for the function of being specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that instruction generation stored in the computer readable memory includes referring to
Enable the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device so that count
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, in computer or
The instruction executed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, computing device includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include computer-readable medium in volatile memory, random access memory (RAM) and/
Or the forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable Jie
The example of matter.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology realizes information storage.Information can be computer-readable instruction, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase transition internal memory (PRAM), static RAM (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), fast flash memory bank or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storages, magnetic tape cassette, tape magnetic disk storage or other magnetic storage apparatus
Or any other non-transmission medium, it can be used for storage and can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
Including so that process, method, commodity or equipment including a series of elements include not only those elements, but also wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including element
There is also other identical elements in process, method, commodity or equipment.
It will be understood by those skilled in the art that embodiments herein can be provided as method, system or computer program product.
Therefore, complete hardware embodiment, complete software embodiment or embodiment combining software and hardware aspects can be used in the application
Form.It is deposited moreover, the application can be used to can be used in the computer that one or more wherein includes computer usable program code
The shape for the computer program product implemented on storage media (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
Formula.
It these are only embodiments herein, be not intended to limit this application.To those skilled in the art,
The application can have various modifications and variations.It is all within spirit herein and principle made by any modification, equivalent replacement,
Improve etc., it should be included within the scope of claims hereof.
Claims (10)
1. a kind of high voltage isolator fault determination method, which is characterized in that including：
Obtain motor current signal, wherein the motor of motor high voltage isolator to be measured in order to control；
Aspect ratio pair is carried out according to the motor current signal and the current signal of preset different faults state；
Aspect ratio to it is successful in the case of, judge the high voltage isolator for corresponding malfunction.
2. according to the method described in claim 1, it is characterized in that, according to the motor current signal and preset normal current
Signal carries out aspect ratio to including：
The wave character of the wave character of the motor current signal and preset normal current signal is subjected to aspect ratio pair.
3. according to the method described in claim 1, it is characterized in that, according to the motor current signal and preset Bu Tong event
The current signal of barrier state carries out aspect ratio to before, and the method further includes：
Obtain the current signal parameter under each malfunction；
According to the current signal parameter training model under each described malfunction, trained model is obtained；
Wherein, aspect ratio is being carried out to packet according to the motor current signal and the current signal of preset different faults state
It includes：Motor current signal is identified by the trained model, obtains recognition result.
4. according to the method described in claim 3, it is characterized in that, the kernel function of the model be radial basis function, obtaining
After trained model, the method further includes：
It penalty to model and is optimized with the parameter of radial basis function, the penalty after being optimized and and optimization
The parameter of radial basis function afterwards；
According to after optimization penalty and and optimization after radial basis function parameter optimized after model.
5. a kind of high voltage isolator failure determination device, which is characterized in that including：
First acquisition unit, for obtaining motor current signal, wherein the electricity of motor high voltage isolator to be measured in order to control
Machine；
Comparing unit, for carrying out aspect ratio according to the motor current signal and the current signal of preset different faults state
It is right；
Judging unit, for aspect ratio to it is successful in the case of, judge the high voltage isolator for corresponding malfunction.
6. device according to claim 5, which is characterized in that the comparing unit is used for：
The wave character of the wave character of the motor current signal and preset normal current signal is subjected to aspect ratio pair.
7. device according to claim 5, which is characterized in that described device further includes：
Second acquisition unit, for according to the motor current signal and the progress of the current signal of preset different faults state
Aspect ratio is to before, obtaining the current signal parameter under each malfunction；
Training unit, for according to the current signal parameter training model under each described malfunction, obtaining trained mould
Type；
Wherein, aspect ratio is being carried out to packet according to the motor current signal and the current signal of preset different faults state
It includes：Motor current signal is identified by the trained model, obtains recognition result.
8. device according to claim 7, which is characterized in that the kernel function of the model is radial basis function, the dress
It sets and further includes：
Optimize unit, for after obtaining trained model, penalty to model and and radial basis function parameter
It optimizes, the penalty after being optimized and the parameter with the radial basis function after optimization；
Processing unit, for according to after optimization penalty and and optimization after radial basis function parameter optimized after
Model.
9. a kind of storage medium, which is characterized in that the storage medium includes the program of storage, wherein run in described program
When control the storage medium where equipment perform claim require the high voltage isolator failure described in any one of 1 to 4 true
Determine method.
10. a kind of processor, which is characterized in that the processor is for running program, wherein right of execution when described program is run
Profit requires the high voltage isolator fault determination method described in any one of 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711446553.XA CN108318810B (en) | 2017-12-27 | 2017-12-27 | High-voltage isolating switch fault determination method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711446553.XA CN108318810B (en) | 2017-12-27 | 2017-12-27 | High-voltage isolating switch fault determination method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108318810A true CN108318810A (en) | 2018-07-24 |
| CN108318810B CN108318810B (en) | 2021-07-20 |
Family
ID=62893391
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711446553.XA Active CN108318810B (en) | 2017-12-27 | 2017-12-27 | High-voltage isolating switch fault determination method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108318810B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110068759A (en) * | 2019-05-22 | 2019-07-30 | 四川华雁信息产业股份有限公司 | A kind of fault type preparation method and device |
| CN111679184A (en) * | 2020-07-06 | 2020-09-18 | 国家电网有限公司 | Method for evaluating performance of isolating switch through motor current |
| CN111950448A (en) * | 2020-08-11 | 2020-11-17 | 平高集团有限公司 | High-voltage isolating switch fault state detection method and device based on machine vision |
| CN113189480A (en) * | 2021-04-22 | 2021-07-30 | 西安交通大学 | Fault diagnosis method and device in closing/opening process of isolating switch |
| CN117368718A (en) * | 2023-12-06 | 2024-01-09 | 浙江万胜智能科技股份有限公司 | Fault monitoring and early warning method and system of measuring switch |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012181579A (en) * | 2011-02-28 | 2012-09-20 | National Institute Of Information & Communication Technology | Pattern classification learning device |
| CN103913698A (en) * | 2014-03-27 | 2014-07-09 | 长沙学院 | Switching current circuit fault diagnosis method based on wavelet fractal and kernel principal characteristics |
| CN106771999A (en) * | 2016-11-24 | 2017-05-31 | 云南电网有限责任公司电力科学研究院 | A kind of high voltage isolator mechanical fault detection device and detection method |
| CN106934157A (en) * | 2017-03-13 | 2017-07-07 | 国网江苏省电力公司电力科学研究院 | Primary cut-out recognition methods based on SVMs and Dynamics Simulation |
-
2017
- 2017-12-27 CN CN201711446553.XA patent/CN108318810B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012181579A (en) * | 2011-02-28 | 2012-09-20 | National Institute Of Information & Communication Technology | Pattern classification learning device |
| CN103913698A (en) * | 2014-03-27 | 2014-07-09 | 长沙学院 | Switching current circuit fault diagnosis method based on wavelet fractal and kernel principal characteristics |
| CN106771999A (en) * | 2016-11-24 | 2017-05-31 | 云南电网有限责任公司电力科学研究院 | A kind of high voltage isolator mechanical fault detection device and detection method |
| CN106934157A (en) * | 2017-03-13 | 2017-07-07 | 国网江苏省电力公司电力科学研究院 | Primary cut-out recognition methods based on SVMs and Dynamics Simulation |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110068759A (en) * | 2019-05-22 | 2019-07-30 | 四川华雁信息产业股份有限公司 | A kind of fault type preparation method and device |
| CN110068759B (en) * | 2019-05-22 | 2021-11-09 | 华雁智能科技(集团)股份有限公司 | Fault type obtaining method and device |
| CN111679184A (en) * | 2020-07-06 | 2020-09-18 | 国家电网有限公司 | Method for evaluating performance of isolating switch through motor current |
| CN111950448A (en) * | 2020-08-11 | 2020-11-17 | 平高集团有限公司 | High-voltage isolating switch fault state detection method and device based on machine vision |
| CN111950448B (en) * | 2020-08-11 | 2024-02-02 | 平高集团有限公司 | High-voltage isolating switch fault state detection method and device based on machine vision |
| CN113189480A (en) * | 2021-04-22 | 2021-07-30 | 西安交通大学 | Fault diagnosis method and device in closing/opening process of isolating switch |
| CN117368718A (en) * | 2023-12-06 | 2024-01-09 | 浙江万胜智能科技股份有限公司 | Fault monitoring and early warning method and system of measuring switch |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108318810B (en) | 2021-07-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108318810A (en) | High voltage isolator fault determination method and device | |
| Balouji et al. | A LSTM-based deep learning method with application to voltage dip classification | |
| Shi et al. | Power system event identification based on deep neural network with information loading | |
| CN108051660A (en) | A kind of transformer fault combined diagnosis method for establishing model and diagnostic method | |
| CN101464964B (en) | Pattern recognition method capable of holding vectorial machine for equipment fault diagnosis | |
| CN107103332A (en) | A kind of Method Using Relevance Vector Machine sorting technique towards large-scale dataset | |
| CN110059714A (en) | Diagnosis Method of Transformer Faults based on multi-category support vector machines | |
| CN110705831A (en) | Power angle instability mode pre-judgment model construction method after power system fault and application thereof | |
| Shukla et al. | Power quality disturbances classification based on Gramian angular summation field method and convolutional neural networks | |
| Moravej et al. | Power transformer protection scheme based on time‐frequency analysis | |
| Todeschini et al. | An image-based deep transfer learning approach to classify power quality disturbances | |
| Ghaemi et al. | Situational awareness and deficiency warning system in a smart distribution network based on stacking ensemble learning | |
| Høiem et al. | Comparative study of event prediction in power grids using supervised machine learning methods | |
| Bodda et al. | Comparative Analysis of Deep Learning and Machine Learning Techniques for Power System Fault type Classification and Location Prediction | |
| CN110874652B (en) | Equipment state evaluation method, device, equipment and system | |
| Wang et al. | Research on transformer fault diagnosis based on GWO-RF algorithm | |
| Moreira et al. | Evaluation of pattern recognition algorithms for applications on power factor compensation | |
| Khodabandehlou et al. | Anomaly classification in distribution networks using a quotient gradient system | |
| Zhang et al. | Transformer fault diagnosis based on support vector machine | |
| KR20220069782A (en) | An intelligent system for power transformer fault diagnosis | |
| Coelho et al. | Approximate linear dependence as a design method for kernel prototype-based classifiers | |
| Pamir et al. | Electricity theft detection for energy optimization using deep learning models | |
| Faisal et al. | Support vector regression based S-transform for prediction of single and multiple power quality disturbances | |
| Ma et al. | Power transformer insulation diagnosis under measurement originated uncertainties | |
| Kim et al. | Cyberattack Detection in Smart Grids based on Reservoir Computing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |