CN115308674A - Method and system for evaluating epitope running state of automatic verification assembly line of electric energy meter - Google Patents
Method and system for evaluating epitope running state of automatic verification assembly line of electric energy meter Download PDFInfo
- Publication number
- CN115308674A CN115308674A CN202210911537.8A CN202210911537A CN115308674A CN 115308674 A CN115308674 A CN 115308674A CN 202210911537 A CN202210911537 A CN 202210911537A CN 115308674 A CN115308674 A CN 115308674A
- Authority
- CN
- China
- Prior art keywords
- epitope
- state
- state evaluation
- electric energy
- energy meter
- 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 41
- 238000012795 verification Methods 0.000 title claims abstract description 31
- 238000012360 testing method Methods 0.000 claims abstract description 38
- 238000013528 artificial neural network Methods 0.000 claims abstract description 32
- 238000013210 evaluation model Methods 0.000 claims abstract description 32
- 238000011156 evaluation Methods 0.000 claims abstract description 31
- 241000272168 Laridae Species 0.000 claims abstract description 29
- 239000013598 vector Substances 0.000 claims abstract description 26
- 230000002159 abnormal effect Effects 0.000 claims abstract description 25
- 230000000694 effects Effects 0.000 claims abstract description 22
- 238000005457 optimization Methods 0.000 claims abstract description 22
- 238000004519 manufacturing process Methods 0.000 claims abstract description 8
- 241000196252 Ulva Species 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 4
- 230000015556 catabolic process Effects 0.000 abstract description 2
- 238000006731 degradation reaction Methods 0.000 abstract description 2
- 238000011835 investigation Methods 0.000 abstract 1
- 241000272161 Charadriiformes Species 0.000 description 9
- 238000013508 migration Methods 0.000 description 4
- 230000005012 migration Effects 0.000 description 4
- 238000013507 mapping Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011524 similarity measure Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000002788 crimping Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 244000062804 prey Species 0.000 description 1
Images
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
- G01R35/04—Testing or calibrating of apparatus covered by the other groups of this subclass of instruments for measuring time integral of power or current
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a system for evaluating the epitope running state of an electric energy meter automatic verification assembly line, which comprises the following steps: acquiring historical test data of the epitopes on the verification production line under different running states, removing batch effects of the historical test data on the basis of normal epitope data, and constructing feature vectors of the epitopes under different running states; constructing a twin neural network, updating network parameters by setting boundary values when the twin neural network is trained based on the feature vectors of all epitopes, and constructing a state evaluation model by introducing a state judgment threshold; performing parameter optimization on the state evaluation model by adopting an Ulva gull optimization algorithm and taking the model evaluation reliability as a fitness function to obtain an optimized state evaluation model; and performing state evaluation on the epitope to be tested by adopting the optimized state evaluation model. The method effectively identifies the abnormal state of the epitope caused by performance degradation, and solves the problems of insufficient reliability and high labor cost in the traditional manual investigation.
Description
Technical Field
The invention relates to the technical field of electric power metering online monitoring, in particular to an electric energy meter automatic verification assembly line epitope running state evaluation method and system.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The automatic electric energy meter verification assembly line provides guarantee for normal operation of the intelligent electric energy meter, however, in the long-term operation process of the assembly line, the intelligent electric energy meter is frequently connected with the meter position, and deformation of a meter position mechanical compression joint terminal can be caused; meanwhile, long-term live operation can accelerate the oxidation speed of the surface material of the mechanical crimping terminal, so that the terminal is corroded. The deformation and corrosion of the mechanical compression joint link of the meter position directly affect the reliability of the error test result, and further affect the verification quality of the intelligent electric energy meter. The current manual regular detection method cannot timely respond to abnormal working conditions occurring in the operation and maintenance interval of the production line.
Disclosure of Invention
In order to solve the problems, the invention provides an electric energy meter automatic verification assembly line epitope running state evaluation method and system, which effectively identify the abnormal state of an epitope caused by performance degradation, overcome the problems of insufficient reliability and high labor cost of the traditional manual check and realize the online judgment of the verification assembly line epitope state.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the invention provides an electric energy meter automatic verification assembly line epitope running state evaluation method, which comprises the following steps:
acquiring historical test data of the epitopes on a verification production line under different running states, removing batch effects on the historical test data on the basis of normal epitope data, and constructing feature vectors of the epitopes under different running states;
constructing a twin neural network, updating network parameters by setting boundary values when the twin neural network is trained based on the feature vectors of all epitopes, and constructing a state evaluation model by introducing a state judgment threshold;
performing parameter optimization on the state evaluation model by adopting an Ulva gull optimization algorithm and taking the model evaluation reliability as a fitness function to obtain an optimized state evaluation model;
and performing state evaluation on the epitope to be detected by adopting the optimized state evaluation model.
As an alternative embodiment, based on normal epitope data, batch effect removal is performed using a mean-centric approach;
wherein epsilon ik The test result of the kth test for the ith epitope,
the test result after the kth test batch effect of the ith epitope is removed;
error for the kth trial batch effect.
As an alternative embodiment, the twin neural network uses a contrast loss function L loss Training is carried out:
wherein margin is a boundary value, D (x) 1 ,x 2 ) Is a sample x 1 、x 2 Y is the label corresponding to the support set, and Q is the number of support sets.
As an alternative embodiment, the fitness function K is:
wherein H 0 To observe the coincidence rate, a 1 、a 2 、a 3 Respectively representing the number of samples which are actually normal, alarm and abnormal and are predicted to be normal, alarm and abnormal, S is the total number of samples, H e Representing chance coincidence rate, b 1 、b 2 、b 3 The actual number of normal, alarm and abnormal samples, c 1 、c 2 、c 3 The numbers of samples predicted to be normal, alarm and abnormal are respectively.
In an alternative embodiment, the parameter optimization process is to optimize the boundary values and the state decision thresholds.
As an alternative embodiment, a nonlinear control parameter a is proposed in the gull optimization algorithm:
wherein f is c For the parameters controlling the frequency a, R is the number of iterations and R is the maximum number of iterations.
As an alternative embodiment, a to-be-detected sample pair is generated by a to-be-detected sample of the to-be-detected epitope and a known state sample, the similarity between the to-be-detected sample and the known state sample is calculated, the similarity mean value in each operating state is taken as the final similarity, and the epitope state judgment of the to-be-detected sample is carried out according to the final similarity and the state judgment threshold.
In a second aspect, the present invention provides an electric energy meter automatic verification assembly line epitope running state evaluation system, including:
the training set acquisition module is configured to acquire historical test data of the epitopes on the verification production line in different running states, remove batch effects on the historical test data on the basis of normal epitope data, and construct feature vectors of the epitopes in different running states;
the model building module is configured to build a twin neural network, update network parameters by setting boundary values when the twin neural network is trained on the basis of the feature vectors of all epitopes, and build a state evaluation model by introducing a state judgment threshold;
the parameter optimizing module is configured to adopt an Ulva gull optimization algorithm, and perform parameter optimizing on the state evaluation model by taking the model evaluation reliability as a fitness function to obtain an optimized state evaluation model;
and the state evaluation module is configured to carry out state evaluation on the epitope to be tested by adopting the optimized state evaluation model.
In a third aspect, the present invention provides an electronic device comprising a memory and a processor, and computer instructions stored on the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method of the first aspect is performed.
In a fourth aspect, the present invention provides a computer readable storage medium for storing computer instructions which, when executed by a processor, perform the method of the first aspect.
Compared with the prior art, the invention has the following beneficial effects:
according to the method and the system for evaluating the running state of the epitope of the automatic verification assembly line of the electric energy meter, the running state of the epitope of the automatic verification assembly line of the electric energy meter is judged by adopting the twin neural network, so that the problem of small sample learning is solved.
According to the method and the system for evaluating the epitope running state of the automatic verification assembly line of the electric energy meter, iterative optimization is carried out on the hyperparameter boundary value and the threshold value introduced by the twin depth neural network and the state judgment mechanism by adopting the Woofer optimization algorithm, and the accuracy and the reliability of model evaluation are improved.
According to the method and the system for evaluating the epitope running state of the automatic verification assembly line of the electric energy meter, batch effect elimination is adopted, distribution differences of test data possibly existing in electric energy meters of different batches are eliminated, and a feature vector with error expectation as a time sequence feature is constructed.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a flowchart of an evaluation method for automatically verifying an epitope running state of an assembly line of an electric energy meter according to embodiment 1 of the present invention;
fig. 2 is a diagram of a state estimation model provided in embodiment 1 of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. 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 invention 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 invention. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and it should be understood that the terms "comprises" and "comprising", and any variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiments and features of the embodiments of the invention may be combined with each other without conflict.
Example 1
The embodiment provides an electric energy meter automatic verification assembly line epitope running state evaluation method, as shown in fig. 1, including:
acquiring historical test data of the epitopes on the verification production line under different running states, removing batch effects of the historical test data on the basis of normal epitope data, and constructing feature vectors of the epitopes under different running states;
constructing a twin neural network, updating network parameters by setting boundary values when the twin neural network is trained based on the feature vectors of all epitopes, and constructing a state evaluation model by introducing a state judgment threshold;
performing parameter optimization on the state evaluation model by adopting a gull-shaped optimization algorithm and taking the model evaluation reliability as a fitness function to obtain an optimized state evaluation model;
and performing state evaluation on the epitope to be tested by adopting the optimized state evaluation model.
In this embodiment, the operating states include normal, alarm, and abnormal. Considering that the electric energy meters in different batches may have distribution differences of test data, in order to eliminate the influence caused by the batch differences, batch effect removal processing is performed on historical test data, specifically:
based on normal epitope data, batch effect removal is performed by adopting an average center method:
wherein epsilon ik The error test result measured by the error test of the kth item of the ith epitope,
the error test result after the kth error test batch effect of the ith epitope is removed;
wherein,
for error in error testing batch effects, n is the number of normal epitopes in the same assay unit, ε jk Error results measured for the kth error test for the jth epitope, where k error tests were performed for each epitope, k =1,2.
In this embodiment, based on the test result after the batch effect is removed, the time sequence feature vector x of each epitope in the normal, alarm, abnormal and other operating states is constructed by using the data of T days as a time window;
wherein m is the number of the electric energy meters detected by the epitope i,
representing an error result obtained by performing a kth error test on the v-th electric energy meter by using the epitope i after removing the batch effect, wherein T is the current moment, and the data of T day is formed by T and the previous T-1 day;
In the embodiment, a twin neural network is constructed by taking the feature vector of each epitope as a training set, and the state evaluation model comprises the twin neural network and a threshold judgment module; as shown in fig. 2.
The twin neural network comprises two sub neural networks with the same model parameters, and aims to measure the similarity of input samples after characteristic vectors are extracted by the sub neural networks, so that the characteristics extracted by the sub neural networks are more discriminative; specifically, the method comprises the following steps:
(1) Constructing an input sample pair (x) based on the characteristic vectors of all epitopes of the assembly line after batch effect removal 1 ,x 2 )；
Constructing a training set and a test set based on the characteristic vectors of all epitopes of the assembly line after batch effect removal, selecting part of samples from the training set to construct sample pairs to form a support set, and randomly selecting one data from the same type of data and the different type of data to form a data pair for each sample in the support set so as to form a support set;
the data composition form of the support set is as follows: normal and normal, normal and alarm, normal and abnormal, alarm and alarm, alarm and abnormal, abnormal and abnormal 6 kinds to obtain input sample pair (x) 1 ,x 2 )。
(2) The Network module in the twin neural Network adopts a 1-D CNN-LSTM sub-Network model, and obtains an input sample pair (x) based on the 1-D CNN-LSTM sub-Network model 1 ,x 2 ) Feature vector G (x) 1 ) And G (x) 2 )：
Sample x 1 、x 2 As input data, inputting the input data into two identical neural Network modules Network in a feature extraction model respectively, wherein the two neural Network modules have shared parameter weight W and bias b, and the feature extraction module inputs two input samples x 1 、x 2 Respectively mapping to the same feature space of the sub-network to obtain two input samples x 1 、x 2 Feature vector G (x) 1 )、G(x 2 )。
(3) Calculating the similarity;
the similarity measure is a measure for calculating the distance between feature vectors of two samples in a sample pair to evaluate the similarity between the two samples, and the present embodiment uses the euclidean distance to input the sample pair (x) 1 ,x 2 ) The similarity measure is:
D(x 1 ,x 2 )＝||G(x 1 )-G(x 2 )|| (6)
(4) Twin neural network using contrast loss function L loss Carrying out model training:
wherein margin is a predetermined boundary value when D (x) 1 ,x 2 ) When the value is smaller than the boundary value margin, the weight W of the twin neural network needs to be adjusted; y is the label corresponding to the support set, and Q is the number of the support sets.
When the input sample is a sample with the same input category of two sub-networks, the corresponding label is 1, so that G (x) of the feature mapping vector of the last layer is 1 ) And G (x) 2 ) The distance functions are as close as possible; when the input samples are different classes of samples, the corresponding labels are 0, so that the feature vector distance function is as far away as possible.
In the embodiment, in order to realize the judgment of the epitope state, a threshold judgment module is accessed behind the twin neural network, and the epitope state judgment of the sample to be detected is completed through a state judgment threshold beta;
generating a to-be-detected sample pair by using a to-be-detected sample and a known state sample, inputting the to-be-detected sample pair into a twin neural network to respectively calculate the similarity of the to-be-detected sample and the known state sample, and taking the sample similarity mean value in each state as the final sample similarity D W (ii) a If D is W If the beta is less than the beta, the same type is obtained; otherwise, they are heterogeneous.
In the embodiment, two new hyper-parameters margin and beta are introduced into a state evaluation model constructed based on a twin neural network and a state judgment mechanism, and the change of the two hyper-parameters margin and beta has a large influence on the evaluation performance of the state evaluation model, so that the embodiment adopts a gull optimization algorithm, takes the reliability of model evaluation as a fitness function, and carries out iterative optimization on margin and beta to improve the reliability of model state evaluation.
Mapping the initial position of the gull of the swallow to a boundary value margin and a state judgment threshold value beta, and the method comprises the following steps of:
(1) And taking the reliability K of model evaluation as a fitness function:
wherein H 0 In order to observe the rate of coincidence,
a 1 、a 2 、a 3 respectively representing the number of samples which are actually normal, alarm and abnormal and are predicted to be normal, alarm and abnormal through a model, wherein S is the total number of samples; h e The probability of the chance is shown,
wherein b is 1 、b 2 、b 3 The actual number of normal, alarm and abnormal samples, c 1 、c 2 、c 3 The number of samples predicted as normal, alarm and abnormal by the model is respectively.
(2) An gull optimization algorithm (STO), migration and attack preys are unique behaviors of gulls, and in the migration process, gulls move to the strongest gulls in a group, and then other gulls start to update the initial positions of the gulls, so that collision among the gulls needs to be avoided; specifically, the updating method of the parameters of the gull optimization algorithm (STO) is as follows:
(1) initializing population size num, maximum iteration times R, and randomly initializing the initial position of the gull;
(2) evaluating a fitness function: calculating the fitness of each gull position according to a fitness function, finding out the optimal fitness value through comparison, and determining the optimal position P of the population best (r)；
(3) Carrying out migration operation on the gull:
wherein, C s Indicating a new position that will not collide with other gulls; p s (r) represents the current position of the gull, and A is the motion mode of the gull in a given space; r represents the number of iterations; r represents the maximum iteration number; f. of c For controlling the frequency of A, where f c The value is 2, and the A is controlled to be reduced from 2 to 0; b is a random variable; m is a group of s Is the movement of the current position to the optimum positionA process; p best (r) is the global optimum position of gull; randvalue is a random number between 0 and 1; l is s Is the updated trajectory of the current location to the optimal location.
However, the linear control parameter cannot characterize the actual convergence process, which is nonlinear, and thus, the present embodiment proposes a nonlinear control parameter a:
in the method, the value A presents a nonlinear change trend in the descending process, the global optimization capability can be better improved, the position conflict between the gulls can be avoided in each iteration, and the exploration and development can be better balanced.
(4) Carrying out attack operation on the gull:
the flying height of the gull can be increased through wings in the migration process, the speed and the attack angle can also be adjusted, and the hovering behavior of the gull in the air can be defined when a prey is attacked:
wherein, x ', y ', z ' are the spiral positions of the simulated gull in the three-dimensional space, and lambda is the radius of the spiral helix; theta is [0,2 pi ]]Random angle of (d); w is a 0 ，
ω is a constant defining the shape of the helix, and this embodiment is set to 1, e is the base of the natural logarithm;
(5) updating the positions of the gulls:
P s (r+1)＝(L s ×(x′+y′+z′))×P best (r) (12)
wherein, P s (r + 1) is the updated position of Woofer, L s Is the updated trajectory of the current position to the optimal position, P best (r) is the populationAn optimal position;
(6) calculating the fitness value of each individual position of the gull and recording the global optimal value:
wherein,
representing the reliability of the model evaluation after updating the wu-gull position,
the observation coincidence rate after the position of the gull is updated,
a 1 am more 、a 2 more 、a 3 furthermore Respectively predicting the number of samples which are actually normal, alarm and abnormal after the position of the gull is updated into the number of samples which are normal, alarm and abnormal through a model, and S Furthermore, the utility model The total number of samples after updating the position of the gull;
representing the chance coincidence rate after the position of the gull is updated,
wherein b is 1 am more 、b 2 more 、b 3 furthermore The actual number of normal, alarm and abnormal samples, c 1 am more 、c 2 more 、c 3 furthermore The number of samples predicted as normal, alarm and abnormal by the model is respectively.
And the expression (13) is a specific calculation process of substituting the updated individual positions of the gull of the swallow (namely r +1 times of iteration) into the expression (8), calculating the fitness of each individual and selecting the optimal fitness.
And (3) solving a global optimum value of the fitness value in the gull group, and recording the position:
[K best P best (r+1)]＝max(K) (14)
(7) judging whether the reliability is greater than a set threshold value: if yes, using a boundary value margin mapped by the current gull position and a threshold value beta as optimal hyper-parameters of the model; and if not, updating the parameters and the optimal position of the gull optimization algorithm, and repeating the steps (3) - (7) until the maximum iteration number is met.
In this embodiment, based on the trained state evaluation model, the state of each epitope of the pipeline is determined by using the feature vector of the epitope to be detected as input.
Example 2
This embodiment provides an electric energy meter automation verification assembly line epitope running state evaluation system, includes:
the training set acquisition module is configured to acquire historical test data of the epitopes on the verification production line in different running states, remove batch effects on the historical test data on the basis of normal epitope data, and construct feature vectors of the epitopes in different running states;
the model building module is configured to build a twin neural network, update network parameters by setting boundary values when the twin neural network is trained on the basis of the feature vectors of all epitopes, and build a state evaluation model by introducing a state judgment threshold;
the parameter optimizing module is configured to adopt an Ulva gull optimization algorithm, and perform parameter optimizing on the state evaluation model by taking the model evaluation reliability as a fitness function to obtain an optimized state evaluation model;
and the state evaluation module is configured to perform state evaluation on the epitope to be tested by adopting the optimized state evaluation model.
It should be noted that the modules correspond to the steps described in embodiment 1, and the modules are the same as the corresponding steps in the implementation examples and application scenarios, but are not limited to the disclosure in embodiment 1. It should be noted that the modules described above as part of a system may be implemented in a computer system such as a set of computer executable instructions.
In further embodiments, there is also provided:
an electronic device comprising a memory and a processor and computer instructions stored on the memory and executed on the processor, the computer instructions when executed by the processor performing the method of embodiment 1. For brevity, no further description is provided herein.
It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and so on. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include both read-only memory and random access memory, and may provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.
A computer readable storage medium storing computer instructions which, when executed by a processor, perform the method described in embodiment 1.
The method in embodiment 1 may be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor. The software modules may be located in ram, flash, rom, prom, or eprom, registers, etc. as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor. To avoid repetition, it is not described in detail here.
Those of ordinary skill in the art will appreciate that the various illustrative elements, i.e., algorithm steps, described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive changes in the technical solutions of the present invention.
Claims (10)
1. The method for evaluating the epitope running state of the automatic verification assembly line of the electric energy meter is characterized by comprising the following steps of:
acquiring historical test data of the epitopes on the verification production line under different running states, removing batch effects of the historical test data on the basis of normal epitope data, and constructing feature vectors of the epitopes under different running states;
constructing a twin neural network, updating network parameters by setting a boundary value when training the twin neural network based on the characteristic vector of each epitope, and constructing a state evaluation model by introducing a state judgment threshold;
performing parameter optimization on the state evaluation model by adopting an Ulva gull optimization algorithm and taking the model evaluation reliability as a fitness function to obtain an optimized state evaluation model;
and performing state evaluation on the epitope to be tested by adopting the optimized state evaluation model.
2. The method for evaluating the epitope running state of the automatic verification assembly line of the electric energy meter according to claim 1, characterized in that the batch effect removal is performed by adopting an average center method based on normal epitope data;
wherein epsilon ik Test results for the kth test for the ith epitope，
The test result after the kth test batch effect of the ith epitope is removed;
error for the k-th trial batch effect.
3. The method for evaluating the epitope running state of the automatic verification assembly line of an electric energy meter according to claim 1, wherein the twin neural network adopts a contrast loss function L loss Training is carried out:
wherein margin is a boundary value, D (x) 1 ,x 2 ) Is a sample x 1 、x 2 Y is the label corresponding to the support set, and Q is the number of the support sets.
4. The method for evaluating the epitope running state of the automatic verification assembly line of the electric energy meter according to claim 1, wherein the fitness function K is as follows:
wherein H 0 To observe the coincidence rate, a 1 、a 2 、a 3 Respectively representing the number of samples which are actually normal, alarm and abnormal and are predicted to be normal, alarm and abnormal, S is the total number of samples, H e Representing chance coincidence rate, b 1 、b 2 、b 3 The actual number of normal, alarm and abnormal samples, c 1 、c 2 、c 3 The numbers of samples predicted to be normal, alarm and abnormal are respectively.
5. The method for evaluating the epitope running state of the automatic verification assembly line of an electric energy meter according to claim 1, wherein the parameter optimizing process is optimizing a boundary value and a state judgment threshold value.
6. The method for evaluating the epitope running state of the automatic verification assembly line of the electric energy meter according to claim 1, wherein a nonlinear control parameter A is provided in the Woofer optimization algorithm:
wherein, f c For the parameters controlling the frequency a, R is the number of iterations and R is the maximum number of iterations.
7. The method for evaluating the epitope running state of the electric energy meter automatic verification assembly line according to claim 1, characterized in that a pair of samples to be tested is generated by a sample to be tested of the epitope to be tested and a sample in a known state, the similarity between the sample to be tested and the sample in the known state is calculated, the mean value of the similarities in all running states is taken as the final similarity, and the epitope state judgment of the sample to be tested is carried out according to the final similarity and a state judgment threshold.
8. Electric energy meter automated verification assembly line epitope running state evaluation system which characterized in that includes:
the training set acquisition module is configured to acquire historical test data of the epitopes on the verification production line in different running states, remove batch effects on the historical test data on the basis of normal epitope data, and construct feature vectors of the epitopes in different running states;
the model building module is configured to build a twin neural network, update network parameters by setting boundary values when the twin neural network is trained on the basis of the feature vectors of all epitopes, and build a state evaluation model by introducing a state judgment threshold;
the parameter optimizing module is configured to adopt an gull-shaped optimization algorithm, take the model evaluation reliability as a fitness function, and conduct parameter optimizing on the state evaluation model to obtain an optimized state evaluation model;
and the state evaluation module is configured to carry out state evaluation on the epitope to be tested by adopting the optimized state evaluation model.
9. An electronic device comprising a memory and a processor and computer instructions stored on the memory and executed on the processor, the computer instructions when executed by the processor performing the method of any of claims 1-7.
10. A computer-readable storage medium storing computer instructions which, when executed by a processor, perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210911537.8A CN115308674A (en) | 2022-07-28 | 2022-07-28 | Method and system for evaluating epitope running state of automatic verification assembly line of electric energy meter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210911537.8A CN115308674A (en) | 2022-07-28 | 2022-07-28 | Method and system for evaluating epitope running state of automatic verification assembly line of electric energy meter |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115308674A true CN115308674A (en) | 2022-11-08 |
Family
ID=83858346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210911537.8A Pending CN115308674A (en) | 2022-07-28 | 2022-07-28 | Method and system for evaluating epitope running state of automatic verification assembly line of electric energy meter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115308674A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116128095A (en) * | 2022-11-18 | 2023-05-16 | 中国人民解放军陆军装甲兵学院 | Method for evaluating combat effectiveness of ground-air unmanned platform |
-
2022
- 2022-07-28 CN CN202210911537.8A patent/CN115308674A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116128095A (en) * | 2022-11-18 | 2023-05-16 | 中国人民解放军陆军装甲兵学院 | Method for evaluating combat effectiveness of ground-air unmanned platform |
| CN116128095B (en) * | 2022-11-18 | 2024-05-07 | 中国人民解放军陆军装甲兵学院 | Method for evaluating combat effectiveness of ground-air unmanned platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109931678B (en) | Air conditioner fault diagnosis method based on deep learning LSTM | |
| CN109141847B (en) | Aircraft system fault diagnosis method based on MSCNN deep learning | |
| CN108920863B (en) | Method for establishing energy consumption estimation model of robot servo system | |
| CN109617888B (en) | Abnormal flow detection method and system based on neural network | |
| CN113109717B (en) | Lithium battery state of charge estimation method based on characteristic curve optimization | |
| CN117056734B (en) | Method and device for constructing equipment fault diagnosis model based on data driving | |
| CN115673596B (en) | Welding abnormity real-time diagnosis method based on Actor-Critic reinforcement learning model | |
| CN108090629A (en) | Load forecasting method and system based on nonlinear auto-companding neutral net | |
| CN112232370A (en) | Fault analysis and prediction method for engine | |
| CN115659249B (en) | Abnormality detection method for intelligent station measurement control system | |
| CN111310722A (en) | Power equipment image fault identification method based on improved neural network | |
| CN115308674A (en) | Method and system for evaluating epitope running state of automatic verification assembly line of electric energy meter | |
| CN114298134A (en) | Wind power prediction method and device and electronic equipment | |
| CN113541985A (en) | Internet of things fault diagnosis method, training method of model and related device | |
| CN113591948A (en) | Defect pattern recognition method and device, electronic equipment and storage medium | |
| CN116794547A (en) | Lithium ion battery residual service life prediction method based on AFSA-GRU | |
| CN117056678B (en) | Machine pump equipment operation fault diagnosis method and device based on small sample | |
| CN113762591A (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM counterstudy | |
| CN109187898B (en) | Soft measurement method and device for ammonia nitrogen content of water in aquaculture environment | |
| CN110705114B (en) | Ventilation fault diagnosis method without training sample | |
| CN117371608A (en) | Pig house multi-point temperature and humidity prediction method and system based on deep learning | |
| CN111695631A (en) | Method, device, equipment and medium for extracting verification fault features based on SAE | |
| CN117032080A (en) | Implementation method and application of algorithm for improving state monitoring capability of numerical control machine tool | |
| CN109389313B (en) | Fault classification diagnosis method based on weighted neighbor decision | |
| CN116415505A (en) | System fault diagnosis and state prediction method based on SBR-DBN model |
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 |