CN114814707A - Intelligent ammeter stress error analysis method, equipment, terminal and readable medium - Google Patents
Intelligent ammeter stress error analysis method, equipment, terminal and readable medium Download PDFInfo
- Publication number
- CN114814707A CN114814707A CN202111142609.9A CN202111142609A CN114814707A CN 114814707 A CN114814707 A CN 114814707A CN 202111142609 A CN202111142609 A CN 202111142609A CN 114814707 A CN114814707 A CN 114814707A
- Authority
- CN
- China
- Prior art keywords
- error
- data
- stress
- neural network
- typical
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 claims abstract description 41
- 238000013528 artificial neural network Methods 0.000 claims abstract description 40
- 239000013598 vector Substances 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 18
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 230000005856 abnormality Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 abstract description 8
- 238000004364 calculation method Methods 0.000 abstract description 6
- 238000004422 calculation algorithm Methods 0.000 abstract description 2
- 239000011159 matrix material Substances 0.000 description 18
- 230000006870 function Effects 0.000 description 12
- 238000002474 experimental method Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000000513 principal component analysis Methods 0.000 description 3
- 230000002457 bidirectional effect Effects 0.000 description 2
- 150000001875 compounds Chemical class 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002699 waste material Substances 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)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a stress error analysis method for an intelligent ammeter, and discloses equipment and a storage medium with the method. The error analysis method analyzes the relevance of various stresses and errors by using a BP neural network algorithm optimized by LM. An additional error is introduced during error modeling, so that error model correction of the intelligent electric energy meter is realized. The method of the invention does not need excessive error calculation and error fitting in the past error analysis. By adopting the PCA idea, the phenomena of over-fitting and under-fitting are not easy to occur, the error analysis efficiency is improved, and higher reliability can be ensured. Therefore, the method of the invention can lead the error predicted value of the intelligent electric energy meter to have a higher confidence interval under certain conditions and lay a foundation for the error correction work of the intelligent electric energy meter.
Description
Technical Field
The invention relates to the field of intelligent power transmission of a power grid, in particular to a method and equipment for analyzing stress errors of an intelligent electric meter and a readable medium.
Background
In the smart grid, the smart electric meter undertakes the tasks of electric energy data acquisition, metering and transmission, develops intelligent services such as a bidirectional multi-rate metering function, a user side control function, a bidirectional data communication function of multiple data transmission modes, an electricity larceny prevention function and the like, and greatly promotes information analysis, integration, optimization and information display. The perfection of the functions of the intelligent electric energy meter accords with the development trend of an intelligent power grid and new energy, and meanwhile, the development of the intelligent electric energy meter also promotes the fusion development of a physical layer and an information layer of a modern electric power system.
The difference of the structure modules of the intelligent electric energy meter, the complexity of the interior of each functional module and the diversity of topological relations among the modules enable the error condition of the intelligent electric energy meter during working to be more complex, and the error condition of the intelligent electric energy meter is difficult to be objectively and accurately described by the existing error analysis methods such as polynomial regression, a neural network method, a least square method and the like. The existing error detection method has the following two problems: on one hand, during verification, only whether the error of the electric energy meter under the reference condition meets the requirement of the accuracy grade is verified, and then the confidence interval of the measured value is estimated, so that whether the electric energy meter is qualified or not is evaluated, and the waste of useful information is caused; on the other hand, the experiment is carried out under the environmental condition of laboratory, and the situation that the service environment is various and various stresses exist under the actual working condition is not fully considered.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a stress error analysis method for an intelligent ammeter, which can reveal the internal relation between various stress factors and errors of the intelligent ammeter from the aspect of data by utilizing a Back-propagation error Back Propagation (BP) neural network optimized by an LM (Levenberg-Marquardt).
The invention also provides equipment and a storage medium with the intelligent ammeter stress error analysis method.
According to a first aspect of the invention, the method for analyzing the stress error of the intelligent ammeter is characterized by comprising the following steps:
acquiring stress data and error data of the intelligent electric meter;
determining typical stress data in the stress data of the intelligent ammeter;
sending the typical stress data and the error data thereof into a neural network for training to obtain a trained neural network;
and establishing error data relationships under different stress conditions by using the trained neural network.
The method for analyzing the stress error of the intelligent electric meter, provided by the embodiment of the invention, at least has the following beneficial effects: and (3) utilizing data acquired by the intelligent electric meter, and then sending the data into the BP neural network optimized by the LM for training, thereby obtaining the trained neural network for predicting the change relation of errors under different stress conditions.
According to some embodiments of the invention, the step of determining typical stresses in the stress data of the smart meter comprises:
carrying out standardization processing on the data;
calculating the contribution rate of each stress by using the data subjected to the standardization processing;
several stresses with relatively large contribution ratios are selected as typical stresses.
According to some embodiments of the invention, the typical stress comprises: temperature, humidity, air pressure, regional voltage conditions.
According to some embodiments of the invention, the sum of the typical stresses exceeds 95%.
According to some embodiments of the present invention, after the step of determining the typical stress in the stress data of the smart meter, the method further includes the steps of:
and processing the typical stress data and the error data thereof, and removing abnormal data to obtain processed data.
According to some embodiments of the invention, the step of processing the typical stress data and the error data thereof to remove the abnormal data to obtain processed data comprises:
arranging error data in the intelligent ammeter according to an acquisition time sequence to obtain x (t), and solving an average value mu and a standard deviation sigma;
rejecting abnormal data in the error data;
correcting sequence abnormality by utilizing average value interpolation;
and transforming the sample sequence of the stress by using a normalization method to obtain processed data.
According to some embodiments of the invention, the neural network used in the stress error analysis method of the smart meter is a BP neural network based on LM optimization.
According to some embodiments of the invention, the step of sending the processed data to a neural network for training to obtain a trained neural network comprises:
setting the stress parameters as input vectors;
setting the error of the intelligent ammeter as an output vector;
the actual error is set to the desired output vector.
According to some embodiments of the invention, the method further comprises:
predicting an estimation error by using the trained neural network;
and adding the estimated error to the reference error of the intelligent electric meter to be used as the error offset of the intelligent electric meter.
According to a second aspect of the invention, the stress error analysis device for the intelligent electric meter is characterized by comprising:
the data collection module can acquire stress data and error data of the intelligent ammeter;
the typical stress analysis module can determine typical stress data in the stress data of the intelligent ammeter;
the model training module can send the typical stress data and the error data thereof into a neural network for training to obtain a trained neural network;
and the relation analysis module can establish error data relation under different stress conditions by utilizing the trained neural network.
A terminal according to an embodiment of the third aspect of the present invention includes: the stress error analysis method for the intelligent electric meter is characterized by comprising a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the stress error analysis method for the intelligent electric meter.
The computer-readable medium according to the fourth aspect of the present invention is characterized in that computer software is stored in the computer medium, and when the software is executed, the method for analyzing the stress error of the smart meter can be implemented.
According to the stress error analysis method for the intelligent electric meter, disclosed by the invention, the relevance of various stresses and errors is analyzed by using a BP neural network algorithm optimized by an LM (Linear modeling). An additional error is introduced during error modeling, so that error model correction of the intelligent electric energy meter is realized. The method of the invention does not need excessive error calculation and error fitting in the past error analysis. By adopting the PCA idea, the phenomena of over-fitting and under-fitting are not easy to occur, the error analysis efficiency is improved, and higher reliability can be ensured. Therefore, the method of the invention can lead the error predicted value of the intelligent electric energy meter to have a higher confidence interval under certain conditions and lay a foundation for the error correction work of the intelligent electric energy meter.
Additional aspects and advantages 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 above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic diagram of a smart meter for use in an embodiment of the invention;
fig. 2 is a schematic step diagram of a method for analyzing stress error of an intelligent electric meter according to a first embodiment of the present invention;
FIG. 3 is a graph illustrating the effect of temperature on the error of the electric meter according to the second embodiment of the present invention;
FIG. 4 is a graph illustrating the effect of humidity on the error of the electric meter according to the second embodiment of the present invention;
FIG. 5 is a graph showing the influence of air pressure on the error of the electric meter according to the second embodiment of the present invention;
FIG. 6 is a diagram illustrating the influence of different area voltages on the error of the electric meter according to a second embodiment of the present invention; wherein, fig. 6-a represents the influence of the voltage in Fujian region on the error of the electric meter, fig. 6-b represents the influence of the voltage in Heilongjiang region on the error of the electric meter, fig. 6-c represents the influence of the voltage in Tibet region on the error of the electric meter, and fig. 6-d represents the influence of the voltage in Xinjiang region on the error of the electric meter.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
As shown in fig. 1, fig. 1 illustrates the metering principle of a smart meter, in which the variation of the error is complicated under the influence of various factors, it is currently difficult to design a method capable of determining the meter error through a theoretical calculation. Most of the existing electric energy meter error analysis methods cannot consider the influence of the actual working environment and working conditions on the errors, so that the method has limitations.
In the analysis method, the data of various influence errors are abstracted into various stresses, the relation between the errors and the stresses is analyzed by an artificial intelligence method, the accuracy of error analysis can be improved, and a foundation is laid for the error compensation and correction work of the electric energy meter later. The details are as follows.
The first embodiment,
Referring to fig. 2, an embodiment of the present application provides a method for analyzing stress error of a smart meter, including the following steps:
and S100, acquiring stress data and error data of the intelligent electric meter.
When the data of the intelligent electric meter is acquired, the data need to be continuously acquired within a long period of time, and as much data as possible are acquired, so that the number of training sets of the model can be increased, and the accuracy of the result is increased.
Preferably, the electricity meter itself is capable of recording electricity usage data, stress data, and error data. When sampling is carried out at a certain moment, all the stress condition data X corresponding to the stress condition data are taken out i The stress data at time i can be expressed as:
X i ＝[X 1 ，X 2 ，…，X m ] (1)
wherein m isThe number of stresses. Error data at time i is Y i 。
If n sets of data are acquired within a sufficiently long time, the n sets of data can be represented as a stress data matrix as follows:
the corresponding error vector in n sets of data can be expressed as:
Y＝[Y 1 ，Y 2 ，…，Y n ] T (3)
and S200, determining typical stress in the stress data of the intelligent electric meter.
The stress data collected in step S100 is usually large in quantity, and some data have very small influence, and if these data are taken into consideration, not only the speed of the subsequent training model is influenced, but also errors are caused by these low-influence data, and the attention is distracted. Only the stress with larger occupation is selected for research.
In order to find a plurality of stresses most closely related to errors of the electric energy meter, an improved Principal Component Analysis (PCA) idea is adopted, a group of orthogonal vectors of a sample space is found, and the group of orthogonal vectors is used for representing the whole situation, so that the original high-dimensional data is described by a few principal components, and the information of the original data is kept to the maximum extent.
In n effective data samples obtained by experiments, each sample has m sampling data, and a sample data matrix X can be obtained n×m With 1 observation data sample x per row vector i Wherein i is more than 0 and less than or equal to n; each column vector is the characteristic quantity xj of the corresponding observation sample, wherein j is more than 0 and less than or equal to m.
Step S201 normalizes the data.
The formula used for the normalization process is as follows:
in the formula (I), the compound is shown in the specification,
for the purpose of the feature quantity after the normalization,
is the mean value of the characteristic quantities, s (x) j ) Is the standard deviation of the characteristic quantity.
In step S202, the contribution ratio of each stress is calculated using the normalized data.
Setting the matrix after standardization as
The covariance matrix is obtained as P, i.e.:
then, the eigenvalue lambda of the covariance matrix P is calculated i And its feature vector e i . By the similarity diagonalization of the matrix, a similar diagonal matrix D with P is obtained, the elements on the diagonal in D are arranged in descending order of eigenvalue size, namely D ═ diag (lambda) 1 ，λ 2 ，…，λ n ) Then P is EDE T Wherein E is a characteristic value λ i Corresponding to a set of eigenvectors ei, and E is an orthonormal matrix, i.e., E ═ diag (E) 1 ，e 2 ，…，e n ) The principal component vectors m are obtained by linear variation of the formula (6) 1 ，m 2 ，…，m n 。
Wherein, the contribution rate corresponding to the kth principal component is expressed as:
λ k representing the characteristic value of the k-th principal component, λ i Corresponding feature vector e i 。
In step S203, a plurality of stresses having relatively large contribution ratios are selected as typical stresses.
And sorting the contribution rates from high to low, and selecting a plurality of principal components which are sorted at the top as typical stress.
According to a large number of experiments, the cumulative contribution rate of the first three or the first four main components can reach more than 95%, so that the main influence factors can be analyzed by only selecting three or four stresses when taking the typical stress. These stresses include: temperature, humidity, air pressure, regional voltage.
And step S300, processing the typical stress data and the error data, and removing abnormal data to obtain processed data. The accuracy of training data in the subsequent process can be improved, and data which are obviously unreasonable in sampling can be eliminated.
According to some preferred embodiments of the present application, the steps specifically include:
step S301, arranging error data in the intelligent ammeter according to a collecting time sequence to obtain x (t), and calculating an average value mu and a standard deviation sigma;
and step S302, eliminating abnormal data in the error data.
And (3) determining data points which are not in the range of [ mu-3 sigma, mu +3 sigma ] in the data segment as abnormal values by using a3 sigma criterion commonly used in statistics, and removing the abnormal values.
Step S303, sequence abnormality correction is performed by mean value interpolation.
The removed data can leave a position, and the data before and after the position are averaged to fill the original position. The formula is as follows:
step S304, a sample sequence of the stress is transformed using a normalization method.
Sample series x of stress using z-score method (normalization method) 1 ，x 2 ，......，x n The transformation is performed, the formula is as follows:
the transformed sequence is y 1 ，y 2 ，......，y n The sequence mean is 0 and the variance is 1, dimensionless. Resulting in processed data.
And S400, sending the processed data to a neural network for training.
Under the three-layer neural network structure, setting the preprocessed typical stress y ═ y 1 ，y 2 ，…，y n ]For input vector, the error z of the intelligent electric energy meter is [ z ═ z% 1 ，z 2 ，…，z m ]And outputting the vector, wherein the actual error t is an expected output vector, w is a connection weight of the neural network, and a sigmoid function is used as an activation function in the middle layer and the output layer.
When the network output result, namely the error z of the intelligent electric energy meter, does not meet the set requirement, the data processing of the network enters a back propagation link, at the moment, the weighted value and the threshold value of each layer of unit are modified by the error signal from back to front, and the back propagation process is completed according to the principle of a gradient descent method. The error function of the output layer is set as E, and the expression is as follows:
w is all the weights, tk is the actual value of the error of the intelligent electric energy meter during the k iteration, zk is the estimated value of the error of the intelligent electric energy meter after the k iteration, t is the actual value of the error of the intelligent electric energy meter, and z is the estimated error of the intelligent electric energy meter.
According to some preferred embodiments of the present application, the actual value t of the error of the smart meter is an accurate error obtained from a large amount of experimental data, and may be considered as the corresponding error of the smart meter under the stress condition.
In the initial stage of the model, the initial value of the weight is set as a random value within a certain range. Decomposing the Hessian matrix into the product of Jacobians matrices, and then solving the inverse matrix of the Jacobians matrices, thereby reducing the complexity of calculation and updating the weight value more quickly, wherein the calculation formula is as follows:
in the formula, Δ W is the variation of the network weight; h is the number of iterations; j. the design is a square h Is the h iteration error function Jacobians matrix; mu.s h Is a constant greater than zero; e is an identity matrix; e.g. of the type h Is the h-th return error.
The process of model training is to reduce the error value through multiple iterations, and the weight vector is updated as:
w (i+1) ＝w (i) +Δw (i) (12)
when the output error function value satisfies the following formula:
E(h)≤e m (13)
wherein e is m And (3) setting a preset termination criterion according to the precision requirement, and stopping iterative computation and finishing the training of the neural network model when the formula (13) is satisfied and the termination condition is met.
That is, when the difference between the estimation error k trained by the model and the actual smart meter error t is small enough, the model has a relatively high accuracy when trained.
The trained model can be used for mining the nonlinear relation between the stress characteristic value acting on the electric energy meter and the error value, and can accurately predict the error under a certain condition.
According to some preferred embodiments of the present application, the present application can predict error conditions under different stress conditions by means of the model, and then perform error correction on the electric meter according to the error conditions, which can be specifically described as:
and S500, estimating the error offset according to the environment and the working condition of the intelligent electric energy meter.
When the method provided by the invention is used for analyzing the error of the intelligent electric energy meter, the influence of various stresses on the error in actual use is fully considered, and the additional error caused by various stresses is considered, so that the error of the intelligent electric energy meter is corrected.
The method specifically comprises the following steps:
and step S501, predicting an estimation error by using the trained neural network.
And predicting an estimation error z generated by the stress error of the intelligent electric meter in the current operation state through the model. And the estimation error z generated by the stress error is the final output of the model after multiple parameter iterative optimization and meeting the termination criterion.
And step S502, adding the estimated error to the reference error of the intelligent ammeter to serve as the error offset of the ammeter.
The estimation error z obtained in the step S501 and the reference error delta e of the electric energy meter under the standard condition are used 0 And adding to obtain the error offset delta e of the electric energy meter. The formula can be expressed as:
Δe＝z+Δe 0 (14)
reference error delta e of electric energy meter 0 Is the statistical error under ideal conditions, the reference error Δ e 0 The error is also a random error, is a rated error of a certain electric energy meter under a standard condition, and is an accuracy level substantially. Because the errors of different electric energy meters are not necessarily the same under the same working conditions, the random errors of the electric energy meters need to be considered.
The estimation error z generated by the stress error under the actual condition is caused by the fact that the stress condition of the working environment is inconsistent with the ideal condition, according to the model in the scheme, the stress condition of the electric energy meter to be measured is used as an input variable, the estimation error z under the environment can be obtained, and the error offset delta e of the electric energy meter is obtained through calculation according to the formula 14.
And S600, establishing a relation of error offsets under different stress conditions by using the trained neural network.
The trained neural network model can establish the relation between the error offset delta e and the stress condition, and the relation is expressed by drawing, so that the change trend can be visually seen.
Example II,
In order to verify the effectiveness of the above embodiments, on the basis of the first embodiment, the following data is taken:
step A100, stress data and error data of the intelligent electric meter are obtained.
In line with the method described in embodiment one, this is omitted here.
And step A200, determining typical stress in stress data of the smart meter.
In a certain experiment, 60725 effective data samples are obtained, each sample has 8 sampling data, and a sample data matrix X can be obtained 60725×8 With 1 observation data sample x per row vector i Wherein i is more than 0 and less than or equal to 60725; each column vector is the characteristic quantity xj of the corresponding observation sample, wherein j is more than 0 and less than or equal to 8.
Step a201, standardizes the data.
The formula is as follows:
in the formula (I), the compound is shown in the specification,
for the purpose of the feature quantity after the normalization,
is the mean value of the characteristic quantities, s (x) j ) Is the standard deviation of the characteristic quantity.
Step a202 calculates the contribution ratio of each stress using the normalized data.
Setting the matrix after standardization as
The covariance matrix is obtained as P, i.e.:
calculating an eigenvalue λ of the covariance matrix P i And its feature vector e i I.e. P ═ EDE T Wherein D is a diagonal matrix arranged in descending order according to the size of the characteristic value, and D is diag (lambda) 1 ，λ 2 ，…，λ 60725 ) E is a characteristic value λ i Corresponding feature vector e i And E is an orthonormal matrix, E ═ diag (E) 1 ，e 2 ，…，e 60725 ) Each principal component vector m is obtained by linear change of the formula (17) 1 ，m 2 ，…，m 60725 。
The contribution rate corresponding to the kth principal component is:
step A203, selecting a plurality of stresses with the largest contribution ratio as typical stresses.
And sorting the contribution rates from high to low, and selecting a plurality of principal components which are sorted at the top as typical stress.
Experiments show that the cumulative contribution rate of the first 4 main components reaches 95%, and the 4 main components are temperature, humidity, air pressure and voltage stress respectively and serve as the input variables of the following model.
And step A300, processing the typical stress data and the error data, and removing abnormal data to obtain processed data.
Step A301, arranging error data in the intelligent ammeter according to an acquisition time sequence to obtain x (t), and calculating an average value mu and a standard deviation sigma;
step A302, setting a rejection threshold.
And (3) determining data points which are not in the range of [ mu-3 sigma, mu +3 sigma ] in the data segment as abnormal values by using a3 sigma criterion commonly used in statistics, and removing the abnormal values.
Step A303, sequence abnormality correction is performed by mean value interpolation.
The removed data can leave a position, and the data before and after the position are averaged to fill the original position. The formula is as follows:
step A304, transforming the sample sequence using a normalization method
Using the z-score method (normalization method), a sequence of samples x is normalized 1 ，x 2 ，......，x n The transformation is performed, the formula is as follows:
the transformed sequence is y 1 ，y 2 ，......，y n The sequence mean is 0 and the variance is 1, dimensionless.
Resulting in processed data.
And A400, sending the processed data to a neural network for training.
The same procedure as in the first embodiment is omitted here.
And A500, calculating the error offset according to the environment and the working condition of the intelligent electric energy meter.
The same procedure as in the first embodiment is omitted here.
Step A600, establishing the relation of error offset under different stress conditions by using the trained neural network.
The invention takes a stress error curve obtained by one experiment as an example, and respectively is a curve (shown in figure 3) of the influence of temperature on the error of an ammeter; humidity versus meter error effect curve (as shown in fig. 4); the influence curve of the air pressure on the electric meter error (shown in figure 5) and the influence of the voltage of different areas on the electric meter error (shown in figure 6).
The method utilizes the trained neural network to establish the relation between the typical stress and the error, and the relation is displayed in an image mode, so that the errors caused by different stresses can be analyzed visually.
An embodiment of the second aspect of the present invention provides a smart meter stress error analysis device, including:
the data collection system can acquire stress data and error data of the intelligent electric meter;
the typical stress analysis system can determine typical stress in the stress data of the intelligent electric meter;
the model training module can send the processed data into a neural network for training to obtain a trained neural network;
and the relation analysis module can establish error data relation under different stress conditions by utilizing the trained neural network.
The stress error analysis method for the intelligent electric meter described in the first embodiment is presented in the form of computer equipment, the corresponding relation between the stress and the error in the intelligent electric meter can be analyzed by using the BP neural network optimized by the LM, and a change curve is drawn, so that the corresponding relation between the stress and the error is established by means of the method, and the effect of the error analysis of the intelligent electric meter is achieved.
Another embodiment of the present application provides a terminal, including: the stress error analysis method for the intelligent electric meter comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the stress error analysis method for the intelligent electric meter.
In particular, the processor may be a CPU, general purpose processor, DSP, ASIC, FPGA or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. A processor may also be a combination of computing functions, e.g., comprising one or more microprocessors, a DSP and a microprocessor, or the like.
In particular, the processor is coupled to the memory via a bus, which may include a path for communicating information. The bus may be a PCI bus or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc.
The memory may be, but is not limited to, a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, an EEPROM, a CD-ROM or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
Optionally, the memory is used for storing codes of computer programs for executing the scheme of the application, and the processor is used for controlling the execution.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (11)
1. The stress error analysis method for the intelligent ammeter is characterized by comprising the following steps:
acquiring stress data and error data of the intelligent electric meter;
determining typical stress data in the stress data of the intelligent electric meter;
sending the typical stress data and the error data thereof into a neural network for training to obtain a trained neural network;
and establishing error data relationships under different stress conditions by using the trained neural network.
2. The method for analyzing stress error of the smart meter according to claim 1, wherein the step of determining typical stress data in the stress data of the smart meter comprises:
carrying out standardization processing on the data;
calculating the contribution rate of each stress by using the data subjected to the standardization processing;
several stresses with relatively large contribution ratios are selected as typical stresses.
3. The method for analyzing stress error of a smart meter according to claim 2, wherein the sum of the typical stress contributions exceeds 95%.
4. The method for analyzing stress error of the smart meter according to claim 1, wherein after the step of determining typical stress data in the stress data of the smart meter, the method further comprises the steps of:
and processing the typical stress data and the error data thereof, and removing abnormal data to obtain processed data.
5. The method for analyzing stress error of a smart meter according to claim 4, wherein the step of processing the typical stress data and the error data thereof to remove abnormal data and obtain processed data comprises:
arranging error data in the intelligent ammeter according to an acquisition time sequence to obtain x (t), and solving an average value mu and a standard deviation sigma;
rejecting abnormal data in the error data;
correcting sequence abnormality by utilizing average value interpolation;
and transforming the sample sequence of the stress by using a normalization method to obtain processed data.
6. The method for analyzing stress error of a smart meter according to claim 1, wherein the neural network is a BP neural network based on LM optimization.
7. The method for analyzing stress error of a smart meter according to claim 6, wherein the step of sending the processed data to a neural network for training to obtain a trained neural network comprises:
setting the stress parameters as input vectors;
setting the error of the intelligent ammeter as an output vector;
the actual error is set to the desired output vector.
8. The method for analyzing stress error of a smart meter according to claim 1, further comprising:
predicting an estimation error by using the trained neural network;
and adding the estimated error to the reference error of the intelligent electric meter to be used as the error offset of the intelligent electric meter.
9. The utility model provides a smart electric meter stress error analysis device which characterized in that includes:
the data collection module can acquire stress data and error data of the intelligent ammeter;
the typical stress analysis module can determine typical stress data in the stress data of the intelligent ammeter;
the model training module can send the typical stress data and the error data thereof into a neural network for training to obtain a trained neural network;
and the relation analysis module can establish error data relation under different stress conditions by utilizing the trained neural network.
10. A terminal, comprising: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor executes the computer program to implement the method of any of claims 1 to 8.
11. A computer-readable medium, characterized in that the computer medium has stored therein computer software, which when executed, can implement the method for analyzing stress error of a smart meter as described in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111142609.9A CN114814707A (en) | 2021-09-28 | 2021-09-28 | Intelligent ammeter stress error analysis method, equipment, terminal and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111142609.9A CN114814707A (en) | 2021-09-28 | 2021-09-28 | Intelligent ammeter stress error analysis method, equipment, terminal and readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114814707A true CN114814707A (en) | 2022-07-29 |
Family
ID=82525336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111142609.9A Pending CN114814707A (en) | 2021-09-28 | 2021-09-28 | Intelligent ammeter stress error analysis method, equipment, terminal and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114814707A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115685048A (en) * | 2022-12-01 | 2023-02-03 | 浙江万胜智能科技股份有限公司 | Online calibration method and system for communication module of intelligent electric meter |
| CN116106816A (en) * | 2023-01-13 | 2023-05-12 | 北京市腾河智慧能源科技有限公司 | Electric energy meter error calibration method, system, equipment and medium based on 5G module |
-
2021
- 2021-09-28 CN CN202111142609.9A patent/CN114814707A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115685048A (en) * | 2022-12-01 | 2023-02-03 | 浙江万胜智能科技股份有限公司 | Online calibration method and system for communication module of intelligent electric meter |
| CN116106816A (en) * | 2023-01-13 | 2023-05-12 | 北京市腾河智慧能源科技有限公司 | Electric energy meter error calibration method, system, equipment and medium based on 5G module |
| CN116106816B (en) * | 2023-01-13 | 2024-04-26 | 北京市腾河智慧能源科技有限公司 | Electric energy meter error calibration method, system, equipment and medium based on 5G module |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7899652B2 (en) | Linear programming support vector regression with wavelet kernel | |
| CN107688825B (en) | Improved integrated weighted extreme learning machine sewage treatment fault diagnosis method | |
| CN113805064B (en) | Lithium ion battery pack health state prediction method based on deep learning | |
| CN105572572B (en) | Analog-circuit fault diagnosis method based on WKNN-LSSVM | |
| CN114814707A (en) | Intelligent ammeter stress error analysis method, equipment, terminal and readable medium | |
| CN114819054B (en) | Power electronic system state monitoring method based on physical information neural network | |
| CN112630659A (en) | Lithium battery SOC estimation method based on improved BP-EKF algorithm | |
| CN110442911B (en) | High-dimensional complex system uncertainty analysis method based on statistical machine learning | |
| CN109298633A (en) | Chemical production process fault monitoring method based on adaptive piecemeal Non-negative Matrix Factorization | |
| CN117574780B (en) | Intelligent thermal power plant load online modeling method and system | |
| CN114487890A (en) | Lithium battery health state estimation method for improving long-term and short-term memory neural network | |
| CN114583767B (en) | Data-driven wind power plant frequency modulation response characteristic modeling method and system | |
| CN117330963B (en) | Energy storage power station fault detection method, system and equipment | |
| CN114357870A (en) | Metering equipment operation performance prediction analysis method based on local weighted partial least squares | |
| CN116865343B (en) | Model-free self-adaptive control method, device and medium for distributed photovoltaic power distribution network | |
| CN117113086A (en) | Energy storage unit load prediction method, system, electronic equipment and medium | |
| CN116901707A (en) | Power battery pack fault early warning method, system and vehicle | |
| CN116400266A (en) | Transformer fault detection method, device and medium based on digital twin model | |
| CN114021465A (en) | Electric power system robust state estimation method and system based on deep learning | |
| CN112541554B (en) | Multi-mode process monitoring method and system based on time constraint and nuclear sparse representation | |
| CN116150666B (en) | Energy storage system fault detection method and device and intelligent terminal | |
| CN116595883B (en) | Real-time online system state correction method for numerical reactor | |
| CN111103789B (en) | Source network load comprehensive energy scheduling analysis method, system and terminal equipment | |
| CN117755154B (en) | Power battery health state assessment method based on new energy automobile real vehicle working condition | |
| Fernandez et al. | Battery State of Health Estimation |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Xiong Suqin Inventor after: Chen Hao Inventor after: Zhang Wei Inventor after: Wang Xiaodong Inventor after: Li Yang Inventor after: Yang Wei Inventor after: Duan Xiaomeng Inventor after: Zhao Yue Inventor after: Guo Jianning Inventor after: Li Longtao Inventor after: Wang Yatao Inventor after: Cheng Da Inventor after: Qin Chenglin Inventor after: Peng Chuning Inventor after: Zhao Bing Inventor after: Li Ning Inventor after: Ge Dehui Inventor after: Zou Heping Inventor after: Li Qiuyang Inventor after: Zhang Baoliang Inventor before: Xiong Suqin Inventor before: Chen Hao Inventor before: Zhang Wei Inventor before: Wang Xiaodong Inventor before: Li Yang Inventor before: Yang Wei Inventor before: Duan Xiaomeng Inventor before: Zhao Yue Inventor before: Guo Jianning Inventor before: Li Longtao Inventor before: Wang Yatao Inventor before: Cheng Da Inventor before: Qin Chenglin Inventor before: Peng Chuning Inventor before: Zhao Bing Inventor before: Li Ning Inventor before: Ge Dehui Inventor before: Zou Heping Inventor before: Li Qiuyang Inventor before: Zhang Baoliang |
|
| CB03 | Change of inventor or designer information |