Electric energy meter metering error evaluation method and device, electronic equipment and storage medium

Abstract

The invention provides an electric energy meter metering error evaluation method and device, electronic equipment and a storage medium, and belongs to the technical field of electric power metering online monitoring, and the method comprises the steps: obtaining real-time data of a to-be-measured electric energy meter, carrying out the empirical mode decomposition of the real-time data, obtaining a plurality of signal components corresponding to the real-time data, and carrying out the calculation of the signal components; z-score standardization is carried out on a plurality of signal components corresponding to the real-time data to obtain a target signal component, wavelet transformation is carried out on the target signal component to obtain a two-dimensional time-frequency image, the two-dimensional time-frequency image is input into a trained electric energy meter error prediction model to obtain an error prediction result of the electric energy meter, and the error prediction result of the electric energy meter is obtained through the electric energy meter error prediction model. Comprising a convolution layer, a standardization layer, a ReLU activation layer, a global average pooling layer and a full connection layer which are sequentially connected in series. According to the invention, the technical problem of low error evaluation precision of the electric energy meter in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of online monitoring of electric power metering, and in particular to a method, a device, an electronic device and a storage medium for evaluating metering errors of electric energy meters. Background Art

[0002] In the power system, in order to accurately measure energy consumption and ensure fair billing, energy meters are needed to measure energy usage. High-voltage energy meters are instruments specifically used to measure energy consumption in high-voltage power grids, and are commonly used for power metering in industrial and commercial fields. First, energy meters are able to measure energy usage in kilowatt-hours; second, some high-voltage energy meters have data logging functions that can record energy usage over a period of time to provide data support for energy management and billing; finally, some advanced high-voltage energy meters also have communication interfaces that can be connected to power management systems or smart grid systems to achieve remote monitoring and control.

[0003] Inaccuracy of high-voltage electricity meters may have serious impacts on users, power companies and the safety and stability of the power system. Therefore, ensuring the accuracy and stability of electricity meters is crucial to the normal operation of the power system and fair billing.

[0004] At present, the commonly used method for evaluating the error of high-voltage electric energy meters is the standard instrument method with regular calibration. During the calibration process, a standard electric energy meter can be used as a reference to compare the measurement results of the two and calculate the error. This method requires the power grid to be shut down, but power outages are difficult to evaluate and the cost is high. Therefore, there is a technical problem in the prior art that the accuracy of the electric energy meter error evaluation is not high. Summary of the invention

[0005] In view of this, it is necessary to provide a method, device, electronic device and storage medium for evaluating the measurement error of an electric energy meter, so as to solve the technical problem of low accuracy of error evaluation of electric energy meters in the prior art.

[0006] In order to solve the above technical problems, on the one hand, the present invention provides a method for evaluating an electric energy meter measurement error, comprising: Obtain the real-time data of the electric energy meter to be tested; the real-time data includes: voltage, current, temperature and acquisition frequency; Performing empirical mode decomposition on the real-time data to obtain multiple signal components corresponding to the real-time data; Perform Z-score standardization on multiple signal components corresponding to real-time data to obtain target signal components; Perform wavelet transform on the target signal component to obtain a two-dimensional time-frequency image; Input the two-dimensional time-frequency image into the trained electric energy meter error prediction model to obtain the error prediction result of the electric energy meter; Among them, the electric energy meter error prediction model includes: Convolutional layer, normalization layer, ReLU activation layer, global average pooling layer and fully connected layer connected in series.

[0007] In a possible implementation, performing empirical mode decomposition on the real-time data to obtain a plurality of signal components corresponding to the real-time data includes: The real-time data is parameterized to obtain corresponding assigned parameters, and the assigned parameters are subjected to empirical mode decomposition to obtain multiple signal components corresponding to the real-time data.

[0008] In a possible implementation, performing empirical mode decomposition on the assigned parameters to obtain multiple signal components corresponding to the real-time data includes: The assigned parameters are fitted with interpolation polynomials to obtain continuous time series data, and the continuous time series data are subjected to empirical mode decomposition to obtain multiple signal components corresponding to the real-time data.

[0009] In a possible implementation, performing Z-score normalization on the multiple signal components corresponding to the real-time data to obtain the target signal component includes: Matching multiple signal components corresponding to the real-time data with preset thresholds to obtain matched signal components; The matched signal components are Z-score normalized to obtain the target signal components.

[0010] In a possible implementation, performing Z-score normalization on the matched signal components to obtain the target signal components includes: The matched signal components are Z-score standardized to obtain weight values ​​corresponding to the multiple signal components, and the target signal components are obtained based on the weight values ​​corresponding to the multiple signal components.

[0011] In a possible implementation manner, obtaining the target signal component based on the weight values ​​corresponding to the multiple signal components includes: The weight values ​​corresponding to the multiple signal components are sorted in order to obtain the target signal component.

[0012] In a possible implementation, the step of sorting the weight values ​​corresponding to the plurality of signal components to obtain the target signal component includes: The weight values ​​corresponding to the multiple signal components are sorted by size to obtain a sorting result, and based on the sorting result, a target signal component is obtained.

[0013] On the other hand, the present invention also provides an electric energy meter measurement error evaluation device, comprising: A data acquisition module is used to acquire real-time data of the electric energy meter to be tested; An empirical mode decomposition module is used to perform empirical mode decomposition on real-time data to obtain multiple signal components corresponding to the real-time data; A standardization processing module is used to perform Z-score standardization on multiple signal components corresponding to real-time data to obtain a target signal component; A wavelet transform module is used to perform wavelet transform on the target signal component to obtain a two-dimensional time-frequency image; The output module is used to input the two-dimensional time-frequency image into the trained electric energy meter error prediction model to obtain the error prediction result of the electric energy meter.

[0014] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the electric energy meter measurement error evaluation method in any of the above implementations.

[0015] On the other hand, the present invention also provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the electric energy meter measurement error evaluation method described in any of the above-mentioned implementations.

[0016] The beneficial effects of the present invention are as follows: the method for evaluating the measurement error of an electric energy meter provided by the present invention comprises: obtaining real-time data of the electric energy meter to be tested; the real-time data comprises: voltage, current, temperature and acquisition frequency; performing empirical mode decomposition on the real-time data to obtain multiple signal components corresponding to the real-time data; performing Z-score standardization on the multiple signal components corresponding to the real-time data to obtain the target signal component; performing wavelet transform on the target signal component to obtain a two-dimensional time-frequency image; inputting the two-dimensional time-frequency image into a trained electric energy meter error prediction model to obtain the error prediction result of the electric energy meter; wherein the electric energy meter error prediction model comprises: a convolution layer, a standardization layer, a ReLU activation layer, a global average pooling layer and a fully connected layer connected in series in sequence. The present invention performs empirical mode decomposition, Z-score standardization and wavelet transform on real-time data, and at the same time constructs an electric energy meter error prediction model, thereby realizing the error state recognition of high-voltage electric energy meters under non-power outage conditions, getting rid of the traditional method of offline detection of electric energy meters, and making the model prediction more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic flow chart of an embodiment of a method for evaluating an electric energy meter measurement error provided by the present invention; Figure 2 A schematic diagram of an embodiment of the electric energy meter measurement error evaluation method provided by the present invention; Figure 3 A schematic diagram of the structure of an embodiment of an electric energy meter measurement error evaluation device provided by the present invention; Figure 4 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] In the description of the embodiments of the present application, unless otherwise specified, “plurality” means two or more than two.

[0021] The terms "including" and "having" and any variations thereof in the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product or equipment comprising a series of steps or modules is not necessarily limited to those steps or modules clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or equipment.

[0022] The naming or numbering of the steps in the embodiments of the present invention does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The execution order of the named or numbered process steps can be changed according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0023] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0024] The present invention provides an electric energy meter measurement error assessment method, device, electronic device and storage medium, which are respectively described below.

[0025] Figure 1 A schematic diagram of an embodiment of the method for evaluating the measurement error of an electric energy meter provided by the present invention and Figure 2 A schematic diagram of an embodiment of the electric energy meter measurement error evaluation method provided by the present invention includes: S101, obtaining real-time data of the electric energy meter to be tested; the real-time data includes: voltage, current, temperature and acquisition frequency; S102, performing empirical mode decomposition on the real-time data to obtain multiple signal components corresponding to the real-time data; S103, performing Z-score standardization on multiple signal components corresponding to the real-time data to obtain a target signal component; S104, performing wavelet transform on the target signal component to obtain a two-dimensional time-frequency image; S105, inputting the two-dimensional time-frequency image into the trained electric energy meter error prediction model to obtain an error prediction result of the electric energy meter; Among them, the electric energy meter error prediction model includes: Convolutional layer, normalization layer, ReLU activation layer, global average pooling layer and fully connected layer connected in series.

[0026] It can be understood that the trained electric energy meter error prediction model is obtained through the following steps: Step 1: Collect various displayed data of the electric energy meter and process the data.

[0027] Collect data from multiple transformers to be tested for one month in history, including voltage data, current data, temperature data, grid frequency data, and the true value of the error value obtained by offline evaluation of the corresponding transformers as training data for the model.

[0028] The collected voltage data, current data, temperature data and grid frequency data are respectively recorded as U C ,I C 、T C and V C, and perform polynomial interpolation on the voltage data, current data, temperature data and grid frequency data, and fit the interpolation polynomial according to the data to obtain continuous time series data, which are recorded as U S ,I S 、T S and V S , and perform EMD empirical mode decomposition on continuous time series data.

[0029] The specific process of EMD empirical mode decomposition is as follows: 1) Determine extreme points: Find all local maximum and minimum points in the signal.

[0030] 2) Generate upper and lower envelopes: By connecting adjacent extreme points, upper and lower envelopes are formed. These envelopes decompose the original signal into a series of parts with gradually changing oscillation frequencies.

[0031] 3) Calculate the mean: average the upper and lower envelopes to get the average envelope.

[0032] 4) Extract detail signal: Subtract the original signal from the average envelope to obtain the detail signal (Detail). If the detail signal meets certain conditions, it is called IMFs .

[0033] 5) Judgment IMFs :Check whether the detail signal meets IMFs The definition of , that is, the number of maximum and minimum values ​​in the entire data range is the same, and there is at most one local extreme point between the maximum and minimum in the entire data range.

[0034] 6) Repeat the steps: subtract the extracted signal from the original signal IMFs , and then repeat the above steps for the remaining signal until the remaining signal can no longer be decomposed into IMFs until.

[0035] 7) Convergence judgment: When the decomposition result meets a certain convergence criterion, stop the decomposition process.

[0036] 8) Get IMFs : The final set of IMFs The original signal can be approximately represented as a linear combination of these IMFs. U s After empirical mode decomposition, the signal components are obtained: IMF U1 , IMF U2 、...、IMF Un（U） ; I S After empirical mode decomposition, the signal components are obtained: IMFI1 、IMF I2 、...、IMF In(S) ; T s After empirical mode decomposition, the signal components are obtained: IMF T1 、IMF T2 、...、IMF Tn(T) ; V S After empirical mode decomposition, the signal components are obtained: IMF V1 , IMF V2 ,..., IMF Vn（V） .

[0037] Step 2: Calculate the signal reference value through the temperature data and frequency data, and obtain the weight value together with the voltage data and current data.

[0038] Will Ts After empirical mode decomposition, the signal components are obtained: IMF T1 , IMF T2 ,..., IMF Tn(T) ,and Vs After empirical mode decomposition, the signal components are obtained: IMF V1 , IMF V2 ,..., IMF Vn（V） Take the first three items, that is IMF T1 , IMF T2 , IMF T3 ,and IMF V1 , IMF V2 , IMF V3 , perform Z-score standardization on it, that is, calculate each value of these 6 time series data: IMF T1 For example,

[0039] in, for IMF T1 No. x The data are observations, for IMF T1 The mean of for IMFT1 The standard deviation of , , and form , similarly calculated , , , , , , , , , Get and calculate , , , , .

[0040] Construct signal reference sequence value , , The calculation formula is as follows:

[0041] in, For signal The yth data of , Signal data composition , the following is obtained by the same logic and .

[0042]

[0043]

[0044] Further, calculate one by one , , The rank correlation coefficient K of the signal component converted from the voltage and current data EMD.

[0045]

[0046] in, for S 1 and IMF U1 The correlation coefficient of ， Similarly, we can calculate all , calculate each IMF and Sn of K Worth it ， like ， Will Sort from largest to smallest to get the 5 with the largest values K value 。 Record the corresponding 5 current / voltage signal component subscripts, and the corresponding 5 signal components are recorded as IMF 1 、IMF 2 、IMF 3 、IMF 4 、IMF 5.

[0047] Step 3: Establish a neural network based on multi-scale feature fusion and train the electricity meter error assessment model.

[0048] The five largest K values ​​above correspond to IMF The signal components are transformed by wavelet transform to convert the one-dimensional signal data into a two-dimensional time-frequency image. A new multi-scale feature fusion module is introduced to extract feature information of different scales using five convolution kernels of different sizes, namely 1×1, 3×3, 5×5, 7×7, and 9×9. IMF1 Input 9×9 size convolution kernel, IMF2 Input 7×7 size convolution kernel, IMF3 Input a 5×5 size convolution kernel, IMF4 Input 3×3 size convolution kernel, IMF5 Input a 1×1 convolution kernel. The expansion coefficients are selected as 1, 12, 24, 36, and 48 respectively; then, the feature maps under the convolution kernels of 5 different receptive fields can be obtained, and the pixels are fused to form a multi-scale feature fusion module and added to the neural network. In the proposed module, batch normalization layer and ReLU activation layer are used after the convolution layer. Then the global average pooling (GAP) operation is imported, and finally the output is obtained through the fully connected layer. The output is the true value of the historical error of the electric energy meter after offline calibration. At this point, the construction of a neural network based on multi-scale feature fusion is completed. The time-frequency diagram obtained by the above processing of the digital current and voltage data of the electric energy meter is used as input, and the error value is used as output to train the error evaluation model of the electric energy meter.

[0049] Step 4: Input the voltage and current data of the day to be measured to predict the error of the electric energy meter.

[0050] The daily real-time data of the electric energy meter to be tested is extracted through polynomial interpolation and empirical mode decomposition to extract the signal component corresponding to the subscript, voltage or current in step 2, which is recorded as IMF1d , IMF2d , IMF3d , IMF4d , IMF5d , after wavelet transform, the time-frequency graph is obtained, the corresponding time-frequency graph is input into the trained model, and the error evaluation value of the electric energy meter is output.

[0051] It can be further understood that, in view of the current problems of heavy workload and low error evaluation efficiency of the electricity meter operation and maintenance staff, the present invention designs a multi-scale feature fusion neural network to get rid of the traditional method of offline detection of electricity meters and improve the accuracy of error evaluation. The results of evaluating the error (ratio error) of the electricity meter using the method of the present invention are shown in Table 1: Table 1: Energy meter error (ratio error) results

[0052] It can be understood that, as shown in Table 1, the error assessment deviation of the method of the present invention is small, and the accuracy is further quantified and characterized by the root mean square error. The root mean square error value is small, indicating that the patent model has a good accuracy rate for the electric energy meter and can be applied to the error assessment of the electric energy meter.

[0053]

[0054] It can be further understood that the electric energy meter measurement error evaluation method provided by the present invention mainly designs a multi-scale feature fusion neural network, combines wavelet transform, empirical mode decomposition and Z-SCORE standardization, designs a signal component fusion formula, and constructs an electric energy meter error evaluation model based on the correlation coefficient formula of the Kendall algorithm to realize the error state recognition of high-voltage electric energy without power outages, get rid of the traditional method of offline detection of electric energy meters, and make the detection accuracy higher.

[0055] In some embodiments of the present invention, performing empirical mode decomposition on the real-time data to obtain a plurality of signal components corresponding to the real-time data includes: The real-time data is parameterized to obtain corresponding assigned parameters, and the assigned parameters are subjected to empirical mode decomposition to obtain multiple signal components corresponding to the real-time data.

[0056] It can be understood that the collected voltage data, current data, temperature data and grid frequency data are respectively recorded as U C ,I C 、T C and V C , and perform polynomial interpolation on the voltage data, current data, temperature data and grid frequency data, and fit the interpolation polynomial according to the data to obtain continuous time series data, which are recorded as U S ,I S 、T S and V S , and perform EMD empirical mode decomposition on continuous time series data.

[0057] The specific process of EMD empirical mode decomposition is as follows: 1) Determine extreme points: Find all local maximum and minimum points in the signal.

[0058] 2) Generate upper and lower envelopes: By connecting adjacent extreme points, upper and lower envelopes are formed. These envelopes decompose the original signal into a series of parts with gradually changing oscillation frequencies.

[0059] 3) Calculate the mean: average the upper and lower envelopes to get the average envelope.

[0060] 4) Extract detail signal: Subtract the original signal from the average envelope to obtain the detail signal (Detail). If the detail signal meets certain conditions, it is called IMFs .

[0061] 5) Judgment IMFs :Check whether the detail signal meets IMFs The definition of , that is, the number of maximum and minimum values ​​in the entire data range is the same, and there is at most one local extreme point between the maximum and minimum in the entire data range.

[0062] 6) Repeat the steps: subtract the extracted signal from the original signal IMFs , and then repeat the above steps for the remaining signal until the remaining signal can no longer be decomposed into IMFs until.

[0063] 7) Convergence judgment: When the decomposition result meets a certain convergence criterion, stop the decomposition process.

[0064] 8) Get IMFs : The final set of IMFs The original signal can be approximately represented as a linear combination of these IMFs. U S After empirical mode decomposition, the signal components are obtained: IMF U1 , IMF U2 、...、IMF Un（U） ; I S After empirical mode decomposition, the signal components are obtained: IMF I1 、IMF I2 、...、IMF In(S) ; T S After empirical mode decomposition, the signal components are obtained: IMF T1 、IMF T2 、...、IMF Tn(T) ; V S After empirical mode decomposition, the signal components are obtained: IMF V1 , IMFV2 ,..., IMF Vn（V） .

[0065] In some embodiments of the present invention, performing empirical mode decomposition on the assigned parameters to obtain multiple signal components corresponding to the real-time data includes: The assigned parameters are fitted with interpolation polynomials to obtain continuous time series data, and the continuous time series data are subjected to empirical mode decomposition to obtain multiple signal components corresponding to the real-time data.

[0066] It can be understood that the collected voltage data, current data, temperature data and grid frequency data are respectively recorded as U C ,I C , T C and V C , and perform polynomial interpolation on the voltage data, current data, temperature data and grid frequency data, and fit the interpolation polynomial according to the data to obtain continuous time series data, which are recorded as U S ,I S , T S and V S , and perform EMD empirical mode decomposition on continuous time series data.

[0067] The specific process of EMD empirical mode decomposition is as follows: 1) Determine extreme points: Find all local maximum and minimum points in the signal.

[0068] 2) Generate upper and lower envelopes: By connecting adjacent extreme points, upper and lower envelopes are formed. These envelopes decompose the original signal into a series of parts with gradually changing oscillation frequencies.

[0069] 3) Calculate the mean: average the upper and lower envelopes to get the average envelope.

[0070] 4) Extract detail signal: Subtract the original signal from the average envelope to obtain the detail signal (Detail). If the detail signal meets certain conditions, it is called IMFs .

[0071] 5) Judgment IMFs :Check whether the detail signal meets IMFs The definition of , that is, the number of maximum and minimum values ​​in the entire data range is the same, and there is at most one local extreme point between the maximum and minimum in the entire data range.

[0072] 6) Repeat the steps: subtract the extracted signal from the original signal IMFs , and then repeat the above steps for the remaining signal until the remaining signal can no longer be decomposed into IMFs until.

[0073] 7) Convergence judgment: When the decomposition result meets a certain convergence criterion, stop the decomposition process.

[0074] 8) Get IMFs : The final set of IMFs The original signal can be approximately represented as a linear combination of these IMFs. U S After empirical mode decomposition, the signal components are obtained: IMF U1 , IMF U2 、...、IMF Un（U） ; I S After empirical mode decomposition, the signal components are obtained: IMF I1 、IMF I2 、...、IMF In(S) ; T S After empirical mode decomposition, the signal components are obtained: IMF T1 、IMF T2 、...、IMF Tn(T) ; V S After empirical mode decomposition, the signal components are obtained: IMF V1 , IMF V2 ,..., IMF Vn（V） .

[0075] In some embodiments of the present invention, performing Z-score normalization on the multiple signal components corresponding to the real-time data to obtain the target signal component includes: Matching multiple signal components corresponding to the real-time data with preset thresholds to obtain matched signal components; The matched signal components are Z-score normalized to obtain the target signal components.

[0076] It can be understood that the collected voltage data, current data, temperature data and grid frequency data are respectively recorded as U C ,I C 、T C and V C , and perform polynomial interpolation on the voltage data, current data, temperature data and grid frequency data, and fit the interpolation polynomial according to the data to obtain continuous time series data, which are recorded as U S ,I S 、T S and V S , and perform EMD empirical mode decomposition on continuous time series data.

[0077] The specific process of EMD empirical mode decomposition is as follows: 1) Determine extreme points: Find all local maximum and minimum points in the signal.

[0078] 2) Generate upper and lower envelopes: By connecting adjacent extreme points, upper and lower envelopes are formed. These envelopes decompose the original signal into a series of parts with gradually changing oscillation frequencies.

[0079] 3) Calculate the mean: average the upper and lower envelopes to get the average envelope.

[0080] 4) Extract detail signal: Subtract the original signal from the average envelope to obtain the detail signal (Detail). If the detail signal meets certain conditions, it is called IMFs .

[0081] 5) Judgment IMFs :Check whether the detail signal meets IMFs The definition of , that is, the number of maximum and minimum values ​​in the entire data range is the same, and there is at most one local extreme point between the maximum and minimum in the entire data range.

[0082] 6) Repeat the steps: subtract the extracted signal from the original signal IMFs , and then repeat the above steps for the remaining signal until the remaining signal can no longer be decomposed into IMFs until.

[0083] 7) Convergence judgment: When the decomposition result meets a certain convergence criterion, stop the decomposition process.

[0084] 8) Get IMFs : The final set of IMFs The original signal can be approximately represented as a linear combination of these IMFs. U s After empirical mode decomposition, the signal components are obtained: IMF U1 , IMF U2 、...、IMF Un（U） ; I S After empirical mode decomposition, the signal components are obtained: IMF I1 、IMF I2 、...、IMF In(S) ; T S After empirical mode decomposition, the signal components are obtained: IMF T1 、IMF T2 、...、IMF Tn(T) ; V SAfter empirical mode decomposition, the signal components are obtained: IMF V1 , IMF V2 ,..., IMF Vn（V） .

[0085] In some embodiments of the present invention, performing Z-score normalization on the matched signal components to obtain the target signal components includes: The matched signal components are Z-score standardized to obtain weight values ​​corresponding to the multiple signal components, and the target signal components are obtained based on the weight values ​​corresponding to the multiple signal components.

[0086] It is understandable that Ts After empirical mode decomposition, the signal components are obtained: IMF T1 , IMF T2 ,..., IMF Tn(T) ,and Vs After empirical mode decomposition, the signal components are obtained: IMF V1 , IMF V2 ,..., IMF Vn（V） Take the first three items, that is IMF T1 , IMF T2 , IMF T3 ,and IMF V1 , IMF V2 , IMF V3 , perform Z-score standardization on it, that is, calculate each value of these 6 time series data: IMF T1 For example,

[0087] in, for IMF T1 No. x The data are observations, for IMF T1 The mean of for IMF T1 The standard deviation of , , and composed of , similarly calculated , , , , , , , , , Get and calculate , , , , .

[0088] Construct signal reference sequence value , , The calculation formula is as follows:

[0089] in, For signal The yth data of , Signal data composition , the following is obtained by the same logic and .

[0090]

[0091]

[0092] Further, calculate one by one , , The rank correlation coefficient K of the signal component converted from the voltage and current data EMD.

[0093]

[0094] in, for S 1 and IMF U1 The correlation coefficient of ， Similarly, we can calculate all , calculate each IMF and Sn of K Worth it ， like ， Will Sort from largest to smallest to get the 5 with the largest values K value 。Record the corresponding 5 current / voltage signal component subscripts, and the corresponding 5 signal components are recorded as IMF 1 、IMF 2 、IMF 3 、IMF 4 、IMF 5.

[0095] In some embodiments of the present invention, obtaining the target signal component based on the weight values ​​corresponding to the multiple signal components includes: The weight values ​​corresponding to the multiple signal components are sorted in order to obtain the target signal component.

[0096] It is understandable that Ts After empirical mode decomposition, the signal components are obtained: IMF T1 , IMF T2 ,..., IMF Tn(T) ,and Vs After empirical mode decomposition, the signal components are obtained: IMF V1 , IMF V2 ,..., IMF Vn（V） Take the first three items, that is IMF T1 , IMF T2 , IMF T3 ,and IMF V1 , IMF V2 , IMF V3 , perform Z-score standardization on it, that is, calculate each value of these 6 time series data: IMF T1 For example,

[0097] in, for IMF T1 No. x The data are observations, for IMF T1 The mean of for IMF T1 The standard deviation of , , and form , similarly calculated , , , , , , , , , Get and calculate , , , , .

[0098] Construct signal reference sequence value , , The calculation formula is as follows:

[0099] in, For signal The yth data of , Signal data composition , the following is obtained by the same logic and .

[0100]

[0101]

[0102] Further, calculate one by one , , The rank correlation coefficient K of the signal component converted from the voltage and current data EMD.

[0103]

[0104] in, for S 1 and IMF U1 The correlation coefficient of ， Similarly, we can calculate all , calculate each IMF and Sn of K Worth it ， like ， Will Sort from largest to smallest to get the 5 with the largest values K value 。 Record the corresponding 5 current / voltage signal component subscripts, and the corresponding 5 signal components are recorded as IMF1 、IMF 2 、IMF 3 、IMF 4 、IMF 5.

[0105] In some embodiments of the present invention, the step of sorting the weight values ​​corresponding to the plurality of signal components to obtain the target signal component includes: The weight values ​​corresponding to the multiple signal components are sorted by size to obtain a sorting result, and based on the sorting result, a target signal component is obtained.

[0106] It is understandable that Ts After empirical mode decomposition, the signal components are obtained: IMF T1 , IMF T2 ,..., IMF Tn(T) ,and Vs After empirical mode decomposition, the signal components are obtained: IMF V1 , IMF V2 ,..., IMF Vn（V） Take the first three items, that is IMF T1 , IMF T2 , IMF T3 ,and IMF V1 , IMF V2 , IMF V3 , perform Z-score standardization on it, that is, calculate each value of these 6 time series data: IMF T1 For example,

[0107] in, for IMF T1 No. x The data are observations, for IMF T1 The mean of for IMF T1 The standard deviation of , , and composed of , similarly calculated , , , , , , , , , Get and calculate , , , , .

[0108] Construct signal reference sequence value , , The calculation formula is as follows:

[0109] in, For signal The yth data of , Signal data composition , the following is obtained by the same logic and .

[0110]

[0111]

[0112] Further, calculate one by one , , The rank correlation coefficient K of the signal component converted from the voltage and current data EMD.

[0113]

[0114] in, for S 1 and IMF U1 The correlation coefficient of ， Similarly, we can calculate all , calculate each IMF and Sn of K Worth it ， like ， Will Sort from largest to smallest to get the 5 with the largest values K value 。 Record the corresponding 5 current / voltage signal component subscripts, and the corresponding 5 signal components are recorded as IMF 1 、IMF 2 、IMF3 、IMF 4 、IMF 5.

[0115] Figure 3 A schematic diagram of an embodiment of the electric energy meter measurement error evaluation device provided by the present invention includes: The data acquisition module 301 is used to acquire the real-time data of the electric energy meter to be tested; An empirical mode decomposition module 302 is used to perform empirical mode decomposition on the real-time data to obtain multiple signal components corresponding to the real-time data; The standardization processing module 303 is used to perform Z-score standardization on multiple signal components corresponding to the real-time data to obtain a target signal component; The wavelet transform module 304 is used to perform wavelet transform on the target signal component to obtain a two-dimensional time-frequency image; The output module 305 is used to input the two-dimensional time-frequency image into the trained electric energy meter error prediction model to obtain the error prediction result of the electric energy meter.

[0116] The electric energy meter measurement error assessment device 300 provided in the above embodiment can implement the technical solution described in the above electric energy meter measurement error assessment method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above electric energy meter measurement error assessment method embodiment, which will not be repeated here.

[0117] like Figure 4 As shown, the present invention also provides an electronic device 400. The electronic device 400 includes a processor 401, a memory 402 and a display 403. Figure 4 Only some components of the electronic device 400 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0118] In some embodiments, the processor 401 may be a central processing unit (CPU), a microprocessor or other data processing chip, which is used to run the program code or process data stored in the memory 402, such as the electric energy meter measurement error evaluation method of the present invention.

[0119] In some embodiments, processor 401 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, processor 401 may be local or remote. In some embodiments, processor 401 may be implemented in a cloud platform. In one embodiment, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.

[0120] In some embodiments, the memory 402 may be an internal storage unit of the electronic device 400, such as a hard disk or memory of the electronic device 400. In other embodiments, the memory 402 may also be an external storage device of the electronic device 400, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 400.

[0121] Furthermore, the memory 402 may include both an internal storage unit of the electronic device 400 and an external storage device. The memory 402 is used to store application software installed in the electronic device 400 and various data.

[0122] In some embodiments, the display 403 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 404 is used to display information on the electronic device 400 and to display a visual user interface. The components 401-403 of the electronic device 400 communicate with each other via a system bus.

[0123] In one embodiment, when the processor 401 executes the electric energy meter measurement error evaluation program in the memory 402, the following steps may be implemented: Obtain the real-time data of the electric energy meter to be tested; the real-time data includes: voltage, current, temperature and acquisition frequency; Performing empirical mode decomposition on the real-time data to obtain multiple signal components corresponding to the real-time data; Perform Z-score standardization on multiple signal components corresponding to real-time data to obtain target signal components; Perform wavelet transform on the target signal component to obtain a two-dimensional time-frequency image; Input the two-dimensional time-frequency image into the trained electric energy meter error prediction model to obtain the error prediction result of the electric energy meter; Among them, the electric energy meter error prediction model includes: Convolutional layer, normalization layer, ReLU activation layer, global average pooling layer and fully connected layer connected in series.

[0124] It should be understood that: when the processor 401 executes the electric energy meter measurement error evaluation program in the memory 402, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0125] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 400 mentioned, and the electronic device 400 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 400 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0126] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions in the electric energy meter measurement error evaluation method provided in the above-mentioned method embodiments can be implemented.

[0127] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0128] The above is a detailed introduction to the electric energy meter measurement error evaluation method, device, electronic device and storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for evaluating measurement error of an electric energy meter, characterized in that: include: Obtain real-time data of the electric energy meter to be tested; Real-time data include: voltage, current, temperature and acquisition frequency; Performing empirical mode decomposition on the real-time data to obtain multiple signal components corresponding to the real-time data; Perform Z-score standardization on multiple signal components corresponding to real-time data to obtain target signal components; Perform wavelet transform on the target signal component to obtain a two-dimensional time-frequency image; Input the two-dimensional time-frequency image into the trained electric energy meter error prediction model to obtain the error prediction result of the electric energy meter; Among them, the electric energy meter error prediction model includes: Convolutional layer, normalization layer, ReLU activation layer, global average pooling layer and fully connected layer connected in series.

2. The method for evaluating the measurement error of an electric energy meter according to claim 1, characterized in that: The real-time data is subjected to empirical mode decomposition to obtain a plurality of signal components corresponding to the real-time data, including: The real-time data is parameterized to obtain corresponding assigned parameters, and the assigned parameters are subjected to empirical mode decomposition to obtain multiple signal components corresponding to the real-time data.

3. The method for evaluating the measurement error of an electric energy meter according to claim 2, characterized in that: The step of performing empirical mode decomposition on the assigned parameters to obtain multiple signal components corresponding to the real-time data includes: The assigned parameters are fitted with interpolation polynomials to obtain continuous time series data, and the continuous time series data are subjected to empirical mode decomposition to obtain multiple signal components corresponding to the real-time data.

4. The method for evaluating the measurement error of an electric energy meter according to claim 1, characterized in that: The Z-score normalization of the multiple signal components corresponding to the real-time data to obtain the target signal component includes: Matching multiple signal components corresponding to the real-time data with preset thresholds to obtain matched signal components; The matched signal components are Z-score normalized to obtain the target signal components.

5. The method for evaluating the measurement error of an electric energy meter according to claim 4, characterized in that: The Z-score normalization of the matched signal components to obtain the target signal components includes: The matched signal components are Z-score standardized to obtain weight values ​​corresponding to the multiple signal components, and the target signal components are obtained based on the weight values ​​corresponding to the multiple signal components.

6. The method for evaluating the measurement error of an electric energy meter according to claim 5, characterized in that: The obtaining of the target signal component based on the weight values ​​corresponding to the plurality of signal components comprises: The weight values ​​corresponding to the multiple signal components are sorted in order to obtain the target signal component.

7. The method for evaluating the measurement error of an electric energy meter according to claim 6, characterized in that: The step of sorting the weight values ​​corresponding to the plurality of signal components to obtain the target signal component includes: The weight values ​​corresponding to the multiple signal components are sorted by size to obtain a sorting result, and based on the sorting result, a target signal component is obtained.

8. An electric energy meter measurement error evaluation device, characterized in that: include: A data acquisition module is used to acquire real-time data of the electric energy meter to be tested; An empirical mode decomposition module is used to perform empirical mode decomposition on real-time data to obtain multiple signal components corresponding to the real-time data; A standardization processing module is used to perform Z-score standardization on multiple signal components corresponding to real-time data to obtain a target signal component; A wavelet transform module is used to perform wavelet transform on the target signal component to obtain a two-dimensional time-frequency image; The output module is used to input the two-dimensional time-frequency image into the trained electric energy meter error prediction model to obtain the error prediction result of the electric energy meter.

9. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the method for evaluating measurement errors of an electric energy meter as described in any one of claims 1 to 7 above.

10. A computer-readable storage medium, characterized in that: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the method for evaluating the measurement error of an electric energy meter as described in any one of claims 1 to 7.

Images