Electric energy meter fault detection method and device based on electric quantity response, computer equipment and storage medium

Abstract

The embodiment of the invention provides an electric energy meter fault detection method and device based on electric quantity response, computer equipment, a storage medium and a computer program product, and relates to the technical field of electric power detection. The method comprises the steps of obtaining target electric quantity data of a to-be-tested electric energy meter; performing dimension reduction processing on the target electric quantity data to obtain dimension-reduced electric quantity data of the to-be-tested electric energy meter; comparing the dimension reduction electric quantity data with a pre-constructed electric energy meter fault mode library to obtain a fault comparison result of the to-be-detected electric energy meter; and obtaining a fault detection result of the to-be-detected electric energy meter according to the fault comparison result. According to the method, the problems of complex operation and high operation cost caused by uncovering detection are avoided, the intelligence of fault detection of the electric energy meter is improved, the operation cost of fault detection of the electric energy meter is reduced, and then the efficiency, simplicity and accuracy of fault detection of the electric energy meter can be improved.

Description

Technical Field

[0001] The present application relates to the field of electric power detection technology, and in particular to an electric energy meter fault detection method, device, computer equipment, storage medium and computer program product based on electric quantity response. Background Art

[0002] With the rapid development of social economy and the popularization of electricity information collection, the number of energy meters in the power system has doubled. Every year, a huge number of energy meters are removed due to rotation, failure, functional replacement, policy removal and other reasons. The energy metering device is an important tool for accurate measurement, precise trade settlement, fair and just transactions and assessment of economic and technical indicators within the power system between power generation companies, power grid companies, power sales companies and power users. The accuracy and stability of its operation are directly related to the economic interests of both parties to the trade. The recycling of energy meters can reduce the exploitation and consumption of natural resources and reduce the impact on the environment. It can also reduce production costs and improve resource utilization efficiency, which can effectively promote the sustainable use of resources and sustainable economic development. Due to the dispersion and small number of old energy meters, the work execution process faces a series of problems such as inconsistent sorting standards, inability to implement professional maintenance, and irregular scrapping and disposal, resulting in about 20% of the reusable old energy meters being directly scrapped, resulting in a large amount of resource waste and a large amount of electronic waste, which seriously pollutes the environment.

[0003] In the actual process of testing the energy meter, it is difficult to quickly and accurately judge the internal fault of the energy meter, which results in only being able to diagnose the externally visible faults, but unable to accurately determine the specific type and cause of the internal faults. In addition, the task of sorting and testing the disassembled smart energy meters for sorting is arduous, and the sorting cannot be completed in a timely and efficient manner, which easily increases the pressure on the grassroots warehouses and wastes effective storage capacity resources. There are pain points such as low manual work efficiency, difficulty in equipment reuse, inflexible storage capacity configuration, difficulty in mining data value, and extensive asset management. Summary of the invention

[0004] Based on this, it is necessary to provide an electric energy meter fault detection method, device, computer equipment, storage medium and computer program product based on electrical quantity response to address the above technical problems.

[0005] In a first aspect, the present application provides a method for detecting electric energy meter faults based on electric quantity response. The method comprises:

[0006] Obtain target power data of the electric energy meter to be tested;

[0007] Performing dimensionality reduction processing on the target electric quantity data to obtain dimensionality reduced electric quantity data of the electric energy meter to be tested;

[0008] Comparing the dimension-reduced electricity data with a pre-built electric energy meter fault mode library to obtain a fault comparison result of the electric energy meter to be tested;

[0009] According to the fault comparison result, the fault detection result of the electric energy meter to be tested is obtained.

[0010] In one of the embodiments, before obtaining the target power data of the electric energy meter to be tested, it also includes: obtaining initial sample power data of the sample electric energy meter; performing data preprocessing on the initial sample power data to obtain target sample power data corresponding to the initial sample power data; using a pre-constructed fault detection model, based on the target sample power data, obtaining a sample fault detection result of the sample electric energy meter; and constructing a fault mode library of the electric energy meter according to the sample fault detection result.

[0011] In one of the embodiments, the use of a pre-built fault detection model to obtain a sample fault detection result of the sample electric energy meter based on the target sample electric energy data includes: inputting the target sample electric energy data into the pre-built fault detection model; determining and outputting the electric energy characteristics of the sample electric energy meter according to the target sample electric energy data by a feature extraction module in the fault detection model; and determining and outputting the sample fault detection result of the sample electric energy meter according to the electric energy characteristics output by the feature extraction module by a classification module of the fault detection model.

[0012] In one of the embodiments, the fault detection result of the electric energy meter to be tested is obtained based on the fault comparison result, including: if the fault comparison result indicates that there is no matching fault type that matches the reduced-dimensionality electric energy data in the fault mode library of the electric energy meter, then determining that the fault detection result of the electric energy meter to be tested is a normal electric energy meter; if the fault comparison result indicates that there is a matching fault type that matches the reduced-dimensionality electric energy data in the fault mode library of the electric energy meter, then determining the fault detection result of the electric energy meter to be tested based on the matching fault type.

[0013] In one of the embodiments, the obtaining of target power data of the electric energy meter to be tested includes: obtaining initial power data of the electric energy meter to be tested; and performing data preprocessing on the initial power data to obtain the target power data.

[0014] In one of the embodiments, the data preprocessing of the initial power data to obtain the target power data includes: data cleaning of the initial power data to obtain candidate power data of the power meter to be tested; missing value processing of the candidate power data to obtain complete power data of the power meter to be tested; and obtaining the target power data based on the complete power data.

[0015] In a second aspect, the present application provides an electric energy meter fault detection device based on electric quantity response. The device comprises:

[0016] A data acquisition module is used to obtain target power data of the electric energy meter to be tested;

[0017] A dimension reduction module, used for performing dimension reduction processing on the target electric quantity data to obtain the dimension reduced electric quantity data of the electric energy meter to be tested;

[0018] A comparison module, used for comparing the dimension-reduced electricity data with a pre-built electric energy meter fault mode library to obtain a fault comparison result of the electric energy meter to be tested;

[0019] The acquisition module is used to acquire the fault detection result of the electric energy meter to be tested according to the fault comparison result.

[0020] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0021] Obtain target power data of the electric energy meter to be tested;

[0022] Performing dimensionality reduction processing on the target electric quantity data to obtain dimensionality reduced electric quantity data of the electric energy meter to be tested;

[0023] Comparing the dimension-reduced electricity data with a pre-built electric energy meter fault mode library to obtain a fault comparison result of the electric energy meter to be tested;

[0024] According to the fault comparison result, the fault detection result of the electric energy meter to be tested is obtained.

[0025] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0026] Obtain target power data of the electric energy meter to be tested;

[0027] Performing dimensionality reduction processing on the target electric quantity data to obtain dimensionality reduced electric quantity data of the electric energy meter to be tested;

[0028] Comparing the dimension-reduced electricity data with a pre-built electric energy meter fault mode library to obtain a fault comparison result of the electric energy meter to be tested;

[0029] According to the fault comparison result, the fault detection result of the electric energy meter to be tested is obtained.

[0030] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0031] Obtain target power data of the electric energy meter to be tested;

[0032] Performing dimensionality reduction processing on the target electric quantity data to obtain dimensionality reduced electric quantity data of the electric energy meter to be tested;

[0033] Comparing the dimension-reduced electricity data with a pre-built electric energy meter fault mode library to obtain a fault comparison result of the electric energy meter to be tested;

[0034] According to the fault comparison result, the fault detection result of the electric energy meter to be tested is obtained.

[0035] In the above-mentioned electric energy meter fault detection method, device, computer equipment, storage medium and computer program product based on electric energy response, first, the target electric energy data of the electric energy meter to be tested can be obtained; next, the target electric energy data can be subjected to dimensionality reduction processing to obtain the reduced-dimensional electric energy data of the electric energy meter to be tested; then, the reduced-dimensional electric energy data can be compared with the pre-constructed electric energy meter fault mode library to obtain the fault comparison result of the electric energy meter to be tested; finally, the fault detection result of the electric energy meter to be tested can be obtained according to the fault comparison result. In the method provided by the embodiment of the present application, the electric energy data of the electric energy meter to be tested can be subjected to dimensionality reduction processing, the accuracy of fault detection can be improved, and the fault detection model can be trained by using a convolutional neural network, and the electric energy meter fault mode library can be constructed by using the fault detection model. Then, the fault detection result of the electric energy meter to be tested can be obtained based on the electric energy meter fault mode library, which avoids the problems of complex operation and high operation cost caused by cover opening detection, improves the intelligence of electric energy meter fault detection, reduces the operation cost of electric energy meter fault detection, and then, can improve the efficiency, simplicity and accuracy of electric energy meter fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] FIG1 is a schematic flow chart of a method for detecting a fault in an electric energy meter based on electric quantity response according to an embodiment of the present application;

[0038] FIG2 is a schematic diagram of a process for constructing a fault mode library of an electric energy meter provided in an embodiment of the present application;

[0039] FIG3 is a schematic diagram of a process for obtaining a sample fault detection result provided by an embodiment of the present application;

[0040] FIG4 is a structural block diagram of an electric energy meter fault detection device based on electric quantity response provided in an embodiment of the present application;

[0041] FIG5 is an internal structure diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0043] In an exemplary embodiment, as shown in FIG1 , a method for detecting faults of an electric energy meter based on electric quantity response is provided. This embodiment is illustrated by applying the method to a server. It is understandable that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0044] Step 102, obtaining target power data of the electric energy meter to be tested.

[0045] Among them, the electric energy meter to be tested can be any electric energy meter that needs to be fault-detected. The electric energy meter type of the electric energy meter can include multiple electric energy meter categories, and the multiple electric energy meter categories can include but are not limited to single-phase meters, three-phase four-wire fee control meters, three-phase three-wire multi-function meters, and three-phase four-wire multi-function meters, etc. The electric energy meter type of the electric energy meter to be tested can be any one of single-phase meters, three-phase four-wire fee control meters, three-phase three-wire multi-function meters, and three-phase four-wire multi-function meters. In this step, in the process of obtaining the target electric energy data of the electric energy meter to be tested, first, the initial electric energy data of the electric energy meter to be tested can be obtained; next, the initial electric energy data can be preprocessed to obtain the target electric energy data of the electric energy meter to be tested, and the target electric energy data can be the preprocessed electric energy data. Acquiring the initial electric quantity data may include: loading input signals of different waveforms on the electric energy meter to be tested at a fixed position of the electric energy meter to be tested, and the input signal may be a sinusoidal signal containing harmonics of different proportions, and then, various types of electric quantity data stored in the microcontroller unit (MCU) may be read at the RS485 communication port of the electric energy meter, which is the response of the circuit to the input signal, i.e., the electric quantity response. By combining the input signal with the electric quantity response, the transfer function of the internal circuit of the electric energy meter can be obtained, thereby obtaining its circuit characteristics, which can be used as a basis for fault diagnosis. The initial electric quantity data may include, but is not limited to, current value, voltage value, power factor, instantaneous active power, instantaneous reactive power, and phase angle, etc. The data preprocessing may include data cleaning, missing value processing and data format adjustment, etc., wherein the data cleaning may check whether there are duplicate data points and / or abnormal data points in the initial power data, for example, whether there are exactly the same data points in the initial power data, that is, duplicate data, if there are duplicate data points, then remove one or more of the duplicate data points and retain one data point; detect whether there are abnormal data points in the initial power data, such as extremely large and extremely small values ​​and abnormal timestamps, if there are abnormal data points in the initial power data, then correct the abnormal data points. For example, if the timestamp is not within a reasonable time range or there are missing values, you can choose to delete or repair it through interpolation methods. Missing value processing can perform missing detection on the data value of each data point in the multiple data points of the initial power data to detect whether there are missing values. If the number of missing values ​​is relatively small, you can choose to delete the data points containing missing values; if the number of missing values ​​is large, you can choose to fill the missing values ​​with interpolation methods, such as linear interpolation, mean filling, etc. Data format adjustment can detect the data format of each field in the initial power data to ensure that the data type is correct. For example, convert the timestamp field to date and time type. If the unit of the power data does not match the requirement, you can perform unit conversion to ensure data consistency.

[0046] Step 104 , performing dimension reduction processing on the target electric quantity data to obtain dimension reduced electric quantity data of the electric energy meter to be tested.

[0047] Among them, in this step, the principal component analysis method can be used to reduce the dimension of the target power data, find the pattern in the target power data and project the target power data into a new feature space. Its main goal is to find a new coordinate system that can retain the original data variable information to the greatest extent through linear transformation, so as to achieve the dimension reduction and removal of redundant information of the target power data. Principal component analysis, also known as principal component analysis, aims to use the idea of ​​dimensionality reduction to transform multiple indicators into a few comprehensive indicators (i.e., principal components), in which each principal component can reflect most of the information of the original variable, and the information contained is not repeated. A given set of related variables can be transformed into another set of unrelated variables through linear transformation, and these new variables are arranged in descending order of variance. In the mathematical transformation, the total variance of the variables is kept unchanged, so that the first variable has the largest variance, which is called the first principal component, and the variance of the second variable is the second largest, and is unrelated to the first variable, which is called the second principal component. By analogy, there are I principal components for I variables. In this step, the reduced-dimensionality electricity data can be an unrelated variable after conversion. One reduced-dimensionality electricity data corresponds to one principal component. The number of data points contained in the reduced-dimensionality electricity data is lower than the number of data points contained in the target electricity data, thereby achieving dimensionality reduction of the target electricity data.

[0048] Step 106 , comparing the dimension-reduced electricity data with a pre-built electricity meter fault mode library to obtain a fault comparison result of the electricity meter to be tested.

[0049] Among them, the electric energy meter fault mode library may include multiple electric quantity data, multiple electric energy meter fault types, and the corresponding relationship between the multiple electric quantity data and the multiple electric energy meter fault types. By matching the reduced-dimensional electric quantity data of the electric energy meter to be tested with the multiple electric quantity data in the electric energy meter fault mode library, the matching electric quantity data of the reduced-dimensional electric quantity data can be obtained, and then, the matching fault type of the reduced-dimensional electric quantity data can be determined according to the matching electric quantity data. Based on this, the fault comparison result of the electric energy meter to be tested can be obtained according to the matching electric quantity data and the matching fault type of the reduced-dimensional electric quantity data. The fault comparison result can be used to indicate whether the matching electric quantity data and the matching fault type of the electric energy meter to be tested exist in the electric energy meter fault mode library. If the matching electric quantity data and the matching fault type of the electric energy meter to be tested exist, it can be used to indicate the matching electric quantity data and the matching fault type corresponding to the electric energy meter to be tested.

[0050] Step 108, obtaining the fault detection result of the electric energy meter to be tested according to the fault comparison result.

[0051] Among them, if the fault comparison result indicates that there is no matching fault type matching the reduced-dimensionality electricity data in the fault pattern library of the electric energy meter, the fault detection result of the electric energy meter to be tested is determined to be a normal electric energy meter; if the fault comparison result indicates that there is a matching fault type matching the reduced-dimensionality electricity data in the fault pattern library of the electric energy meter, the fault detection result of the electric energy meter to be tested is determined according to the matching fault type. The fault detection result can be used to indicate whether the electric energy meter to be tested has a fault, and if the electric energy meter to be tested has a fault, the fault detection result can indicate the fault category of the electric energy meter to be tested.

[0052] In the method of this embodiment, first, the target power data of the electric energy meter to be tested can be obtained; next, the target power data can be subjected to dimensionality reduction processing to obtain the reduced-dimensional power data of the electric energy meter to be tested; then, the reduced-dimensional power data can be compared with the pre-constructed electric energy meter fault mode library to obtain the fault comparison result of the electric energy meter to be tested; finally, the fault detection result of the electric energy meter to be tested can be obtained according to the fault comparison result. In the method provided by the embodiment of the present application, the power data of the electric energy meter to be tested can be subjected to dimensionality reduction processing, which improves the accuracy of fault detection, and a convolutional neural network can be used to train a fault detection model, and an electric energy meter fault mode library can be constructed using the fault detection model. Then, based on the electric energy meter fault mode library, the fault detection result of the electric energy meter to be tested can be obtained, which avoids the problems of complex operation and high operating cost caused by cover opening detection, improves the intelligence of electric energy meter fault detection, and reduces the operating cost of electric energy meter fault detection. Then, the efficiency, simplicity and accuracy of electric energy meter fault detection can be improved.

[0053] In an exemplary embodiment, as shown in FIG2 , the embodiment of the present application further includes the following steps, which are used to provide an implementation method for building a fault mode library of an electric energy meter, and specifically may include steps 202 to 208. Among them:

[0054] Step 202: Acquire initial sample electricity data of a sample electricity meter.

[0055] Among them, the multiple sample electric energy meters include electric energy meters of multiple electric energy meter types. The multiple electric energy meter types may include but are not limited to single-phase meters, three-phase four-wire fee control meters, three-phase three-wire multifunctional meters, and three-phase four-wire multifunctional meters, etc. Each meter type has normal meter samples and faulty meter samples, and comes from different manufacturers. An input signal of different waveforms is loaded on the fixed table position of the sample electric energy meter. The input signal may be a sinusoidal signal containing harmonics of different proportions. Then, various types of electric quantity data stored in the microcontroller unit (MCU) can be read at the RS485 communication port of the electric energy meter, which is the response of the circuit to the input signal, that is, the electric quantity response. By combining the input signal and the electric quantity response, the transfer function of the internal circuit of the electric energy meter can be obtained, thereby obtaining its circuit characteristics, which can be used as a basis for fault diagnosis. The initial sample electric quantity data may include but are not limited to current value, voltage value, power factor, instantaneous active power, instantaneous reactive power, and phase angle, etc.

[0056] Step 204 , performing data preprocessing on the initial sample power data to obtain target sample power data corresponding to the initial sample power data.

[0057] The data preprocessing may include data cleaning, missing value processing and data format adjustment, etc., wherein the data cleaning may check whether there are duplicate data points and / or abnormal data points in the initial sample power data, for example, whether there are exactly the same data points, i.e., duplicate data, in the initial sample power data. If there are duplicate data points, one or more of the duplicate data points are removed and one data point is retained; detect whether there are abnormal data points in the initial sample power data, such as extremely large and extremely small values ​​and abnormal timestamps, and if there are abnormal data points in the initial sample power data, the abnormal data points are corrected. For example, if the timestamp is not within a reasonable time range or there are missing values, it can be deleted or repaired by interpolation methods. Missing value processing can detect the missing value of each data point in the multiple data points of the initial sample power data, and detect whether there are missing values. If the number of missing values ​​is relatively small, the data points containing missing values ​​can be deleted; if the number of missing values ​​is large, the interpolation method can be selected to fill the missing values, such as linear interpolation, mean filling, etc. The data format adjustment can detect the data format of each field in the initial sample power data to ensure that the data type is correct. For example, convert the timestamp field to a date and time type. If the unit of the electricity data does not match the demand, unit conversion can be performed to ensure data consistency. In this step, the data preprocessing may also include dimensionality reduction processing of the initial sample electricity data to obtain the target sample electricity data of the sample electric energy meter. The target sample electricity data may be electricity data after data cleaning, missing value processing, data format adjustment and dimensionality reduction processing. In one possible implementation, the principal component analysis method may be used to perform dimensionality reduction processing on the initial sample electricity data after data processing, discover patterns in the initial sample electricity data and project the initial sample electricity data into a new feature space. Its main goal is to find a new coordinate system that can retain the original data variable information to the greatest extent through linear transformation, thereby achieving dimensionality reduction and removing redundant information of the initial sample electricity data.

[0058] Step 206 , using the pre-built fault detection model, based on the target sample electricity data, obtain a sample fault detection result of the sample electric energy meter.

[0059] Among them, the pre-trained fault detection model can be a convolutional neural network (CNN). The pre-trained fault detection model may include an input layer, at least one convolutional layer, at least one pooling layer, a fully connected layer and an output layer. The feature extraction module of the fault detection model may include at least one convolutional layer and at least one pooling layer; the classification module of the fault detection model may include at least one fully connected layer. The feature extraction module in the fault detection model may include at least one convolutional layer and at least one pooling layer, and the classification module in the fault detection model may include at least one fully connected layer. The convolutional layer is used to extract the features of the input data; the pooling layer is used to sample the input data. Both the convolutional layer and the pooling layer include an activation function. Specifically, the target sample power data can be input into the pre-built fault detection model; the feature extraction module in the fault detection model determines and outputs the power features of the sample electric energy meter according to the target sample power data; the classification module of the fault detection model determines and outputs the sample fault detection result of the sample electric energy meter according to the power features output by the feature extraction module.

[0060] Step 208: construct an electric energy meter fault mode library according to the sample fault detection results.

[0061] The sample fault detection result may include an electric energy meter identification, sample electric quantity data and an electric energy meter fault type (or fault category) of a sample electric energy meter, and the electric energy meter identification may include an electric energy meter type identification and an electric energy meter number. The electric energy meter fault mode library may include multiple electric quantity data, multiple electric energy meter fault types, and corresponding relationships between the multiple electric quantity data and the multiple electric energy meter fault types.

[0062] In the method of this embodiment, a pre-built fault detection model can be used to construct an electric energy meter fault mode library, which is convenient for subsequent use of the electric energy meter fault mode library to perform fault detection on the electric energy meter, thereby improving the intelligence of electric energy meter fault detection and reducing the operating cost of electric energy meter fault detection. Furthermore, the efficiency, simplicity and accuracy of electric energy meter fault detection can be improved.

[0063] In an exemplary embodiment, as shown in FIG3 , step 206 may include steps 302 to 306. Among them:

[0064] Step 302: input the target sample power data into a pre-built fault detection model.

[0065] Step 304 : The feature extraction module in the fault detection model determines and outputs the power feature of the sample electric energy meter according to the target sample power data.

[0066] Step 306: The classification module of the fault detection model determines and outputs a sample fault detection result of the sample electric energy meter according to the electric quantity feature output by the feature extraction module.

[0067] The feature extraction module in the fault detection model may include at least one convolution layer and at least one pooling layer, and the classification module in the fault detection model may include at least one fully connected layer. The convolution layer is used to extract the features of the input data; the pooling layer is used to sample the input data. The convolution layer and the pooling layer both include an activation function. The target sample power data may include multiple power data.

[0068] Specifically, the target sample power data can be input into the pre-trained fault detection model, and the convolution layer can be used to extract the initial features of multiple power data. The first step is to convert multiple power data into vectors to obtain multiple power data vectors, which can be combined into a power data vector matrix; the second step is to input the power data vector matrix into the convolution layer, and use the convolution kernel to perform convolution operation with the power data vector matrix, that is, to perform inner product operation on the power data vector matrix and the convolution kernel to obtain the convolution result corresponding to the power data vector matrix; next, based on the activation function, the convolution result is nonlinearly transformed, and the bias vector is added to obtain the initial feature vector; the third step is to input the initial feature vector into the pooling layer, and the initial feature vector can be sampled; then, based on the activation function, the feature sampling result is nonlinearly transformed, and the bias vector is added to obtain the power characteristics of the sample electric energy meter.

[0069] The fully connected layer can be classified according to the electric quantity feature to obtain the fault category of the sample electric energy meter. In addition, the fully connected layer may include an activation function, and the activation function includes a weight matrix and a bias constant.

[0070] Specifically, the electric quantity feature can be input into the fully connected layer, and the electric quantity feature can be nonlinearly transformed based on the weight matrix and bias vector of the activation function, and then normalized to obtain the fault category of the sample electric energy meter. The fault category can indicate whether the sample electric energy meter has a fault, and can also indicate the corresponding fault type when the sample electric energy meter has a fault. Furthermore, the sample fault detection result of the sample electric energy meter can be obtained according to the fault category. The sample fault detection result can be used to indicate whether the sample electric energy meter has a fault, and if the sample electric energy meter has a fault, the sample fault detection result can indicate the fault category of the sample electric energy meter.

[0071] In the method of this embodiment, a fault detection model can be combined to obtain sample fault detection results of sample electricity meters, thereby improving the intelligence of electricity meter fault detection, reducing the operating cost of electricity meter fault detection, and further improving the efficiency, simplicity and accuracy of electricity meter fault detection.

[0072] In an exemplary embodiment, step 108 may include:

[0073] If the fault comparison result indicates that there is no matching fault type in the electric energy meter fault pattern library that matches the reduced-dimensionality electric energy data, the fault detection result of the electric energy meter to be tested is determined to be a normal electric energy meter; if the fault comparison result indicates that there is a matching fault type in the electric energy meter fault pattern library that matches the reduced-dimensionality electric energy data, the fault detection result of the electric energy meter to be tested is determined according to the matching fault type.

[0074] The fault comparison result can be used to indicate whether the electric energy meter fault mode library has the matching electric energy data and the matching fault type of the electric energy meter to be tested. If the matching electric energy data and the matching fault type of the electric energy meter to be tested exist, it can be used to indicate the matching electric energy data and the matching fault type corresponding to the electric energy meter to be tested. The fault detection result can be used to indicate whether the electric energy meter to be tested has a fault, and if the electric energy meter to be tested has a fault, the fault detection result can indicate the fault type of the electric energy meter to be tested.

[0075] In the method of this embodiment, a pre-built electric energy meter fault mode library can be used to perform fault detection on the electric energy meter to be tested, thereby improving the simplicity and efficiency of fault detection.

[0076] In an exemplary embodiment, step 102 may include:

[0077] Acquire initial power data of the electric energy meter to be tested; perform data preprocessing on the initial power data to obtain target power data.

[0078] In an exemplary embodiment, the step of performing data preprocessing on the initial power data to obtain target power data may include: performing data cleaning on the initial power data to obtain candidate power data of the power meter to be tested; performing missing value processing on the candidate power data to obtain complete power data of the power meter to be tested; and obtaining target power data based on the complete power data.

[0079] The data preprocessing may include data cleaning, missing value processing and data format adjustment, etc., wherein the data cleaning may check whether there are duplicate data points and / or abnormal data points in the initial power data, for example, whether there are exactly the same data points in the initial power data, that is, duplicate data, if there are duplicate data points, then remove one or more of the duplicate data points and retain one data point; detect whether there are abnormal data points in the initial power data, such as extremely large and extremely small values ​​and abnormal timestamps, if there are abnormal data points in the initial power data, then correct the abnormal data points. For example, if the timestamp is not within a reasonable time range or there are missing values, you can choose to delete or repair it through interpolation methods. Missing value processing can perform missing detection on the data value of each data point in the multiple data points of the initial power data to detect whether there are missing values. If the number of missing values ​​is relatively small, you can choose to delete the data points containing missing values; if the number of missing values ​​is large, you can choose to fill the missing values ​​with interpolation methods, such as linear interpolation, mean filling, etc. Data format adjustment can detect the data format of each field in the initial power data to ensure that the data type is correct. For example, convert the timestamp field to date and time type. If the unit of the power data does not match the requirement, you can perform unit conversion to ensure data consistency.

[0080] In the method of this embodiment, data preprocessing can be performed on the initial electric quantity data of the electric energy meter to be tested, so as to ensure the accuracy of the electric quantity data and further improve the accuracy of fault detection.

[0081] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0082] Based on the same inventive concept, the embodiment of the present application also provides an electric energy meter fault detection device based on electric energy response for implementing the electric energy meter fault detection method based on electric energy response involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more electric energy meter fault detection devices based on electric energy response provided below can refer to the limitations of the electric energy meter fault detection method based on electric energy response above, and will not be repeated here.

[0083] In one embodiment, as shown in FIG. 4 , an electric energy meter fault detection device based on electric quantity response is provided, comprising: a data acquisition module 402 , a dimension reduction module 404 , a comparison module 406 and an acquisition module 408 , wherein:

[0084] The data acquisition module 402 is used to obtain the target power data of the electric energy meter to be tested;

[0085] A dimension reduction module 404 is used to perform dimension reduction processing on the target power data to obtain dimension-reduced power data of the electric energy meter to be tested;

[0086] A comparison module 406 is used to compare the dimension-reduced electricity data with a pre-built electric energy meter fault mode library to obtain a fault comparison result of the electric energy meter to be tested;

[0087] The acquisition module 408 is used to acquire the fault detection result of the electric energy meter to be tested according to the fault comparison result.

[0088] In one embodiment, the comparison module 406 is also used to: obtain initial sample power data of the sample power meter; perform data preprocessing on the sample power data to obtain target sample power data corresponding to the sample power data; use a pre-constructed fault detection model to obtain a sample fault detection result of the sample power meter based on the target sample power data; and construct a fault mode library of the power meter according to the sample fault detection result.

[0089] In one embodiment, the comparison module 406 is also used to: input the target sample electricity data into the pre-built fault detection model; determine and output the electricity characteristics of the sample electricity meter according to the target sample electricity data by the feature extraction module in the fault detection model; determine and output the sample fault detection result of the sample electricity meter according to the electricity characteristics output by the feature extraction module by the classification module of the fault detection model.

[0090] In one embodiment, the acquisition module 408 is also used for: if the fault comparison result indicates that there is no matching fault type in the fault mode library of the electric energy meter that matches the reduced-dimensionality electric energy data, then determining the fault detection result of the electric energy meter to be tested as a normal electric energy meter; if the fault comparison result indicates that there is a matching fault type in the fault mode library of the electric energy meter that matches the reduced-dimensionality electric energy data, then determining the fault detection result of the electric energy meter to be tested according to the matching fault type.

[0091] In one embodiment, the data acquisition module 402 is further used to: obtain initial power data of the electric energy meter to be tested; and perform data preprocessing on the initial power data to obtain the target power data.

[0092] In one embodiment, the data acquisition module 402 is also used to: perform data cleaning on the initial power data to obtain candidate power data of the power meter to be tested; perform missing value processing on the candidate power data to obtain complete power data of the power meter to be tested; and obtain the target power data based on the complete power data.

[0093] Each module in the above-mentioned electric energy meter fault detection device based on electric quantity response can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0094] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG5. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data related to electric energy meter fault detection based on electric energy response. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for detecting electric energy meter faults based on electric energy response is implemented.

[0095] Those skilled in the art will understand that the structure shown in FIG. 5 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0096] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0097] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0098] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0099] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0100] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0101] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0102] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting electric energy meter faults based on electric quantity response, characterized in that: The method comprises: Obtain target power data of the electric energy meter to be tested; Performing dimensionality reduction processing on the target electric quantity data to obtain dimensionality reduced electric quantity data of the electric energy meter to be tested; Comparing the dimension-reduced electricity data with a pre-built electric energy meter fault mode library to obtain a fault comparison result of the electric energy meter to be tested; According to the fault comparison result, the fault detection result of the electric energy meter to be tested is obtained.

2. The method according to claim 1, characterized in that Before obtaining the target power data of the electric energy meter to be tested, the method further includes: Obtaining initial sample electricity data of a sample electric energy meter; Performing data preprocessing on the initial sample power data to obtain target sample power data corresponding to the initial sample power data; Using a pre-built fault detection model, based on the target sample power data, a sample fault detection result of the sample electric energy meter is obtained; The electric energy meter fault mode library is constructed according to the sample fault detection results.

3. The method according to claim 2, characterized in that The method of using the pre-built fault detection model to obtain the sample fault detection result of the sample electric energy meter based on the target sample electric quantity data includes: Inputting the target sample power data into the pre-built fault detection model; The feature extraction module in the fault detection model determines and outputs the power feature of the sample electric energy meter according to the target sample electric energy data; The classification module of the fault detection model determines and outputs the sample fault detection result of the sample electric energy meter according to the electric quantity feature output by the feature extraction module.

4. The method according to claim 1, characterized in that: The obtaining, according to the fault comparison result, a fault detection result of the electric energy meter to be tested comprises: If the fault comparison result indicates that there is no matching fault type matching the reduced-dimensionality electricity data in the electric energy meter fault mode library, then determining that the fault detection result of the electric energy meter to be tested is a normal electric energy meter; If the fault comparison result indicates that there is a matching fault type that matches the reduced-dimensionality electricity data in the electric energy meter fault mode library, the fault detection result of the electric energy meter to be tested is determined according to the matching fault type.

5. The method according to any one of claims 1 to 4, characterized in that The step of obtaining target power data of the electric energy meter to be tested includes: Acquiring initial power data of the electric energy meter to be tested; The initial power data is preprocessed to obtain the target power data.

6. The method according to claim 5, characterized in that The performing data preprocessing on the initial power data to obtain the target power data includes: Performing data cleaning on the initial electric quantity data to obtain candidate electric quantity data of the electric energy meter to be tested; Processing missing values ​​on the candidate electric quantity data to obtain complete electric quantity data of the electric energy meter to be tested; The target power data is obtained according to the complete power data.

7. An electric energy meter fault detection device based on electric quantity response, characterized in that: The device comprises: A data acquisition module is used to obtain target power data of the electric energy meter to be tested; A dimension reduction module, used for performing dimension reduction processing on the target electric quantity data to obtain the dimension reduced electric quantity data of the electric energy meter to be tested; A comparison module, used for comparing the dimension-reduced electricity data with a pre-built electric energy meter fault mode library to obtain a fault comparison result of the electric energy meter to be tested; The acquisition module is used to acquire the fault detection result of the electric energy meter to be tested according to the fault comparison result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images