CN113449258A - Quality evaluation method and device for intelligent electric meter, terminal equipment and storage medium - Google Patents
Quality evaluation method and device for intelligent electric meter, terminal equipment and storage medium Download PDFInfo
- Publication number
- CN113449258A CN113449258A CN202110595132.3A CN202110595132A CN113449258A CN 113449258 A CN113449258 A CN 113449258A CN 202110595132 A CN202110595132 A CN 202110595132A CN 113449258 A CN113449258 A CN 113449258A
- Authority
- CN
- China
- Prior art keywords
- intelligent electric
- electric meter
- load
- total
- quality evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
Abstract
The invention is suitable for the technical field of ammeter detection, and provides a quality evaluation method, a device, terminal equipment and a storage medium of an intelligent ammeter, wherein the method comprises the following steps: the total line load of the intelligent electric meter under different environmental temperatures is measured; sequentially carrying out component analysis and positive definite matrix factorization to obtain classification data corresponding to the total load of the line; and obtaining an evaluation index of the intelligent electric meter according to the classification data corresponding to the total load of the line, the display data of the intelligent electric meter and the established quality evaluation model, and evaluating the quality grade of the intelligent electric meter according to the evaluation index, wherein the established quality evaluation model is obtained by training a convolutional neural network model. According to the invention, the established quality evaluation model can be used for rapidly finishing the quality evaluation of the intelligent electric meter, so that the evaluation time is greatly saved when the system scale is large, and the evaluation precision is improved.
Description
Technical Field
The invention belongs to the technical field of ammeter detection, and particularly relates to a quality evaluation method and device for an intelligent ammeter, terminal equipment and a storage medium.
Background
With the development of smart grids, electric energy meters are developing towards intellectualization and multiple functions. The intelligent electric meter is one of basic devices for data acquisition of an intelligent power grid (particularly an intelligent power distribution network), undertakes the tasks of original electric energy data acquisition, metering and intelligent transmission, and is the basis for realizing information integration, analysis optimization and information display. Therefore, the quality evaluation of the smart meter becomes a necessary choice.
Currently, an analytic hierarchy process and a parametric analysis process are generally adopted to evaluate the quality of the smart electric meter. The analytic hierarchy process mainly combines qualitative analysis and quantitative analysis, can effectively solve the difficulty of expert scoring, and reduces the preference of expert individual scoring; the parameter analysis method mainly combines hardware and software of the intelligent electric meter, comprehensively considers internal and external factors, and comprehensively analyzes and evaluates the intelligent electric meter.
However, the quality evaluation method of the smart meter described above may cause a problem of low evaluation accuracy.
Disclosure of Invention
In view of this, embodiments of the present invention provide a quality evaluation method and apparatus for a smart meter, a terminal device, and a storage medium, so as to solve the problem of low evaluation accuracy in the prior art.
The first aspect of the embodiment of the invention provides a quality evaluation method for an intelligent electric meter, which comprises the following steps:
acquiring the total line load of the intelligent electric meter at different environmental temperatures;
sequentially carrying out component analysis and positive definite matrix factorization on the total line load of the intelligent electric meter under different environmental temperatures to obtain classification data corresponding to the total line load;
and obtaining an evaluation index of the intelligent electric meter according to the classification data corresponding to the total load of the line, the display data of the intelligent electric meter and the established quality evaluation model, and evaluating the quality grade of the intelligent electric meter according to the evaluation index, wherein the established quality evaluation model is obtained by training a convolutional neural network model.
A second aspect of the embodiments of the present invention provides a quality evaluation apparatus for a smart meter, the apparatus including:
the data acquisition module is used for acquiring the total line load of the intelligent electric meter under different environmental temperatures;
the classification data determining module is used for sequentially carrying out component analysis and positive definite matrix factorization on the total line load of the intelligent electric meter under different environmental temperatures to obtain classification data corresponding to the total line load;
and the quality evaluation module is used for obtaining an evaluation index of the intelligent electric meter according to the classification data corresponding to the total load of the line, the display data of the intelligent electric meter and the established quality evaluation model so as to evaluate the quality grade of the intelligent electric meter according to the evaluation index, wherein the established quality evaluation model is obtained by training a convolutional neural network model.
A third aspect of the embodiments of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor, when executing the computer program, implements the steps of the quality assessment method for the smart meter according to any one of the above items.
A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the quality evaluation method for the smart meter according to any one of the above.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
according to the embodiment of the invention, firstly, the total load of the line of the intelligent electric meter under different environmental temperatures is subjected to component analysis and positive definite matrix factorization in sequence to obtain classification data corresponding to the total load of the line; and obtaining an evaluation index of the intelligent electric meter according to the classification data corresponding to the total load of the line, the display data of the intelligent electric meter and the established quality evaluation model, and evaluating the quality grade of the intelligent electric meter according to the evaluation index, wherein the established quality evaluation model is obtained by training a convolutional neural network model. According to the invention, the established quality evaluation model can be used for rapidly finishing the quality evaluation of the intelligent electric meter, so that the evaluation time is greatly saved when the system scale is large, and the evaluation precision is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic flow chart illustrating an implementation process of a quality evaluation method for a smart meter according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a quality evaluation device of an intelligent electric meter according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
Fig. 1 is a schematic flow chart illustrating an implementation process of a quality evaluation method for a smart meter according to an embodiment of the present invention. As shown in fig. 1, a quality evaluation method of a smart meter of this embodiment includes:
step S101: acquiring the total line load of the intelligent electric meter at different environmental temperatures;
step S102: sequentially carrying out component analysis and positive definite matrix factorization on the total line load of the intelligent electric meter under different environmental temperatures to obtain classification data corresponding to the total line load;
step S103: and obtaining an evaluation index of the intelligent electric meter according to the classification data corresponding to the total load of the line, the display data of the intelligent electric meter and the established quality evaluation model, and evaluating the quality grade of the intelligent electric meter according to the evaluation index, wherein the established quality evaluation model is obtained by training a convolutional neural network model.
In one embodiment, the display data of the smart meter and the total load of the line reflect the electrical performance of the smart meter, and are the most important basis for evaluating the quality of the smart meter. Therefore, the display data and the total line load of the intelligent electric meter are analyzed to determine the quality grade of the intelligent electric meter. Optionally, select a smart electric meter, with this smart electric meter on according to temperature sensor, set up under different ambient temperature through this smart electric meter who carries temperature sensor to acquire smart electric meter's circuit total load under different ambient temperature. The method comprises the steps of obtaining the total load of a line of the intelligent electric meter, firstly calculating the load current flowing through each line (a power supply inlet wire, a high-voltage and low-voltage distribution line and the like), and then calculating the total load of the line according to the load current.
Further, if the measured quality grade of the intelligent electric meter is within the set grade range, the quality grade data of the intelligent electric meter is uploaded to a remote server to be stored; if the score of the intelligent electric meter measured actually exceeds the set grade range, the score of the intelligent electric meter is uploaded to a remote server, and the remote server selects to carry out fault maintenance or replacement operation on the intelligent electric meter according to the score of the intelligent electric meter.
Specifically, the consumption of the line inevitably causes the difference of the total load of the line due to the consumption of the smart meter under different environmental temperatures, for example, the line consumption is relatively small and the total load of the line is not high under the condition that the smart meter is at 5-10 ℃; under the condition that the temperature of the intelligent electric meter is 35-40 ℃, the line consumption is large, and the total load of the line is relatively high. The method comprises the steps of summarizing the total line load of the intelligent electric meter under different environmental temperatures, and then carrying out component analysis and positive definite matrix factorization on the summarized total line load, so that the total line load can be effectively classified to determine classified data of the total line load.
Further, a Convolutional Neural Network (CNN) is a kind of feed-forward Neural network containing convolution calculation and having a deep structure, and is one of the representative algorithms of deep learning. Convolutional neural networks have a characteristic learning ability, and can perform translation invariant classification on input information according to a hierarchical structure thereof, and are also called "translation invariant artificial neural networks". The convolutional neural network is constructed by imitating a visual perception mechanism of a living being, and can be used for supervised learning and unsupervised learning, and the parameter sharing of convolution kernels in hidden layers and the sparsity of interlayer connection enable the convolutional neural network to learn lattice characteristics such as pixels and audio with small calculation amount, have stable effect and have no additional characteristic engineering requirement on data. According to the quality evaluation method and device, the convolutional neural network model is used as the basic model to determine the quality evaluation model, the model calculation time can be saved, the calculation precision is improved, and the reliability of quality evaluation of the intelligent electric meter is ensured.
According to the embodiment of the invention, firstly, the total load of the line of the intelligent electric meter under different environmental temperatures is subjected to component analysis and positive definite matrix factorization in sequence to obtain classification data corresponding to the total load of the line; and obtaining an evaluation index of the intelligent electric meter according to the classification data corresponding to the total load of the line, the display data of the intelligent electric meter and the established quality evaluation model, and evaluating the quality grade of the intelligent electric meter according to the evaluation index, wherein the established quality evaluation model is obtained by training a convolutional neural network model. According to the invention, the established quality evaluation model can be used for rapidly finishing the quality evaluation of the intelligent electric meter, so that the evaluation time is greatly saved when the system scale is large, and the evaluation precision is improved.
In one embodiment, step S102 includes:
step S201: analyzing the components of the total line load of the intelligent electric meter at different environmental temperatures to obtain the grouped total line load;
step S202: cleaning and converting the grouped total load of the line to obtain a standardized file corresponding to the total load of the line;
step S203: and carrying out positive definite matrix factorization on the standardized file to obtain classification data corresponding to the total load of the line.
In an embodiment, the total load of the line is grouped based on an environmental temperature interval, for example, 5 ℃ is used as an interval difference, the preset environmental temperature difference may include a first environmental interval of 5 ℃ to 10 ℃, a second environmental interval of 10 ℃ to 15 ℃, a third environmental interval of 15 ℃ to 20 ℃, and so on, and the interval difference and the number of the environmental temperature intervals are set according to specific situations, which is described herein again.
Specifically, 5 ℃ is taken as an interval difference, the first environment interval comprises the total load of a first group of lines at 5-10 ℃, the second environment interval comprises the total load of a second group of lines at 10-15 ℃, the third environment interval comprises the total load of a third group of lines at 15-20 ℃, and the like. After obtaining the total loads of the plurality of groups of lines, the total loads of each group of lines need to be cleaned and converted so as to determine the standardized files corresponding to the total loads of the lines. The total load of the line is standardized, so that invalid data can be avoided, and the efficiency of later-period calculation is improved.
Furthermore, positive definite matrix factorization is a matrix decomposition method under the condition that all elements in a matrix are not negative numbers, and non-negative constraints are applied to factor load and factor scores in the solving process, so that negative values in matrix decomposition results are avoided, and the factor load and the factor scores have interpretability and definite physical significance. The positive definite matrix factorization uses a least square method to carry out iterative operation, can simultaneously determine the spectrum and the contribution of a pollution source, can be directly compared with an original data matrix without conversion, and elements in the decomposed matrix are not negative, so that the analysis result is clear and easy to explain, and the data quality can be optimized by using uncertainty.
In one embodiment, step S203 includes:
step S301: acquiring a positive definite matrix factorization model;
step S302: inputting the standardized file into a positive definite matrix factorization model to obtain a factor analysis result corresponding to the standardized file;
step S303: and classifying the factor analysis result to obtain classification data corresponding to the total load of the line.
In one embodiment, the positive definite matrix factorization model is a method based on factor analysis, and has the advantages of no need of measuring a source fingerprint spectrum, nonnegative elements in a decomposition matrix, capability of optimizing by using a data standard deviation and the like. The utility model discloses a standardized file is carried out positive definite factorization analysis to positive definite matrix factorization model, obtains the classification data that circuit gross load corresponds, can improve the speed that the quality assessment model carries out the processing to the classification data that circuit gross load corresponds to ensure the efficiency to smart electric meter quality assessment.
Further, the standardized file is subjected to factor decomposition, and the standardized file with different factors can be obtained according to different factors, namely a factor analysis result. Since different factors may belong to the same type of factor, the classification data corresponding to the total load of the line can be determined only by further classifying the factor analysis result.
Specifically, the normalized file is subjected to factor decomposition to obtain a factor analysis result A1, a factor analysis result A2, a factor analysis result B and a factor analysis result C. Since the factor analysis result a1 and the factor analysis result a2 both belong to the same category a, the factor analysis results can be classified to obtain a-type data corresponding to the total line load, and a-type data corresponding to the total line load.
In one embodiment, step S103: the method comprises the following steps:
step S401: acquiring an established quality evaluation model;
step S402: inputting classification data corresponding to the total load of the line and display data of the intelligent electric meter into the established quality evaluation model to obtain an evaluation index of the intelligent electric meter;
step S403: weighting the evaluation indexes of the intelligent electric meter to obtain weighted values corresponding to the evaluation indexes;
step S404: and matching the weighted value with a preset grade interval to determine the quality grade of the intelligent electric meter.
In an embodiment, the number of the evaluation indexes of the smart meter is multiple, each evaluation index has a different weight coefficient, and weighting processing is performed on the evaluation indexes of the smart meter to obtain weighted values corresponding to the multiple evaluation indexes.
Specifically, the preset grade interval is automatically set by the system, and may include a plurality of preset grade intervals. Such as the primary interval (70, 80), the secondary interval (80, 90) and the tertiary interval (90, 100), the weighted value corresponding to the level interval is higher as the level increases. If the corresponding weighted value of the plurality of evaluation indexes of the intelligent electric meter is 88, namely 88 belongs to the second-level interval (80, 90), the quality grade of the intelligent electric meter belongs to the second level.
In one embodiment, step S402 includes:
step S501: inputting classification data corresponding to the total load of the line and display data of the intelligent electric meter into the established quality evaluation model;
step S502: and under the condition that the iteration times of the established quality evaluation model reach the preset iteration times, outputting the service life, the operation efficiency and the display data precision of the intelligent electric meter.
In one embodiment, the evaluation metrics include service life, operating efficiency, and display data accuracy. Taking an intelligent electric meter as an example, after classification data corresponding to the total line load of the intelligent electric meter and display data of the intelligent electric meter are input into the established quality assessment model, iteration is performed, if the iteration times reach preset iteration times, the established quality assessment model is converged, and output assessment indexes such as service life, operation efficiency and display data precision meet precision requirements. The preset iteration times belong to the operation parameters of the established quality evaluation model, are set after the quality evaluation model is established, and the specific iteration times need to be adjusted according to specific conditions, and are not specifically limited here.
In an embodiment, before step S401, the method further includes:
step S601: establishing a quality evaluation model;
step S601: the method comprises the following steps:
step S6011: acquiring a training sample set, wherein the training sample set comprises a plurality of training samples;
step S6012: and training the convolutional neural network model by using each training sample in the plurality of training samples in sequence to obtain a quality evaluation model.
In an embodiment, before step S6011, the method further includes:
step S701: acquiring classification data corresponding to the total load of the line and display data of the intelligent electric meter;
step S702: the classification data corresponding to the total load of the line and the display data of the intelligent electric meter are matched one by one, and a plurality of training samples are determined;
step S703: and combining the plurality of training samples to obtain a training sample set.
In an embodiment, in the case of training a convolutional neural network model, multiple training samples are required. The classification data corresponding to the total load of the parameter circuit forming the training sample and the display data of the intelligent electric meter need to be matched. For example, the classification data corresponding to the total line load includes a type a data corresponding to the total line load, a type B data corresponding to the total line load, and a type C data corresponding to the total line load; the display data of the intelligent electric meter comprise first display data D, second display data E and third display data F. The data can be matched to obtain a training sample.
Specifically, the matching of the a-type data corresponding to the total load of the line, the B-type data corresponding to the total load of the line, the C-type data corresponding to the total load of the line, the first display data D, the second display data E, and the third display data F may be randomly set, and for example, may be divided into three training samples including a first training sample (the a-type data corresponding to the total load of the line, the first display data D), a second training sample (the B-type data corresponding to the total load of the line, the second display data E), and a third training sample (the C-type data corresponding to the total load of the line, the third display data F), or may be divided into a first training sample (the a-type data corresponding to the total load of the line, the first display data E), a second training sample (the B-type data corresponding to the total load of the line, the second display data D), and a third training sample (the C-type data corresponding to the total load of the line, the third display data F), the grouping manner is not particularly limited, and may be automatically adjusted as needed.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
In one embodiment, as shown in fig. 2, there is provided a quality evaluation apparatus of a smart meter, including: a data acquisition module 201, a classification data determination module 202, and a quality assessment module 203, wherein:
the data acquisition module 201 is used for acquiring the total line load of the intelligent electric meter at different environmental temperatures;
the classification data determining module 202 is used for sequentially performing component analysis and positive definite matrix factorization on the total line load of the intelligent electric meter under different environmental temperatures to obtain classification data corresponding to the total line load;
and the quality evaluation module 203 is used for obtaining an evaluation index of the intelligent electric meter according to the classification data corresponding to the total load of the line, the display data of the intelligent electric meter and the established quality evaluation model so as to evaluate the quality grade of the intelligent electric meter according to the evaluation index, wherein the established quality evaluation model is obtained by training a convolutional neural network model.
In one embodiment, the classification data determining module 202 includes:
the component analysis submodule is used for carrying out component analysis on the total line load of the intelligent electric meter under different environmental temperatures to obtain the grouped total line load;
the standardization submodule is used for cleaning and converting the grouped total load of the line to obtain a standardization file corresponding to the total load of the line;
and the factor decomposition submodule is used for carrying out positive definite matrix factor decomposition on the standardized file to obtain classification data corresponding to the total load of the line.
In one embodiment, a factorization submodule, comprising:
the decomposition model obtaining unit is used for obtaining a positive definite matrix factorization model;
the factor decomposition unit is used for inputting the standardized file into the positive definite matrix factor decomposition model to obtain a factor analysis result corresponding to the standardized file;
and the data classification unit is used for classifying the factor analysis result to obtain classification data corresponding to the total load of the line.
In one embodiment, the quality assessment module 203 comprises:
the evaluation model obtaining submodule is used for obtaining the established quality evaluation model;
the evaluation index determining submodule is used for inputting classification data corresponding to the total load of the line and display data of the intelligent electric meter into the established quality evaluation model to obtain an evaluation index of the intelligent electric meter;
the weighting processing submodule is used for weighting the evaluation indexes of the intelligent electric meter to obtain weighted values corresponding to the evaluation indexes;
and the data matching submodule is used for matching the weighted value with a preset grade interval and determining the quality grade of the intelligent electric meter.
In one embodiment, the evaluation index includes service life, operation efficiency and display data accuracy; an evaluation index determination submodule including:
the data input unit is used for inputting classification data corresponding to the total load of the line and display data of the intelligent electric meter into the established quality evaluation model;
and the iteration unit is used for outputting the service life, the operation efficiency and the display data precision of the intelligent ammeter under the condition that the iteration times of the established quality evaluation model reach the preset iteration times.
In an embodiment, before evaluating the model obtaining sub-module, the method further includes:
the evaluation model establishing submodule is used for establishing a quality evaluation model;
the evaluation model establishing submodule comprises:
the training sample acquisition unit is used for acquiring a training sample set, wherein the training sample set comprises a plurality of training samples;
and the network model training unit is used for training the convolutional neural network model by utilizing each training sample in the plurality of training samples in sequence to obtain a quality evaluation model.
In an embodiment, before training the sample acquiring unit, the method further includes:
the input data acquisition unit is used for acquiring classification data corresponding to the total load of the line and display data of the intelligent electric meter;
the training sample determining unit is used for matching the classification data corresponding to the total load of the line with the display data of the intelligent electric meter one by one to determine a plurality of training samples;
and the training sample set determining unit is used for combining the plurality of training samples to obtain a training sample set.
Fig. 3 is a schematic diagram of a terminal device according to an embodiment of the present invention. As shown in fig. 3, the terminal device 3 of this embodiment includes: a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and operable on the processor 301. The processor 301, when executing the computer program 303, implements the steps in the above-described embodiments of the method for evaluating the quality of each smart meter, such as the steps 101 to 103 shown in fig. 1. Alternatively, the processor 301, when executing the computer program 303, implements the functions of the modules/units in the above-described device embodiments, such as the functions of the modules 201 to 203 shown in fig. 2.
Illustratively, the computer program 303 may be partitioned into one or more modules/units, which are stored in the memory 302 and executed by the processor 301 to implement the present invention. One or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 303 in the terminal device 3. For example, the computer program 303 may be divided into a data acquisition module, a classification data determination module, and a quality assessment module, each of which functions specifically as follows:
the data acquisition module is used for acquiring the total line load of the intelligent electric meter under different environmental temperatures;
the classification data determining module is used for sequentially carrying out component analysis and positive definite matrix factorization on the total line load of the intelligent electric meter under different environmental temperatures to obtain classification data corresponding to the total line load;
and the quality evaluation module is used for obtaining an evaluation index of the intelligent electric meter according to the classification data corresponding to the total load of the line, the display data of the intelligent electric meter and the established quality evaluation model so as to evaluate the quality grade of the intelligent electric meter according to the evaluation index, wherein the established quality evaluation model is obtained by training a convolutional neural network model.
The terminal device 3 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The 3 terminal device may include, but is not limited to, a processor 301, a memory 302. Those skilled in the art will appreciate that fig. 3 is merely an example of a terminal device and is not limiting of terminal devices and may include more or fewer components than shown, or some components may be combined, or different components, e.g., a terminal device may also include input output devices, network access devices, buses, etc.
The Processor 301 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 302 may be an internal storage unit of the terminal device 3, such as a hard disk or a memory of the terminal device 3. The memory 302 may also be an external storage device of the terminal device 3, such as a plug-in hard disk provided on the terminal device 3, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the memory 302 may also include both an internal storage unit of the terminal device 3 and an external storage device. The memory 302 is used for storing computer programs and other programs and data required by the terminal device. The memory 302 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, a module or a unit may be divided into only one logical function, and may be implemented in other ways, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method according to the embodiments of the present invention may also be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of the embodiments of the method. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, in accordance with legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunications signals.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. A quality evaluation method of a smart meter is characterized by comprising the following steps:
acquiring the total line load of the intelligent electric meter at different environmental temperatures;
sequentially carrying out component analysis and positive definite matrix factorization on the total line load of the intelligent electric meter under different environmental temperatures to obtain classification data corresponding to the total line load;
and obtaining an evaluation index of the intelligent electric meter according to the classification data corresponding to the total load of the line, the display data of the intelligent electric meter and the established quality evaluation model, and evaluating the quality grade of the intelligent electric meter according to the evaluation index, wherein the established quality evaluation model is obtained by training a convolutional neural network model.
2. The method for evaluating the quality of the smart meter according to claim 1, wherein the step of sequentially performing component analysis and positive definite matrix factorization on the total line load of the smart meter at different environmental temperatures to obtain classification data corresponding to the total line load comprises the steps of:
analyzing the components of the total line load of the intelligent electric meter at different environmental temperatures to obtain the grouped total line load;
cleaning and converting the grouped total line load to obtain a standardized file corresponding to the total line load;
and carrying out positive definite matrix factorization on the standardized file to obtain classification data corresponding to the total load of the line.
3. The method for evaluating the quality of an intelligent electric meter according to claim 2, wherein the step of performing positive definite matrix factorization on the standardized file to obtain classification data corresponding to the total line load comprises the following steps:
acquiring a positive definite matrix factorization model;
inputting the standardized file into the positive definite matrix factorization model to obtain a factor analysis result corresponding to the standardized file;
and classifying the factor analysis result to obtain classification data corresponding to the total load of the line.
4. The method for evaluating the quality of the smart meter according to any one of claims 1 to 3, wherein the obtaining of the evaluation index of the smart meter according to the classification data corresponding to the total load of the line, the display data of the smart meter and the established quality evaluation model to evaluate the quality grade of the smart meter according to the evaluation index comprises:
obtaining the established quality evaluation model;
inputting classification data corresponding to the total load of the line and display data of the intelligent electric meter into the established quality evaluation model to obtain an evaluation index of the intelligent electric meter;
weighting the evaluation indexes of the intelligent electric meter to obtain weighted values corresponding to the evaluation indexes;
and matching the weighted value with a preset grade interval to determine the quality grade of the intelligent electric meter.
5. The method of claim 4, wherein the evaluation indexes include a service life, an operation efficiency, and a display data accuracy;
the step of inputting the classification data corresponding to the total load of the line and the display data of the intelligent electric meter into the established quality evaluation model to obtain the evaluation index of the intelligent electric meter comprises the following steps:
inputting classification data corresponding to the total load of the line and display data of the intelligent electric meter into the established quality evaluation model;
and under the condition that the iteration times of the established quality evaluation model reach preset iteration times, outputting the service life, the operation efficiency and the display data precision of the intelligent electric meter.
6. The method for quality assessment of smart meters of claim 4, wherein said obtaining an established quality assessment model further comprises:
establishing the quality evaluation model;
the establishing the quality evaluation model comprises:
acquiring a training sample set, wherein the training sample set comprises a plurality of training samples;
and training the convolutional neural network model by utilizing each training sample in the plurality of training samples in sequence to obtain the quality evaluation model.
7. The method for quality assessment of smart meters of claim 6, wherein prior to said obtaining a set of training samples, further comprising:
acquiring classification data corresponding to the total line load and display data of the intelligent electric meter;
matching the classification data corresponding to the total line load with the display data of the intelligent electric meter one by one to determine a plurality of training samples;
and combining the plurality of training samples to obtain the training sample set.
8. A quality assessment device of a smart meter, characterized in that said device comprises:
the data acquisition module is used for acquiring the total line load of the intelligent electric meter under different environmental temperatures;
the classification data determining module is used for sequentially carrying out component analysis and positive definite matrix factorization on the total line load of the intelligent electric meter under different environmental temperatures to obtain classification data corresponding to the total line load;
and the quality evaluation module is used for obtaining an evaluation index of the intelligent electric meter according to the classification data corresponding to the total load of the line, the display data of the intelligent electric meter and the established quality evaluation model so as to evaluate the quality grade of the intelligent electric meter according to the evaluation index, wherein the established quality evaluation model is obtained by training a convolutional neural network model.
9. Terminal device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, characterized in that said processor, when executing said computer program, carries out the steps of the method for quality assessment of a smart meter according to any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for quality assessment of a smart meter according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110595132.3A CN113449258B (en) | 2021-05-28 | 2021-05-28 | Quality evaluation method and device for intelligent electric meter, terminal equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110595132.3A CN113449258B (en) | 2021-05-28 | 2021-05-28 | Quality evaluation method and device for intelligent electric meter, terminal equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113449258A true CN113449258A (en) | 2021-09-28 |
| CN113449258B CN113449258B (en) | 2022-12-27 |
Family
ID=77810490
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110595132.3A Active CN113449258B (en) | 2021-05-28 | 2021-05-28 | Quality evaluation method and device for intelligent electric meter, terminal equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113449258B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105158722A (en) * | 2015-04-23 | 2015-12-16 | 国网上海市电力公司 | Evaluation method for performance index of electric energy meter |
| US20160020609A1 (en) * | 2013-03-07 | 2016-01-21 | Siemens Corporation | Demand shaping in an electrical power grid |
| CN106338708A (en) * | 2016-08-30 | 2017-01-18 | 中国电力科学研究院 | Electric energy metering error analysis method by combining deep learning and recursive neural network |
| CN109307854A (en) * | 2018-10-29 | 2019-02-05 | 中国电力科学研究院有限公司 | A kind of electric energy metering device comprehensive estimation method and system |
| CN109523190A (en) * | 2018-11-29 | 2019-03-26 | 国网河北省电力有限公司电力科学研究院 | A kind of management method of electric energy meter, managing device and terminal |
| CN109754146A (en) * | 2018-08-23 | 2019-05-14 | 国网天津市电力公司电力科学研究院 | It is a kind of based on the intelligent electric energy meter health degree comprehensive estimation method for being relation analysis |
| CN112564107A (en) * | 2020-12-15 | 2021-03-26 | 深圳供电局有限公司 | Transient stability assessment method for power system |
-
2021
- 2021-05-28 CN CN202110595132.3A patent/CN113449258B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160020609A1 (en) * | 2013-03-07 | 2016-01-21 | Siemens Corporation | Demand shaping in an electrical power grid |
| CN105158722A (en) * | 2015-04-23 | 2015-12-16 | 国网上海市电力公司 | Evaluation method for performance index of electric energy meter |
| CN106338708A (en) * | 2016-08-30 | 2017-01-18 | 中国电力科学研究院 | Electric energy metering error analysis method by combining deep learning and recursive neural network |
| CN109754146A (en) * | 2018-08-23 | 2019-05-14 | 国网天津市电力公司电力科学研究院 | It is a kind of based on the intelligent electric energy meter health degree comprehensive estimation method for being relation analysis |
| CN109307854A (en) * | 2018-10-29 | 2019-02-05 | 中国电力科学研究院有限公司 | A kind of electric energy metering device comprehensive estimation method and system |
| CN109523190A (en) * | 2018-11-29 | 2019-03-26 | 国网河北省电力有限公司电力科学研究院 | A kind of management method of electric energy meter, managing device and terminal |
| CN112564107A (en) * | 2020-12-15 | 2021-03-26 | 深圳供电局有限公司 | Transient stability assessment method for power system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113449258B (en) | 2022-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107169628B (en) | Power distribution network reliability assessment method based on big data mutual information attribute reduction | |
| CN111860982A (en) | Wind power plant short-term wind power prediction method based on VMD-FCM-GRU | |
| He et al. | A combined model for short-term wind power forecasting based on the analysis of numerical weather prediction data | |
| CN109783879B (en) | Radar radiation source signal identification efficiency evaluation method and system | |
| CN113205207A (en) | XGboost algorithm-based short-term power consumption load fluctuation prediction method and system | |
| CN111435463A (en) | Data processing method and related equipment and system | |
| CN109633448B (en) | Method and device for identifying battery health state and terminal equipment | |
| CN116150897A (en) | Machine tool spindle performance evaluation method and system based on digital twin | |
| Pei et al. | Short-term regional wind power forecasting based on spatial–temporal correlation and dynamic clustering model | |
| CN111008726A (en) | Class image conversion method in power load prediction | |
| CN111209316A (en) | Information literacy data mining method and device, electronic equipment and storage medium | |
| CN111160626A (en) | Power load time sequence control method based on decomposition and fusion | |
| CN114066073A (en) | Power grid load prediction method | |
| CN113469266B (en) | Electricity stealing behavior detection method based on improved deep convolutional neural network | |
| CN101206727B (en) | Data processing apparatus, data processing method | |
| CN115099511A (en) | Photovoltaic power probability estimation method and system based on optimized copula | |
| Owerko et al. | Unsupervised optimal power flow using graph neural networks | |
| CN114154716A (en) | Enterprise energy consumption prediction method and device based on graph neural network | |
| CN112257958A (en) | Power saturation load prediction method and device | |
| CN113449258B (en) | Quality evaluation method and device for intelligent electric meter, terminal equipment and storage medium | |
| Gao et al. | Evaluation of electric vehicle integrated charging safety state based on fuzzy neural network | |
| CN115545164A (en) | Photovoltaic power generation power prediction method, system, equipment and medium | |
| CN114202174A (en) | Electricity price risk grade early warning method and device and storage medium | |
| CN115409317A (en) | Transformer area line loss detection method and device based on feature selection and machine learning | |
| CN114784795A (en) | Wind power prediction method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |