CN112748390A - Method and device for evaluating state of electric energy meter - Google Patents
Method and device for evaluating state of electric energy meter Download PDFInfo
- Publication number
- CN112748390A CN112748390A CN202011539625.7A CN202011539625A CN112748390A CN 112748390 A CN112748390 A CN 112748390A CN 202011539625 A CN202011539625 A CN 202011539625A CN 112748390 A CN112748390 A CN 112748390A
- Authority
- CN
- China
- Prior art keywords
- electric energy
- energy meter
- working condition
- state
- matrix
- 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
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/04—Testing or calibrating of apparatus covered by the other groups of this subclass of instruments for measuring time integral of power or current
-
- 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
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application discloses a method and a device for evaluating the state of an electric energy meter, wherein the method comprises the following steps: the historical working condition parameters of the electric energy meter are regarded as independent variables, and the state of the electric energy meter is regarded as dependent variables, so that the problem of multivariate regression statistical analysis is abstracted, but because the historical working condition parameters comprise multiple types of multidimensional information parameters, certain correlation relationship may exist among the multidimensional information, namely certain serious multiple correlation may exist among the independent variables. In order to solve the problem, a partial least square method is introduced, firstly a matrix is established according to historical working condition parameters, then the matrix is divided, evaluation modeling is established through the partial least square method, the state of the electric energy meter is evaluated according to an evaluation model, the characteristic that the partial least square method can be used for analyzing the pattern recognition problem under the condition of small samples and multiple variables is utilized, the problems of system noise and multiple linearity can be well solved, and the technical problem that the existing online monitoring technology has poor evaluation precision on the state of the electric energy meter is solved.
Description
Technical Field
The application relates to the technical field of power electronics, in particular to a method and a device for evaluating the state of an electric energy meter.
Background
Electric energy metering is the legal basis for electric energy trade and electric charge settlement in the power industry, and electric energy meters for electric energy trade settlement are generally installed in substations, power plants and subscriber stations. The reliability and the accuracy of the electric energy measurement are not only responsible for enhancing the satisfaction degree of customers, but also play an important role in increasing the management benefits of enterprises. The operation management and maintenance of the electric energy meter are the most important of the management work of the daily electric energy metering technology.
Considering that the operating environment of the electric energy meter may have high temperature, high humidity and high salinity, and the service life of the electric energy meter itself, the state of the electric energy meter needs to be evaluated, so as to provide reference for subsequent maintenance and replacement of the electric energy meter. At present, the state evaluation method of the electric energy meter mainly adopts an online monitoring technical scheme, and quantitative and qualitative analysis is carried out on data such as electric quantity, current, voltage harmonic frequency, clock and the like before and after the electric energy meter breaks down remotely through data collected by an electricity consumption information collection system. However, because different electric energy meters have different actual operation conditions, the existing working condition parameters are difficult to evaluate the operation states of the electric energy meters under various working conditions, so that more working condition parameters need to be introduced for comprehensive evaluation, but for a low-voltage distribution network, when more working condition parameters are introduced, the problems of system noise, multiple linearity and the like are easily caused due to the fact that the dimension of the working condition parameters is increased rapidly, and the evaluation accuracy of the states of the electric energy meters is seriously influenced.
Disclosure of Invention
The embodiment of the application provides a method and a device for evaluating the state of an electric energy meter, which are used for solving the technical problem of poor evaluation precision of the state of the electric energy meter by the existing online monitoring technology.
In view of the above, a first aspect of the present application provides a method for evaluating a state of an electric energy meter, the method including:
s1, obtaining historical working condition parameters of a plurality of electric energy meters in a distribution area, respectively converting the historical working condition parameters of each electric energy meter into working condition parameter vectors to obtain an electric energy meter working condition parameter matrix X of the distribution area, and classifying the electric energy meters after comparing the historical working condition parameters of each electric energy meter with a preset threshold value to obtain an electric energy meter category matrix Y of the distribution area;
s2, obtaining an electric energy meter combined sample matrix of the distribution room according to the working condition parameter matrix X and the category matrix Y, and dividing the combined sample matrix into equal-width intervals to obtain k sections of data intervals, wherein k is a positive integer;
s3, sequentially setting each section of data interval in the k sections of data intervals as a test set to obtain k test sets, setting a complementary set of each section of data interval as a training set, and respectively modeling according to each training set based on a partial least square method to obtain k sub-models;
s4, selecting the submodel with the minimum mean square error from the k submodels, and setting a data interval corresponding to the submodel with the minimum mean square error as a first optimal combination;
s5, performing regression analysis on the submodel with the minimum mean square error according to the first optimal combination based on a partial least square method to obtain an electric energy meter state evaluation model of the station area;
and S6, inputting the k test sets into the electric energy meter state evaluation model to obtain the electric energy meter state of the transformer area.
Optionally, after step S4, the method further includes:
s01, selecting the optimal principal component number of the first optimal combination based on a leave-one-out cross verification method to obtain a second optimal combination;
and S02, performing regression analysis on the submodel with the minimum mean square error according to the second optimal combination based on a partial least square method to obtain an electric energy meter state evaluation model of the station area, and inputting the k test sets into the electric energy meter state evaluation model to obtain the electric energy meter state of the station area.
Optionally, step S01 specifically includes:
and selecting the extracted principal component number corresponding to the minimum value in the cross validation root-mean-square error as the optimal principal component number based on a leave-one-out cross validation method to obtain the second optimal combination.
Optionally, after comparing the historical operating condition parameter of each electric energy meter with a preset threshold, classifying the electric energy meters to obtain an electric energy meter category matrix Y of the distribution room, which specifically includes:
and sequentially judging whether all category parameters in the historical working condition parameters of each electric energy meter are within a preset threshold value, if so, assigning the electric energy meter to be 1, otherwise, assigning the electric energy meter to be 0, and classifying according to the assignment of each electric energy meter to obtain an electric energy meter category matrix Y of the distribution area.
Optionally, step S3 specifically includes:
s03, setting the ith segment of data interval in the k segments of data intervals as an ith test set, setting the complement of the ith segment of data interval as an ith training set, and modeling according to the ith training set based on a partial least square method to obtain an ith sub-model, wherein i is a positive integer;
and S04, assigning i +1 to i, and returning to the step S03 until i is k, so as to obtain the k test sets and the k sub-models.
Optionally, the historical operating condition parameters include: clock battery voltage, terminal average temperature, residual current magnitude, metering error, voltage total harmonic group distortion rate.
A second aspect of the present application provides an apparatus for evaluating a state of an electric energy meter, the apparatus comprising:
the system comprises an acquisition unit, a classification unit and a classification unit, wherein the acquisition unit is used for acquiring historical working condition parameters of a plurality of electric energy meters in a distribution room, respectively converting the historical working condition parameters of each electric energy meter into working condition parameter vectors to obtain an electric energy meter working condition parameter matrix X of the distribution room, and classifying the electric energy meters after comparing the historical working condition parameters of each electric energy meter with a preset threshold value to obtain an electric energy meter category matrix Y of the distribution room;
the dividing unit is used for obtaining an electric energy meter combined sample matrix of the distribution room according to the working condition parameter matrix X and the category matrix Y, and dividing the combined sample matrix into equal-width intervals to obtain k sections of data intervals, wherein k is a positive integer;
the first modeling unit is used for sequentially setting each section of data interval in the k sections of data intervals as a test set to obtain k test sets, setting a complementary set of each section of data interval as a training set, and respectively modeling according to each training set based on a partial least square method to obtain k sub-models;
the first calculation unit is used for selecting the submodel with the minimum mean square error from the k submodels and setting a data interval corresponding to the submodel with the minimum mean square error as a first optimal combination;
the second modeling unit is used for carrying out regression analysis on the submodel with the minimum mean square error according to the first optimal combination based on a partial least square method to obtain an electric energy meter state evaluation model of the station area;
and the analysis unit is used for inputting the k test sets into the electric energy meter state evaluation model to obtain the electric energy meter state of the transformer area.
Optionally, the method further comprises:
the second calculation unit is used for selecting the optimal principal component number of the first optimal combination based on a leave-one-out cross verification method to obtain a second optimal combination;
the analysis unit is used for performing regression analysis on the submodel with the minimum mean square error according to the second optimal combination based on a partial least square method to obtain an electric energy meter state evaluation model of the station area, and inputting the k test sets into the electric energy meter state evaluation model to obtain the electric energy meter state of the station area.
Optionally, the second computing unit is specifically configured to:
and selecting the extracted principal component number corresponding to the minimum value in the cross validation root-mean-square error as the optimal principal component number based on a leave-one-out cross validation method to obtain the second optimal combination.
Optionally, the acquisition unit is specifically configured to:
obtaining historical working condition parameters of a plurality of electric energy meters in the distribution area, respectively converting the historical working condition parameters of each electric energy meter into working condition parameter vectors to obtain an electric energy meter working condition parameter matrix X of the distribution area, sequentially judging whether all category parameters in the historical working condition parameters of each electric energy meter are within a preset threshold value, if so, assigning the electric energy meter to be '1', otherwise, assigning the electric energy meter to be '0', and classifying according to the assignment of each electric energy meter to obtain an electric energy meter category matrix Y of the distribution area.
According to the technical scheme, the embodiment of the application has the following advantages:
in an embodiment of the present application, a method for evaluating a state of an electric energy meter is provided, including: s1, obtaining historical working condition parameters of a plurality of electric energy meters in the transformer area, respectively converting the historical working condition parameters of each electric energy meter into working condition parameter vectors to obtain an electric energy meter working condition parameter matrix X of the transformer area, and classifying the electric energy meters after comparing the historical working condition parameters of each electric energy meter with a preset threshold value to obtain an electric energy meter category matrix Y of the transformer area; s2, obtaining an electric energy meter combined sample matrix of the distribution room according to the working condition parameter matrix X and the class matrix Y, and dividing the combined sample matrix into equal-width intervals to obtain k sections of data intervals, wherein k is a positive integer; s3, sequentially setting each data interval in the k data intervals as a test set to obtain k test sets, setting a complementary set of each data interval as a training set, and respectively modeling according to each training set based on a partial least square method to obtain k sub-models; s4, selecting a submodel with the minimum mean square error from the k submodels, and setting a data interval corresponding to the submodel with the minimum mean square error as a first optimal combination; s5, carrying out regression analysis on the submodel with the minimum mean square error according to the first optimal combination based on a partial least square method to obtain an electric energy meter state evaluation model of the transformer area; and S6, inputting the k test sets into the electric energy meter state evaluation model to obtain the electric energy meter state of the transformer area.
According to the method for evaluating the state of the electric energy meter, the historical working condition parameters of the electric energy meter are regarded as independent variables, and the state of the electric energy meter is regarded as dependent variables, so that the problem of multivariate variable regression statistical analysis is abstracted, but as the historical working condition parameters comprise multi-dimensional information parameters of various types, certain correlation relation may exist among the multi-dimensional information, namely certain serious multiple correlation may exist among the independent variables. In order to solve the problem, a partial least square method is introduced, firstly a matrix is established according to historical working condition parameters, then the matrix is divided, evaluation modeling is established through the partial least square method, the state of the electric energy meter is evaluated according to an evaluation model, the characteristic that the partial least square method can be used for analyzing the pattern recognition problem under the condition of small samples and multiple variables is utilized, the problems of system noise and multiple linearity can be well solved, and the technical problem that the existing online monitoring technology has poor evaluation precision on the state of the electric energy meter is solved.
Drawings
Fig. 1 is a schematic flow chart of a first embodiment of a method for evaluating a state of an electric energy meter according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a second embodiment of a method for evaluating a state of an electric energy meter according to the present embodiment;
fig. 3 is a structural diagram of an embodiment of an apparatus for evaluating a state of an electric energy meter provided in an embodiment of the present application;
FIG. 4 is a schematic diagram of selecting and extracting principal component numbers provided in the embodiment of the present application;
fig. 5 is a schematic diagram of a state evaluation result of the electric energy meter provided in the embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, a first embodiment of a method for evaluating a state of an electric energy meter according to the present application includes:
The transformer area refers to a power supply range or area of (one) transformer. It can be understood that historical operating condition parameters of a plurality of electric energy meters in a certain area in the past month are collected through the concentrator, and the historical operating condition parameters comprise: clock battery voltage, terminal average temperature, residual current magnitude, metering error, voltage total harmonic group distortion rate. The historical operating condition parameter of each electric energy meter is represented by an operating condition parameter vector in the form of a row vector, such as:
[υj1,υj2,...,υj30,tj1,tj2,...,tj30,ij1,ij2,...,ij30,ej1,ej2,...,ej30,hj1,hj2,...,hj30]
wherein upsilon isj1,υj2,...,υj30Respectively representing the battery voltage, t, of the clock of the last 30 daysj1,tj2,...,tj30Respectively representing the average temperature of the terminal in the past 30 days, ij1,ij2,...,ij30Respectively representing the magnitude of the residual current of the past 30 days, ej1,ej2,...,ej30Respectively representing the metering error of the past 30 days, hj1,hj2,...,hj30Respectively representing the total harmonic group distortion of the voltage of the last 30 days。
In addition, the preset threshold value set in this embodiment is shown in table 1, when any one working condition parameter of the electric energy meter exceeds the set threshold value range, the electric energy meter j is marked as an abnormal electric energy meter, and the category of the electric energy meter j can be assigned as 1; otherwise, the electric energy meter can be recorded as a normal electric energy meter, and the category of the electric energy meter j can be assigned to be 0.
| Operating parameters | Setting a threshold range |
| Current |
0～3.6V |
| Current |
0～135℃ |
| Current total error self-monitoring data | -2～+2％ |
| Residual current (Single-phase meter) | 0～30mA |
| Distortion rate of total harmonic group of |
0～5％ |
TABLE 1
The working condition parameter vector and the classification can respectively form a working condition parameter matrix X and a category matrix Y of multidimensional information, and the matrix comprises the following components:
102, obtaining an electric energy meter combined sample matrix of the distribution room according to the working condition parameter matrix X and the category matrix Y, and dividing the combined sample matrix into equal-width intervals to obtain k sections of data intervals, wherein k is a positive integer.
It can be understood that, for example, the application divides the combined sample matrix into 5 equal-width data intervals, then the following results are obtained: data set A, data set B, data set C, data set D and data set E.
And 103, sequentially setting each section of data interval in the k sections of data intervals as a test set to obtain k test sets, setting a complementary set of each section of data interval as a training set, and respectively modeling according to each training set based on a partial least square method to obtain k sub-models.
It is understood that, taking data set a as the test set, data set B, C,.. J is the training set, and so on, taking data set B as the test set, data set a, c.. J is the training set, and thus there are 10 test sets and 10 training sets in total, and 10 sub-models are built accordingly.
And 104, selecting the submodel with the minimum mean square error from the k submodels, and setting a data interval corresponding to the submodel with the minimum mean square error as a first optimal combination.
It can be understood that the mean square error of each submodel is respectively obtained, the submodel with the minimum mean square error is selected, and the corresponding data interval of the submodel is set as the optimal combination, which is to say, the combination is the combination of the category and the corresponding operating condition parameter.
And 105, performing regression analysis on the submodel with the minimum mean square error according to the first optimal combination based on a partial least square method to obtain an electric energy meter state evaluation model of the transformer area.
It should be noted that, because the partial least square analysis method is a regression algorithm based on characteristic variables, and can be used for analyzing the pattern recognition problem under the condition of small samples and multivariable, and well solving the problems of system noise and multiple linearity, the electric energy meter state evaluation model of the platform area is established based on the partial least square method, and is used for evaluating the state of the electric energy meter.
And 106, inputting the k test sets into an electric energy meter state evaluation model to obtain the electric energy meter state of the transformer area.
And inputting the plurality of test sets obtained in the step 103 into an evaluation model to obtain a plurality of electric energy meter states of the transformer area. Referring to table 2 and fig. 5, the corresponding confusion matrix is shown in table 2, and the state evaluation result of the electric energy meter is shown in fig. 5.
TABLE 2
| Electric energy meter with abnormal predicted value | Electric energy meter with normal predicted value | |
| Electric energy meter with abnormal actual value | 3 | 0 |
| Electric energy meter with normal actual value | 1 | 111 |
Assuming that the normal electric energy meter is a positive sample, the corresponding calculable accuracy is 75% (3/(3+1)), and the recall rate is 100% (3/(111+ 0)).
According to the method for evaluating the state of the electric energy meter, the historical working condition parameters of the electric energy meter are regarded as dependent variables, and the state of the electric energy meter is regarded as dependent variables, so that the problem of multivariate variable regression statistical analysis is abstracted. In order to solve the problem, a partial least square method is introduced, firstly a matrix is established according to historical working condition parameters, then the matrix is divided, evaluation modeling is established through the partial least square method, the state of the electric energy meter is evaluated according to an evaluation model, the characteristic that the partial least square method can be used for analyzing the pattern recognition problem under the condition of small samples and multiple variables is utilized, the problems of system noise and multiple linearity can be well solved, and the technical problem that the existing online monitoring technology has poor evaluation precision on the state of the electric energy meter is solved.
The first embodiment of the method for evaluating the state of the electric energy meter provided by the embodiment of the present application is described above, and the second embodiment of the method for evaluating the state of the electric energy meter provided by the embodiment of the present application is described below.
Referring to fig. 2, a second embodiment of the method for evaluating the state of an electric energy meter according to the present application includes:
Step 201 is the same as step 101, please refer to step 101 for description, and will not be described herein again.
Step 202 is the same as step 102, please refer to step 102, and will not be described herein.
And 203, setting the ith data interval in the k data intervals as an ith test set, setting the complement of the ith data interval as an ith training set, and modeling according to the ith training set based on a partial least square method to obtain an ith sub-model, wherein i is a positive integer.
And step 204, assigning i +1 as i, and returning to the step 203 until i is equal to k, so as to obtain k test sets and k sub-models.
For steps 203 and 204, it can be understood that assuming data set a is taken as the test set, data set B, C.
Step 205 is the same as step 104, please refer to step 104 for description, and further description is omitted here.
And step 206, selecting the extracted principal component number corresponding to the minimum value in the cross validation root mean square error as the optimal principal component number based on the leave-one-out cross validation method, and obtaining a second optimal combination.
It should be noted that, in the second embodiment of the present application, an optimal principal component number is further selected by using a leave-one cross validation method, and the first optimal combination is optimized, as shown in fig. 4, the optimal principal component number corresponding to the minimum value of the root mean square error of the interactive validation of the extracted principal component number is selected, that is, the optimal principal component number is selected to be 8.
And step 207, performing regression analysis on the submodel with the minimum mean square error according to the first optimal combination or the second optimal combination based on a partial least square method to obtain an electric energy meter state evaluation model of the transformer area.
It can be understood that, in the second embodiment of the present application, two electric energy meter state evaluation models can be established according to the first optimal combination or the second optimal combination, and the second optimal combination is a combination obtained by optimizing the first optimal combination through leave-one cross-validation.
And 208, inputting the k test sets into an electric energy meter state evaluation model to obtain the electric energy meter state of the transformer area.
Step 208 is the same as step 105, please refer to step 105, and will not be described herein.
The second embodiment of the method for evaluating the state of the electric energy meter provided in the embodiment of the present application is as follows.
Referring to fig. 3, an embodiment of an apparatus for evaluating a state of an electric energy meter according to the present application includes:
the acquisition unit 301 is configured to acquire historical operating condition parameters of a plurality of electric energy meters in the distribution room, convert the historical operating condition parameters of each electric energy meter into operating condition parameter vectors respectively, obtain an electric energy meter operating condition parameter matrix X of the distribution room, compare the historical operating condition parameters of each electric energy meter with a preset threshold, and classify the electric energy meters to obtain an electric energy meter classification matrix Y of the distribution room.
The dividing unit 302 is configured to obtain an electric energy meter combined sample matrix of the distribution room according to the working condition parameter matrix X and the category matrix Y, and divide the combined sample matrix into equal-width intervals to obtain k segments of data intervals, where k is a positive integer.
The first modeling unit 303 is configured to sequentially set each of the k segments of data intervals as a test set to obtain k test sets, set a complement of each segment of data interval as a training set, and perform modeling according to each training set based on a partial least square method to obtain k sub-models.
The first calculating unit 304 selects a submodel with the minimum mean square error from the k submodels, and sets a data interval corresponding to the submodel with the minimum mean square error as a first optimal combination.
And the second modeling unit 305 is configured to perform regression analysis on the sub-model with the minimum mean square error according to the first optimal combination based on a partial least square method to obtain an electric energy meter state evaluation model of the transformer area.
And the analysis unit 306 is configured to input the k test sets into the electric energy meter state evaluation model to obtain the electric energy meter state of the distribution room.
According to the device for evaluating the state of the electric energy meter, the historical working condition parameters of the electric energy meter are regarded as dependent variables, and the state of the electric energy meter is regarded as dependent variables, so that the problem of multivariate variable regression statistical analysis is abstracted, but as the historical working condition parameters comprise multi-dimensional information parameters of various types, certain correlation relation may exist among the multi-dimensional information, namely certain serious multiple correlation may exist among independent variables. In order to solve the problem, a partial least square method is introduced, firstly a matrix is established according to historical working condition parameters, then the matrix is divided, evaluation modeling is established through the partial least square method, the state of the electric energy meter is evaluated according to an evaluation model, the characteristic that the partial least square method can be used for analyzing the pattern recognition problem under the condition of small samples and multiple variables is utilized, the problems of system noise and multiple linearity can be well solved, and the technical problem that the existing online monitoring technology has poor evaluation precision on the state of the electric energy meter is solved.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The terms "first," "second," "third," "fourth," and the like in the description of the present application and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, 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.
The 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 application 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 unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should 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; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. A method for evaluating the state of an electric energy meter is characterized by comprising the following steps:
s1, obtaining historical working condition parameters of a plurality of electric energy meters in a distribution area, respectively converting the historical working condition parameters of each electric energy meter into working condition parameter vectors to obtain an electric energy meter working condition parameter matrix X of the distribution area, and classifying the electric energy meters after comparing the historical working condition parameters of each electric energy meter with a preset threshold value to obtain an electric energy meter category matrix Y of the distribution area;
s2, obtaining an electric energy meter combined sample matrix of the distribution room according to the working condition parameter matrix X and the category matrix Y, and dividing the combined sample matrix into equal-width intervals to obtain k sections of data intervals, wherein k is a positive integer;
s3, sequentially setting each section of data interval in the k sections of data intervals as a test set to obtain k test sets, setting a complementary set of each section of data interval as a training set, and respectively modeling according to each training set based on a partial least square method to obtain k sub-models;
s4, selecting the submodel with the minimum mean square error from the k submodels, and setting a data interval corresponding to the submodel with the minimum mean square error as a first optimal combination;
s5, performing regression analysis on the submodel with the minimum mean square error according to the first optimal combination based on a partial least square method to obtain an electric energy meter state evaluation model of the station area;
and S6, inputting the k test sets into the electric energy meter state evaluation model to obtain the electric energy meter state of the transformer area.
2. The method for evaluating the status of an electric energy meter according to claim 1, wherein after the step S4, the method further comprises:
s01, selecting the optimal principal component number of the first optimal combination based on a leave-one-out cross verification method to obtain a second optimal combination;
and S02, performing regression analysis on the submodel with the minimum mean square error according to the second optimal combination based on a partial least square method to obtain an electric energy meter state evaluation model of the station area, and inputting the k test sets into the electric energy meter state evaluation model to obtain the electric energy meter state of the station area.
3. The method for evaluating the state of the electric energy meter according to claim 2, wherein the step S01 specifically comprises:
and selecting the extracted principal component number corresponding to the minimum value in the cross validation root-mean-square error as the optimal principal component number based on a leave-one-out cross validation method to obtain the second optimal combination.
4. The method for evaluating the state of the electric energy meter according to claim 1, wherein the step of classifying the electric energy meter after comparing the historical operating condition parameter of each electric energy meter with a preset threshold value to obtain the electric energy meter category matrix Y of the distribution area specifically comprises the steps of:
and sequentially judging whether all category parameters in the historical working condition parameters of each electric energy meter are within a preset threshold value, if so, assigning the electric energy meter to be 1, otherwise, assigning the electric energy meter to be 0, and classifying according to the assignment of each electric energy meter to obtain an electric energy meter category matrix Y of the distribution area.
5. The method for evaluating the state of the electric energy meter according to claim 1, wherein the step S3 specifically comprises:
s03, setting the ith segment of data interval in the k segments of data intervals as an ith test set, setting the complement of the ith segment of data interval as an ith training set, and modeling according to the ith training set based on a partial least square method to obtain an ith sub-model, wherein i is a positive integer;
and S04, assigning i +1 to i, and returning to the step S03 until i is k, so as to obtain the k test sets and the k sub-models.
6. The method for evaluating the state of an electric energy meter according to claim 1, wherein the historical operating condition parameters comprise: clock battery voltage, terminal average temperature, residual current magnitude, metering error, voltage total harmonic group distortion rate.
7. An apparatus for evaluating a state of an electric energy meter, comprising:
the system comprises an acquisition unit, a classification unit and a classification unit, wherein the acquisition unit is used for acquiring historical working condition parameters of a plurality of electric energy meters in a distribution room, respectively converting the historical working condition parameters of each electric energy meter into working condition parameter vectors to obtain an electric energy meter working condition parameter matrix X of the distribution room, and classifying the electric energy meters after comparing the historical working condition parameters of each electric energy meter with a preset threshold value to obtain an electric energy meter category matrix Y of the distribution room;
the dividing unit is used for obtaining an electric energy meter combined sample matrix of the distribution room according to the working condition parameter matrix X and the category matrix Y, and dividing the combined sample matrix into equal-width intervals to obtain k sections of data intervals, wherein k is a positive integer;
the first modeling unit is used for sequentially setting each section of data interval in the k sections of data intervals as a test set to obtain k test sets, setting a complementary set of each section of data interval as a training set, and respectively modeling according to each training set based on a partial least square method to obtain k sub-models;
the first calculation unit is used for selecting the submodel with the minimum mean square error from the k submodels and setting a data interval corresponding to the submodel with the minimum mean square error as a first optimal combination;
the second modeling unit is used for carrying out regression analysis on the submodel with the minimum mean square error according to the first optimal combination based on a partial least square method to obtain an electric energy meter state evaluation model of the station area;
and the analysis unit is used for inputting the k test sets into the electric energy meter state evaluation model to obtain the electric energy meter state of the transformer area.
8. The apparatus for evaluating the status of an electric energy meter according to claim 7, further comprising:
the second calculation unit is used for selecting the optimal principal component number of the first optimal combination based on a leave-one-out cross verification method to obtain a second optimal combination;
the analysis unit is used for performing regression analysis on the submodel with the minimum mean square error according to the second optimal combination based on a partial least square method to obtain an electric energy meter state evaluation model of the station area, and inputting the k test sets into the electric energy meter state evaluation model to obtain the electric energy meter state of the station area.
9. The device for evaluating the status of an electric energy meter according to claim 8, wherein the second computing unit is specifically configured to:
and selecting the extracted principal component number corresponding to the minimum value in the cross validation root-mean-square error as the optimal principal component number based on a leave-one-out cross validation method to obtain the second optimal combination.
10. The device for evaluating the status of an electric energy meter according to claim 7, wherein the collecting unit is specifically configured to:
obtaining historical working condition parameters of a plurality of electric energy meters in the distribution area, respectively converting the historical working condition parameters of each electric energy meter into working condition parameter vectors to obtain an electric energy meter working condition parameter matrix X of the distribution area, sequentially judging whether all category parameters in the historical working condition parameters of each electric energy meter are within a preset threshold value, if so, assigning the electric energy meter to be '1', otherwise, assigning the electric energy meter to be '0', and classifying according to the assignment of each electric energy meter to obtain an electric energy meter category matrix Y of the distribution area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011539625.7A CN112748390B (en) | 2020-12-23 | 2020-12-23 | Method and device for evaluating state of electric energy meter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011539625.7A CN112748390B (en) | 2020-12-23 | 2020-12-23 | Method and device for evaluating state of electric energy meter |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112748390A true CN112748390A (en) | 2021-05-04 |
| CN112748390B CN112748390B (en) | 2022-02-15 |
Family
ID=75646638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011539625.7A Active CN112748390B (en) | 2020-12-23 | 2020-12-23 | Method and device for evaluating state of electric energy meter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112748390B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117405971A (en) * | 2023-10-09 | 2024-01-16 | 国网河南电力公司营销服务中心 | Power acquisition digitization method based on flow automation |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101726642A (en) * | 2009-12-17 | 2010-06-09 | 朱学东 | Electric metering tank |
| CN105678456A (en) * | 2016-01-06 | 2016-06-15 | 深圳供电局有限公司 | Method for automatically assessing electric energy metering device operation status and system thereof |
| CN106874676A (en) * | 2017-02-20 | 2017-06-20 | 广东工业大学 | A kind of electric power meter state evaluating method |
| CN109767061A (en) * | 2018-12-06 | 2019-05-17 | 中国电力科学研究院有限公司 | A kind of appraisal procedure and device of electric energy meter crash rate |
| CN111123188A (en) * | 2019-12-20 | 2020-05-08 | 国网山东省电力公司电力科学研究院 | Electric energy meter comprehensive verification method and system based on improved least square method |
| CN111999695A (en) * | 2020-10-28 | 2020-11-27 | 武汉格蓝若智能技术有限公司 | State evaluation and abnormity diagnosis method for metering device of transformer substation |
-
2020
- 2020-12-23 CN CN202011539625.7A patent/CN112748390B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101726642A (en) * | 2009-12-17 | 2010-06-09 | 朱学东 | Electric metering tank |
| CN105678456A (en) * | 2016-01-06 | 2016-06-15 | 深圳供电局有限公司 | Method for automatically assessing electric energy metering device operation status and system thereof |
| CN106874676A (en) * | 2017-02-20 | 2017-06-20 | 广东工业大学 | A kind of electric power meter state evaluating method |
| CN109767061A (en) * | 2018-12-06 | 2019-05-17 | 中国电力科学研究院有限公司 | A kind of appraisal procedure and device of electric energy meter crash rate |
| CN111123188A (en) * | 2019-12-20 | 2020-05-08 | 国网山东省电力公司电力科学研究院 | Electric energy meter comprehensive verification method and system based on improved least square method |
| CN111999695A (en) * | 2020-10-28 | 2020-11-27 | 武汉格蓝若智能技术有限公司 | State evaluation and abnormity diagnosis method for metering device of transformer substation |
Non-Patent Citations (2)
| Title |
|---|
| （德）马斯蒂安: "《数据仓库与数据挖掘》", 30 September 2003 * |
| 李志刚: "《光谱数据处理与定量分析技术》", 30 June 2017 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117405971A (en) * | 2023-10-09 | 2024-01-16 | 国网河南电力公司营销服务中心 | Power acquisition digitization method based on flow automation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112748390B (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112699913B (en) | Method and device for diagnosing abnormal relationship of household transformer in transformer area | |
| CN114298863B (en) | Data acquisition method and system of intelligent meter reading terminal | |
| CN106780121B (en) | Power consumption abnormity identification method based on power consumption load mode analysis | |
| CN106909933B (en) | A kind of stealing classification Forecasting Methodology of three stages various visual angles Fusion Features | |
| CN110727662A (en) | Low-voltage transformer area user phase identification method and system based on correlation analysis | |
| CN111738462B (en) | Fault first-aid repair active service early warning method for electric power metering device | |
| CN110689279A (en) | System and method for analyzing potential safety hazard of residential electricity consumption based on power load data | |
| CN114004296A (en) | Method and system for reversely extracting monitoring points based on power load characteristics | |
| CN111815060A (en) | Short-term load prediction method and device for power utilization area | |
| CN113125903A (en) | Line loss anomaly detection method, device, equipment and computer-readable storage medium | |
| CN112748390B (en) | Method and device for evaluating state of electric energy meter | |
| CN111160404A (en) | Method and device for analyzing reasonable value of line loss marking pole of power distribution network | |
| CN111126499A (en) | Secondary clustering-based power consumption behavior pattern classification method | |
| CN111612149A (en) | Main network line state detection method, system and medium based on decision tree | |
| CN111931992A (en) | Power load prediction index selection method and device | |
| CN111738348A (en) | Power data anomaly detection method and device | |
| CN112508260B (en) | Medium-and-long-term load prediction method and device of distribution transformer based on comparative learning | |
| CN112508254B (en) | Method for determining investment prediction data of transformer substation engineering project | |
| CN109409629B (en) | Acquisition terminal manufacturer evaluation method based on multi-attribute decision model | |
| CN110929220A (en) | Power distribution network index weight calculation method and device | |
| CN107274025B (en) | System and method for realizing intelligent identification and management of power consumption mode | |
| CN109670550B (en) | Power distribution terminal maintenance decision method and device | |
| CN112595918A (en) | Low-voltage meter reading fault detection method and device | |
| CN112215482A (en) | Method and device for identifying user variable relationship | |
| CN115877145A (en) | Transformer overload working condition big data cross evaluation system and method |
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 |