CN115798184B - Multi-module coordination-based multi-table joint self-checking method and system - Google Patents
Multi-module coordination-based multi-table joint self-checking method and system Download PDFInfo
- Publication number
- CN115798184B CN115798184B CN202211437692.7A CN202211437692A CN115798184B CN 115798184 B CN115798184 B CN 115798184B CN 202211437692 A CN202211437692 A CN 202211437692A CN 115798184 B CN115798184 B CN 115798184B
- Authority
- CN
- China
- Prior art keywords
- data
- self
- checking
- acquisition information
- data acquisition
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004458 analytical method Methods 0.000 claims abstract description 142
- 238000006243 chemical reaction Methods 0.000 claims abstract description 97
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 83
- 239000004973 liquid crystal related substance Substances 0.000 claims abstract description 24
- 238000005070 sampling Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000008859 change Effects 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 15
- 230000002688 persistence Effects 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 6
- 235000012571 Ficus glomerata Nutrition 0.000 claims description 5
- 244000153665 Ficus glomerata Species 0.000 claims description 5
- 230000000295 complement effect Effects 0.000 claims description 5
- 230000005611 electricity Effects 0.000 claims description 5
- 238000013210 evaluation model Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 abstract description 7
- 230000000694 effects Effects 0.000 description 9
- 238000012544 monitoring process Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000013480 data collection Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004377 microelectronic Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a multi-module coordination-based multi-table joint self-checking method and a multi-module coordination-based multi-table joint self-checking system, which relate to the technical field of data processing, wherein the method comprises the following steps: acquiring ammeter data acquisition information, hotlist data acquisition information, water meter data acquisition information and gas meter data acquisition information through a data sampling module respectively; interface conversion is carried out on the heat meter data acquisition information, the water meter data acquisition information and the gas meter data acquisition information through an interface conversion module; acquiring multi-meter data acquisition information according to the ammeter data acquisition information, the heat meter conversion data information, the water meter conversion data information and the gas meter conversion data information; inputting the multi-table data acquisition information into a multi-table combined self-checking model for analysis, and outputting a multi-table combined self-checking result; and carrying out display management on the multi-table combined self-checking result based on the liquid crystal display module. The intelligent and visual self-checking of the multi-meter combined self-checking is improved, and further the accuracy of the multi-meter combined self-checking result is guaranteed.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a multi-table combined self-checking method and system based on multi-module coordination.
Background
Along with the gradual development of the power industry, equipment applied in an electric power supply system is developed towards a more modern direction, and an ammeter, a water meter and the like are commonly used metering equipment so as to realize metering of consumed energy, information storage, real-time monitoring, automatic control and the like. The method has important practical significance for ensuring the accurate metering operation of each meter device and realizing accurate self-checking.
However, the self-checking intelligent degree of each meter device in the prior art is not high, so that the technical problem of inaccurate self-checking result is caused.
Disclosure of Invention
The multi-table combined self-checking method and system based on multi-module coordination solve the technical problem that the self-checking result is inaccurate due to low self-checking intelligent degree of each table device in the prior art, achieve the technical effects of carrying out combined self-checking on multiple tables through multi-module coordination, reducing investment cost, improving the intelligent and visual self-checking of the multi-table combined self-checking, and further guaranteeing the accuracy of the multi-table combined self-checking result.
In view of the above problems, the invention provides a multi-table joint self-checking method and system based on multi-module coordination.
In a first aspect, the present application provides a multi-module coordination-based multi-table joint self-checking method, the method comprising: the method comprises the steps of obtaining a special transformer acquisition terminal, wherein the special transformer acquisition terminal comprises a CPU module, a data sampling module, a liquid crystal display module and an interface conversion module; acquiring ammeter data acquisition information, hotlist data acquisition information, water meter data acquisition information and gas meter data acquisition information through the data sampling module respectively; interface conversion is carried out on the heat meter data acquisition information, the water meter data acquisition information and the gas meter data acquisition information through the interface conversion module, so that heat meter conversion data information, water meter conversion data information and gas meter conversion data information are obtained; acquiring multi-meter data acquisition information according to the ammeter data acquisition information, the heat meter conversion data information, the water meter conversion data information and the gas meter conversion data information; calling by the CPU module to obtain a multi-table joint self-checking model; inputting the multi-table data acquisition information into the multi-table combined self-checking model for analysis, and outputting a multi-table combined self-checking result; and carrying out display management on the multi-table combined self-checking result based on the liquid crystal display module.
In another aspect, the present application further provides a multi-module coordination-based multi-table joint self-checking system, where the system includes: the special transformer acquisition terminal acquisition module is used for acquiring a special transformer acquisition terminal, and comprises a CPU module, a data sampling module, a liquid crystal display module and an interface conversion module; the data sampling module is used for respectively obtaining ammeter data acquisition information, hotlist data acquisition information, water meter data acquisition information and gas meter data acquisition information through the data sampling module; the interface conversion module is used for carrying out interface conversion on the heat meter data acquisition information, the water meter data acquisition information and the gas meter data acquisition information through the interface conversion module to obtain heat meter conversion data information, water meter conversion data information and gas meter conversion data information; the multi-meter data information acquisition module is used for acquiring multi-meter data acquisition information according to the ammeter data acquisition information, the heat meter conversion data information, the water meter conversion data information and the gas meter conversion data information; the model calling module is used for calling the CPU module to obtain a multi-table joint self-checking model; the model analysis output module is used for inputting the multi-table data acquisition information into the multi-table combined self-checking model for analysis and outputting a multi-table combined self-checking result; and the display management module is used for carrying out display management on the multi-table combined self-checking result based on the liquid crystal display module.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
The data sampling module is used for respectively obtaining ammeter data acquisition information, hotlist data acquisition information, water meter data acquisition information and gas meter data acquisition information, the interface conversion module is used for carrying out interface conversion on the hotlist data acquisition information, the water meter data acquisition information and the gas meter data acquisition information to obtain hotlist conversion data information, water meter conversion data information and gas meter conversion data information, and the multi-meter data acquisition information is obtained according to the ammeter data acquisition information, the hotlist conversion data information, the water meter conversion data information and the gas meter conversion data information; and calling a multi-table combined self-checking model through a CPU module, inputting the multi-table data acquisition information into the multi-table combined self-checking model for analysis, outputting a multi-table combined self-checking result, and carrying out display management on the multi-table combined self-checking result based on the technical scheme of the liquid crystal display module. And then, the multi-table combined self-checking is carried out through the coordination of the multiple modules, so that the investment cost is reduced, the intelligent and visual self-checking of the multi-table combined self-checking is improved, and the technical effect of the accuracy of the multi-table combined self-checking result is further ensured.
Drawings
FIG. 1 is a schematic flow chart of a multi-table joint self-checking method based on multi-module coordination;
FIG. 2 is a schematic flow chart of a multi-table joint self-checking model obtained in a multi-table joint self-checking method based on multi-module coordination of the application;
FIG. 3 is a schematic flow chart of obtaining table operation characteristics in a multi-table combined self-checking method based on multi-module coordination according to the present application;
FIG. 4 is a schematic structural diagram of a multi-module coordination-based multi-table joint self-checking system according to the present application;
Reference numerals illustrate: the system comprises a private transformer acquisition terminal acquisition module 11, a data sampling module 12, an interface conversion module 13, a multi-table data information acquisition module 14, a model calling module 15, a model analysis output module 16 and a display management module 17.
Detailed Description
The application provides a multi-table combined self-checking method system based on multi-module coordination, which solves the technical problem of inaccurate self-checking results caused by low self-checking intelligent degree of each table device in the prior art, achieves the technical effects of carrying out combined self-checking on multiple tables through multi-module coordination, reducing investment cost, improving intelligent and visual self-checking of the multi-table combined self-checking, and further ensuring the accuracy of the multi-table combined self-checking results.
Example 1
As shown in fig. 1, the present application provides a multi-module coordination-based multi-table joint self-checking method, which is applied to a multi-table joint self-checking system, and comprises the following steps:
step S100: the method comprises the steps of obtaining a special transformer acquisition terminal, wherein the special transformer acquisition terminal comprises a CPU module, a data sampling module, a liquid crystal display module and an interface conversion module;
In particular, with the gradual development of the power industry, devices used in the power supply system are also developed towards more modernization, and electric meters, water meters and the like are commonly used metering devices to realize metering of consumed energy, information storage, real-time monitoring, automatic control and the like. The method has important practical significance for ensuring the accurate metering operation of each meter device and realizing accurate self-checking.
The special transformer acquisition terminal is a customer electricity management terminal specially designed based on an embedded software and hardware development platform by combining years of design development and field operation experience in the power industry and meeting the requirements of modernization of management at the power demand side. The system adopts the most advanced technology of the micro-electronics technology, the computer chip technology, the modern communication technology and the like, supports the public wireless communication network technology of GPRS/GSM/CDMA and the like, can realize the functions of automatic meter reading, load monitoring and control for power users, prepayment management, electric energy quality management, electricity larceny prevention, abnormal alarm and the like by being matched with a power load management master station system, is widely applicable to an electricity utilization field service and power load management system, and is a terminal product with higher practical value in an electric power marketing automation system. The special transformer acquisition terminal comprises a CPU module, a data sampling module, a liquid crystal display module, an interface conversion module and the like, and the modules directly coordinate to each other.
Step S200: acquiring ammeter data acquisition information, hotlist data acquisition information, water meter data acquisition information and gas meter data acquisition information through the data sampling module respectively;
Specifically, the data sampling module is used for collecting real-time consumption data of the electric meter, the heat meter, the water meter and the gas meter to respectively obtain electric meter data collection information, heat meter data collection information, water meter data collection information and gas meter data collection information, wherein the information comprises total electric quantity, peak electric quantity, valley electric quantity, total power, water flow accumulated flow, accumulated heat, thermal power, heat flow, gas accumulated quantity and the like.
Step S300: interface conversion is carried out on the heat meter data acquisition information, the water meter data acquisition information and the gas meter data acquisition information through the interface conversion module, so that heat meter conversion data information, water meter conversion data information and gas meter conversion data information are obtained;
Step S400: acquiring multi-meter data acquisition information according to the ammeter data acquisition information, the heat meter conversion data information, the water meter conversion data information and the gas meter conversion data information;
Specifically, the interface conversion module is used for carrying out interface conversion on the heat meter data acquisition information, the water meter data acquisition information and the gas meter data acquisition information, so that the integration of multiple meter data is realized, and corresponding heat meter conversion data information, water meter conversion data information and gas meter conversion data information are obtained. And collecting the ammeter data acquisition information, the heat meter conversion data information, the water meter conversion data information and the gas meter conversion data information to obtain multi-meter data acquisition information, and carrying out data integration acquisition to reduce investment cost and achieve multi-meter collection and reading.
Step S500: calling by the CPU module to obtain a multi-table joint self-checking model;
as shown in fig. 2, further, the step S500 of obtaining the multi-table joint self-checking model further includes:
Step S510: acquiring historical ammeter data acquisition information, historical hotlist data acquisition information, historical watermeter data acquisition information and historical gas meter data acquisition information;
Step S520: respectively carrying out characteristic analysis on the historical ammeter data acquisition information, the historical hotlist data acquisition information, the historical watermeter data acquisition information and the historical gas meter data acquisition information to obtain ammeter operation characteristics, hotlist operation characteristics, watermeter operation characteristics and gas meter operation characteristics;
Step S530: respectively performing self-checking model training according to the ammeter operation characteristics, the hotlist operation characteristics, the water meter operation characteristics and the gas meter operation characteristics to obtain an ammeter self-checking analysis model, a hotlist self-checking analysis model, a water meter self-checking analysis model and a gas meter self-checking analysis model;
Step S540: extracting model parameters of the ammeter self-checking analysis model, the hotlist self-checking analysis model, the water meter self-checking analysis model and the gas meter self-checking analysis model to obtain ammeter analysis model parameters, hotlist analysis model parameters, water meter analysis model parameters and gas meter analysis model parameters;
Step S550: and constructing the multi-meter combined self-checking model based on the ammeter analysis model parameters, the hotlist analysis model parameters, the water meter analysis model parameters and the gas meter analysis model parameters.
As shown in fig. 3, further, the obtaining the electricity meter operation feature, the heat meter operation feature, the water meter operation feature, and the gas meter operation feature in step S520 of the present application further includes:
step S521: respectively performing unsupervised learning classification on the historical ammeter data acquisition information, the historical hotlist data acquisition information, the historical watermeter data acquisition information and the historical gas meter data acquisition information to generate a continuity list data set;
Step S522: constructing a table data change curve set according to the continuity table data set;
Step S523: performing curvature analysis on the table data change curve to obtain a table data curvature change result set;
Step S524: and inputting the table data curvature change result set into a table data characteristic evaluation model to respectively obtain the ammeter operation characteristic, the hotlist operation characteristic, the water meter operation characteristic and the gas meter operation characteristic.
Further, the generating the continuity table data set, step S521 of the present application further includes:
Step S5211: performing traversal access processing on the historical ammeter data acquisition information, the historical hotlist data acquisition information, the historical watermeter data acquisition information and the historical gas meter data acquisition information respectively to generate a uniformity list data set;
Step S5212: defining the data in the uniformity table data set as P clusters;
Step S5213: average value calculation is carried out on the distances of the data points in the P clusters, so that an average distance data set is obtained;
step S5214: obtaining a class table data set according to the average distance data set, wherein the class table data set comprises a class set with the minimum distance average value;
Step S5215: performing layer-by-layer recursive clustering on the average distance data set according to the class table data set until a table data clustering tree of the uniformity table data set is generated;
Step S5216: and carrying out learning classification based on the table data cluster tree to generate the continuity table data set.
Specifically, the CPU module is the core of the special transformer acquisition terminal, controls each module to coordinate, and calls the multi-table joint self-checking model through the CPU module, wherein the multi-table joint self-checking model is a neural network model and is used for carrying out data joint self-checking on each table. The model training construction process comprises the steps of acquiring historical ammeter data acquisition information, historical heat meter data acquisition information, historical water meter data acquisition information and historical gas meter data acquisition information through big data or a system historical module. And respectively carrying out characteristic analysis on the historical ammeter data acquisition information, the historical hotlist data acquisition information, the historical water meter data acquisition information and the historical gas meter data acquisition information, wherein the analysis process is to respectively carry out unsupervised learning classification on the historical ammeter data acquisition information, the historical hotlist data acquisition information, the historical water meter data acquisition information and the historical gas meter data acquisition information, wherein the unsupervised learning is based on training samples with unknown categories, namely, no data label exists, only the data is used, and the problem in pattern recognition is solved.
The continuous table data set is generated through unsupervised learning classification, and firstly, traversal access processing is respectively carried out on all data information in the historical ammeter data acquisition information, the historical hotlist data acquisition information, the historical watermeter data acquisition information and the historical gas meter data acquisition information, so that the uniform table data set can be generated. The data in the uniformity table data set is then defined as P clusters, where the clusters refer to the process of grouping similar things together and classifying dissimilar things into different categories. And further measuring and calculating the distances between the data points in the P clusters, and then carrying out average value calculation to obtain the average distance between the data points in the P clusters, namely an average distance data set, wherein the average distance data set has P average value data which are respectively in one-to-one correspondence with the P clusters.
And further obtaining P pieces of clustering average table data information, namely class table data sets, according to the average distance data sets, wherein the class table data sets comprise the class sets with the smallest distance average value. The class table data set includes a class set having a smallest distance average. And carrying out layer-by-layer recursive clustering on the average distance data set according to the class table data set until a table data clustering tree of the uniformity table data set is generated, wherein the layer-by-layer recursive clustering means that data with the largest or smallest average distance data are combined into a large class according to the size of the average distance data and the sequence from large to small or from small to large. And finally, carrying out learning classification on each table data based on the table data clustering tree to generate a continuity table data set when the table data are continuous. The continuity data in the continuity table data set indicates the monitored trend of the table data information, and the classification of the table data information is realized through unsupervised learning, so that the technical effect of more accurate learning classification of the table data is achieved through intelligent calculation.
And constructing a table data change curve set according to the continuity table data set, wherein the table data change curve set is a continuous data change curve obtained by monitoring each table data in real time. And carrying out curvature analysis on the table data change curve to obtain a corresponding table data curvature change result set, wherein the curvature analysis shows that the larger the curvature is, and the curve bending degree is. Inputting the table data curvature change result set into a table data characteristic evaluation model, wherein the table data characteristic evaluation model is used for carrying out operation characteristic analysis on the table data curvature change, and can be obtained through historical data training, so that the corresponding electric meter operation characteristic, heat meter operation characteristic, water meter operation characteristic and gas meter operation characteristic are respectively output and obtained, and the electric meter operation characteristic, heat meter operation characteristic, water meter operation characteristic and gas meter operation characteristic are operation characteristics of each table operation.
And respectively performing self-checking model training according to the ammeter operation characteristics, the hotlist operation characteristics, the water meter operation characteristics and the gas meter operation characteristics, performing neural network model training through historical data, and ending the supervision and learning process when the output information of the neural network model reaches a preset accuracy rate or reaches a convergence state to obtain an ammeter self-checking analysis model, a hotlist self-checking analysis model, a water meter self-checking analysis model and a gas meter self-checking analysis model corresponding to corresponding characteristic data, wherein the ammeter self-checking analysis model, the hotlist self-checking analysis model, the water meter self-checking analysis model and the gas meter self-checking analysis model are used for performing self-checking analysis on the working states of the ammeter, the hotlist, the water meter and the gas meter. And extracting model parameters of the ammeter self-checking analysis model, the hotlist self-checking analysis model, the water meter self-checking analysis model and the gas meter self-checking analysis model to obtain ammeter analysis model parameters, hotlist analysis model parameters, water meter analysis model parameters and gas meter analysis model parameters, wherein the ammeter analysis model parameters, the hotlist analysis model parameters, the gas meter analysis model parameters comprise model weights, characteristic parameters, identification parameters and the like.
Based on the ammeter analysis model parameters, the hotlist analysis model parameters, the watermeter analysis model parameters and the gas meter analysis model parameters, constructing a multi-meter combined self-checking model obtained by combined training of the model parameters, wherein the multi-meter combined self-checking model is used for carrying out data combined self-checking on the tables and self-checking the running state and the fault type of the tables. And the self-checking model is built through the combined training of the model parameters of each table, the model training output accuracy is more accurate, and the multi-table combined self-checking intellectualization and the self-checking high efficiency are improved.
Step S600: inputting the multi-table data acquisition information into the multi-table combined self-checking model for analysis, and outputting a multi-table combined self-checking result;
Further, the step S600 of the present application further includes:
Step S610: the multi-table combined self-checking model comprises an input layer, a characteristic analysis layer, a self-checking analysis layer and an output layer;
Step S620: the multi-table data acquisition information is used as an input layer and is input into the feature analysis layer, so that table data operation features are obtained;
Step S630: inputting the table data operation characteristics into the self-checking analysis layer to obtain a multi-table combined self-checking result;
Step S640: and outputting the multi-table combined self-checking result as a model output result through the output layer.
Specifically, the multi-table data acquisition information is input into the multi-table combined self-checking model for analysis, and the multi-table combined self-checking model comprises an input layer, a characteristic analysis layer, a self-checking analysis layer and an output layer. Firstly, the multi-table data acquisition information is used as an input layer and is input into the characteristic analysis layer, the characteristic analysis layer is used for analyzing the operation characteristics of each table, and the analysis process is the table data characteristic analysis, so that the table data operation characteristics, such as the characteristics of stable operation, operation faults and the like, are obtained. And inputting the table data operation characteristics into the self-checking analysis layer, wherein the self-checking analysis layer can be obtained through historical data training and is used for carrying out fault identification analysis on the operation characteristics and outputting to obtain a multi-table combined self-checking result, and the multi-table combined self-checking result comprises a self-checking safe operation result, a self-checking fault type and the like. And the multi-table combined self-checking result is output as a model output result through the output layer, and the self-checking result is output through constructing a model multi-logic layer, so that the accuracy of the multi-table combined self-checking result is improved.
Step S700: and carrying out display management on the multi-table combined self-checking result based on the liquid crystal display module.
Further, the step S700 of the present application further includes:
Step S710: obtaining a table fault type according to the multi-table joint self-checking result;
Step S720: performing fault level assessment on the multi-table combined self-checking result to obtain a table fault level coefficient;
step S730: based on the table fault type and the table fault class coefficient, formulating a table fault solution;
Step S740: and displaying and controlling the table fault type, the table fault grade coefficient and the table fault solution through the liquid crystal display module.
Specifically, display management is performed on the multi-table combined self-checking result based on the liquid crystal display module, and specifically, the type of the table fault is determined according to the multi-table combined self-checking result, including the types of the table metering fault, the table operation fault and the like. And carrying out fault grade assessment on each fault type of the multi-table combined self-checking result, and determining the corresponding table fault grade coefficient, wherein the larger the coefficient is, the larger the fault grade is. And based on the table fault types and the table fault grade coefficients, formulating a table fault solution, wherein the table fault solution is a solution of each table fault type, for example, measures such as calibrating and clearing an ammeter are carried out. The liquid crystal display module is used for displaying, controlling and controlling the meter fault type, the meter fault grade coefficient and the meter fault solution, and the multi-meter is subjected to joint self-checking through multi-module coordination, so that the investment cost is reduced, and the intelligent and visual self-checking of the multi-meter joint self-checking is improved.
Further, step S524 of the present application further includes:
Step S5241: obtaining a discrete table data set according to the complement of the continuous table data set;
Step S5242: obtaining a discrete persistence table data set exceeding a predetermined time threshold value in the discrete persistence table data set;
Step S5243: carrying out variance calculation on the numerical values in the discrete persistence table data set, and taking a variance calculation result as a table data deviation degree;
Step S5244: and if the deviation degree of the table data exceeds the preset deviation degree, carrying out self-checking early warning on the table data.
Specifically, the discrete table data set is determined according to the complement of the continuous table data set, that is, the complement of the total remaining data of the continuous table data set, and discrete data in the discrete table data set is a discrete result caused by a plurality of factors, such as a table device signal interference factor, an external pressure factor, an environmental temperature factor, and the like, so that the discrete data cannot be used as an actual value of the table data, and other monitoring data need to be analyzed after the discrete data are excluded. The discrete persistence table data set is data exceeding a predetermined time threshold in the discrete persistence table data set, and the predetermined time threshold is a preset discrete table data duration range, which indicates that the discrete result of the data needs to be analyzed.
And carrying out variance calculation on the numerical values in the discrete persistence table data set, taking a variance calculation result as a table data deviation degree, wherein the variance indicates the discrete degree of the table data, and the larger the variance is, the higher the discrete degree of the monitoring data is, and the worse the running condition of the table data is. If the deviation degree of the meter data exceeds the preset deviation degree, the condition that the working quality of the meter is not up to the standard due to external factors such as environment and the like is indicated, metering faults are caused, and self-checking and early warning are needed to be carried out on the meter data. By considering the influence of factors such as the working environment of the meter, the meter equipment and the like on the metering work, the accuracy of the self-checking result is improved, the fault of the meter is early warned in time, and the technical effect of the metering accuracy of the meter work is further ensured.
In summary, the multi-table combined self-checking method and system based on multi-module coordination provided by the application have the following technical effects:
The data sampling module is used for respectively obtaining ammeter data acquisition information, hotlist data acquisition information, water meter data acquisition information and gas meter data acquisition information, the interface conversion module is used for carrying out interface conversion on the hotlist data acquisition information, the water meter data acquisition information and the gas meter data acquisition information to obtain hotlist conversion data information, water meter conversion data information and gas meter conversion data information, and the multi-meter data acquisition information is obtained according to the ammeter data acquisition information, the hotlist conversion data information, the water meter conversion data information and the gas meter conversion data information; and calling a multi-table combined self-checking model through a CPU module, inputting the multi-table data acquisition information into the multi-table combined self-checking model for analysis, outputting a multi-table combined self-checking result, and carrying out display management on the multi-table combined self-checking result based on the technical scheme of the liquid crystal display module. And then, the multi-table combined self-checking is carried out through the coordination of the multiple modules, so that the investment cost is reduced, the intelligent and visual self-checking of the multi-table combined self-checking is improved, and the technical effect of the accuracy of the multi-table combined self-checking result is further ensured.
Example two
Based on the same inventive concept as the multi-module coordination-based multi-table joint self-checking method in the foregoing embodiment, the present invention further provides a multi-module coordination-based multi-table joint self-checking system, as shown in fig. 4, where the system includes:
the special transformer acquisition terminal acquisition module 11 is used for acquiring a special transformer acquisition terminal, and the special transformer acquisition terminal comprises a CPU module, a data sampling module, a liquid crystal display module and an interface conversion module;
the data sampling module 12 is used for respectively obtaining ammeter data acquisition information, hotlist data acquisition information, water meter data acquisition information and gas meter data acquisition information through the data sampling module;
the interface conversion module 13 is configured to perform interface conversion on the heat meter data acquisition information, the water meter data acquisition information, and the gas meter data acquisition information through the interface conversion module to obtain heat meter conversion data information, water meter conversion data information, and gas meter conversion data information;
A multi-meter data information obtaining module 14, configured to obtain multi-meter data acquisition information according to the electric meter data acquisition information, the heat meter conversion data information, the water meter conversion data information, and the gas meter conversion data information;
The model calling module 15 is used for calling the CPU module to obtain a multi-table joint self-checking model;
the model analysis output module 16 is configured to input the multi-table data acquisition information into the multi-table joint self-test model for analysis, and output a multi-table joint self-test result;
and the display management module 17 is used for carrying out display management on the multi-table combined self-checking result based on the liquid crystal display module.
Further, the model calling module further includes:
The historical data information acquisition unit is used for acquiring historical ammeter data acquisition information, historical hotlist data acquisition information, historical watermeter data acquisition information and historical gas meter data acquisition information;
The characteristic analysis unit is used for respectively carrying out characteristic analysis on the historical ammeter data acquisition information, the historical hotlist data acquisition information, the historical watermeter data acquisition information and the historical gas meter data acquisition information to obtain ammeter operation characteristics, hotlist operation characteristics, watermeter operation characteristics and gas meter operation characteristics;
The model training unit is used for respectively carrying out self-checking model training according to the ammeter operation characteristics, the hotlist operation characteristics, the water meter operation characteristics and the gas meter operation characteristics to obtain an ammeter self-checking analysis model, a hotlist self-checking analysis model, a water meter self-checking analysis model and a gas meter self-checking analysis model;
the model parameter extraction unit is used for extracting model parameters of the ammeter self-checking analysis model, the hotlist self-checking analysis model, the water meter self-checking analysis model and the gas meter self-checking analysis model to obtain ammeter analysis model parameters, hotlist analysis model parameters, water meter analysis model parameters and gas meter analysis model parameters;
The multi-meter combined self-checking model construction unit is used for constructing the multi-meter combined self-checking model based on the ammeter analysis model parameter, the hotlist analysis model parameter, the water meter analysis model parameter and the gas meter analysis model parameter.
Further, the feature analysis unit further includes:
The non-supervision learning classification unit is used for performing non-supervision learning classification on the historical ammeter data acquisition information, the historical hotlist data acquisition information, the historical watermeter data acquisition information and the historical gas meter data acquisition information respectively to generate a continuity list data set;
The change curve set construction unit is used for constructing a table data change curve set according to the continuity table data set;
The curvature analysis unit is used for carrying out curvature analysis on the table data change curve to obtain a table data curvature change result set;
And the operation characteristic obtaining unit is used for inputting the table data curvature change result set into a table data characteristic evaluation model to respectively obtain the ammeter operation characteristic, the hotlist operation characteristic, the water meter operation characteristic and the gas meter operation characteristic.
Further, the unsupervised learning classification unit further includes:
The traversal access processing unit is used for respectively performing traversal access processing on the historical ammeter data acquisition information, the historical hotlist data acquisition information, the historical watermeter data acquisition information and the historical gas meter data acquisition information to generate a uniformity list data set;
a data definition unit, configured to define data in the uniformity table data set as P clusters;
The distance average value calculation unit is used for carrying out average value calculation on the distances of the data points in the P clusters to obtain an average distance data set;
A class table data set obtaining unit, configured to obtain a class table data set according to the average distance data set, where the class table data set includes a class set with a minimum distance average value;
A recursive clustering unit, configured to recursively cluster the average distance data set layer by layer according to the class table data set until a table data cluster tree of the uniformity table data set is generated;
And the cluster tree classification unit is used for carrying out learning classification based on the table data cluster tree and generating the continuity table data set.
Further, the system further comprises:
a discrete table data set obtaining unit, configured to obtain a discrete table data set according to a complement of the continuous table data set;
A discrete persistence table data obtaining unit configured to obtain a discrete persistence table data set exceeding a predetermined time threshold value from among the discrete persistence table data sets;
the variance calculation unit is used for carrying out variance calculation on the numerical values in the discrete persistence table data set, and taking a variance calculation result as a table data deviation degree;
And the self-checking early warning unit is used for carrying out self-checking early warning on the meter data if the deviation degree of the meter data exceeds the preset deviation degree.
Further, the model analysis output module further includes:
the model forming unit is used for the multi-table combined self-checking model and comprises an input layer, a characteristic analysis layer, a self-checking analysis layer and an output layer;
The model input unit is used for taking the multi-table data acquisition information as an input layer and inputting the multi-table data acquisition information into the feature analysis layer to obtain table data operation features;
the self-checking analysis unit is used for inputting the table data operation characteristics into the self-checking analysis layer to obtain a multi-table combined self-checking result;
and the model output unit is used for outputting the multi-table combined self-checking result as a model output result through the output layer.
Further, the display management module further includes:
the fault type obtaining unit is used for obtaining the table fault type according to the multi-table combined self-checking result;
the fault grade evaluation unit is used for carrying out fault grade evaluation on the multi-table combined self-checking result to obtain a table fault grade coefficient;
a fault solution formulation unit, configured to formulate a table fault solution based on the table fault type and the table fault class coefficient;
and the display management and control unit is used for carrying out display management and control on the table fault type, the table fault grade coefficient and the table fault solution through the liquid crystal display module.
The application provides a multi-module coordination-based multi-table joint self-checking method, which comprises the following steps: the method comprises the steps of obtaining a special transformer acquisition terminal, wherein the special transformer acquisition terminal comprises a CPU module, a data sampling module, a liquid crystal display module and an interface conversion module; acquiring ammeter data acquisition information, hotlist data acquisition information, water meter data acquisition information and gas meter data acquisition information through the data sampling module respectively; interface conversion is carried out on the heat meter data acquisition information, the water meter data acquisition information and the gas meter data acquisition information through the interface conversion module, so that heat meter conversion data information, water meter conversion data information and gas meter conversion data information are obtained; acquiring multi-meter data acquisition information according to the ammeter data acquisition information, the heat meter conversion data information, the water meter conversion data information and the gas meter conversion data information; calling by the CPU module to obtain a multi-table joint self-checking model; inputting the multi-table data acquisition information into the multi-table combined self-checking model for analysis, and outputting a multi-table combined self-checking result; and carrying out display management on the multi-table combined self-checking result based on the liquid crystal display module. The technical problem that the self-checking result is not accurate enough due to the fact that the self-checking intelligent degree of each meter device is not high in the prior art is solved. The technical effects of carrying out the combined self-checking on the multiple tables through the coordination of multiple modules, reducing the investment cost, improving the intellectualization and the visual self-checking of the combined self-checking of the multiple tables and further ensuring the accuracy of the result of the combined self-checking of the multiple tables are achieved.
The specification and drawings are merely exemplary of the present application, and the present application is intended to cover modifications and variations of the present application provided they come within the scope of the application and its equivalents.
Claims (7)
1. The multi-module coordination-based multi-table joint self-checking method is characterized by comprising the following steps of:
the method comprises the steps of obtaining a special transformer acquisition terminal, wherein the special transformer acquisition terminal comprises a CPU module, a data sampling module, a liquid crystal display module and an interface conversion module;
Acquiring ammeter data acquisition information, hotlist data acquisition information, water meter data acquisition information and gas meter data acquisition information through the data sampling module respectively;
Interface conversion is carried out on the heat meter data acquisition information, the water meter data acquisition information and the gas meter data acquisition information through the interface conversion module, so that heat meter conversion data information, water meter conversion data information and gas meter conversion data information are obtained;
acquiring multi-meter data acquisition information according to the ammeter data acquisition information, the heat meter conversion data information, the water meter conversion data information and the gas meter conversion data information;
calling by the CPU module to obtain a multi-table joint self-checking model;
Inputting the multi-table data acquisition information into the multi-table combined self-checking model for analysis, and outputting a multi-table combined self-checking result;
Performing display management on the multi-table combined self-checking result based on the liquid crystal display module;
wherein the obtaining of the multi-table joint self-test model comprises:
acquiring historical ammeter data acquisition information, historical hotlist data acquisition information, historical watermeter data acquisition information and historical gas meter data acquisition information;
respectively carrying out characteristic analysis on the historical ammeter data acquisition information, the historical hotlist data acquisition information, the historical watermeter data acquisition information and the historical gas meter data acquisition information to obtain ammeter operation characteristics, hotlist operation characteristics, watermeter operation characteristics and gas meter operation characteristics;
Respectively performing self-checking model training according to the ammeter operation characteristics, the hotlist operation characteristics, the water meter operation characteristics and the gas meter operation characteristics to obtain an ammeter self-checking analysis model, a hotlist self-checking analysis model, a water meter self-checking analysis model and a gas meter self-checking analysis model;
extracting model parameters of the ammeter self-checking analysis model, the hotlist self-checking analysis model, the water meter self-checking analysis model and the gas meter self-checking analysis model to obtain ammeter analysis model parameters, hotlist analysis model parameters, water meter analysis model parameters and gas meter analysis model parameters;
and constructing the multi-meter combined self-checking model based on the ammeter analysis model parameters, the hotlist analysis model parameters, the water meter analysis model parameters and the gas meter analysis model parameters.
2. The method of claim 1, wherein the obtaining electricity meter operating characteristics, heat meter operating characteristics, water meter operating characteristics, gas meter operating characteristics comprises:
respectively performing unsupervised learning classification on the historical ammeter data acquisition information, the historical hotlist data acquisition information, the historical watermeter data acquisition information and the historical gas meter data acquisition information to generate a continuity list data set;
constructing a table data change curve set according to the continuity table data set;
performing curvature analysis on the table data change curve to obtain a table data curvature change result set;
And inputting the table data curvature change result set into a table data characteristic evaluation model to respectively obtain the ammeter operation characteristic, the hotlist operation characteristic, the water meter operation characteristic and the gas meter operation characteristic.
3. The method of claim 2, wherein the generating a continuity table data set comprises:
performing traversal access processing on the historical ammeter data acquisition information, the historical hotlist data acquisition information, the historical watermeter data acquisition information and the historical gas meter data acquisition information respectively to generate a uniformity list data set;
defining the data in the uniformity table data set as P clusters;
average value calculation is carried out on the distances of the data points in the P clusters, so that an average distance data set is obtained;
Obtaining a class table data set according to the average distance data set, wherein the class table data set comprises a class set with the minimum distance average value;
Performing layer-by-layer recursive clustering on the average distance data set according to the class table data set until a table data clustering tree of the uniformity table data set is generated;
And carrying out learning classification based on the table data cluster tree to generate the continuity table data set.
4. The method of claim 2, wherein the method further comprises:
obtaining a discrete table data set according to the complement of the continuous table data set;
obtaining a discrete persistence table data set exceeding a predetermined time threshold value in the discrete persistence table data set;
Carrying out variance calculation on the numerical values in the discrete persistence table data set, and taking a variance calculation result as a table data deviation degree;
And if the deviation degree of the table data exceeds the preset deviation degree, carrying out self-checking early warning on the table data.
5. The method of claim 1, wherein outputting the multi-table joint self-test result comprises:
The multi-table combined self-checking model comprises an input layer, a characteristic analysis layer, a self-checking analysis layer and an output layer;
the multi-table data acquisition information is used as an input layer and is input into the feature analysis layer, so that table data operation features are obtained;
inputting the table data operation characteristics into the self-checking analysis layer to obtain a multi-table combined self-checking result;
and outputting the multi-table combined self-checking result as a model output result through the output layer.
6. The method of claim 1, wherein the performing display management on the multi-table joint self-test result based on the liquid crystal display module comprises:
obtaining a table fault type according to the multi-table joint self-checking result;
Performing fault level assessment on the multi-table combined self-checking result to obtain a table fault level coefficient;
based on the table fault type and the table fault class coefficient, formulating a table fault solution;
and displaying and controlling the table fault type, the table fault grade coefficient and the table fault solution through the liquid crystal display module.
7. A multi-module coordination-based multi-table joint self-test system, the system comprising:
The special transformer acquisition terminal acquisition module is used for acquiring a special transformer acquisition terminal, and comprises a CPU module, a data sampling module, a liquid crystal display module and an interface conversion module;
the data sampling module is used for respectively obtaining ammeter data acquisition information, hotlist data acquisition information, water meter data acquisition information and gas meter data acquisition information through the data sampling module;
The interface conversion module is used for carrying out interface conversion on the heat meter data acquisition information, the water meter data acquisition information and the gas meter data acquisition information through the interface conversion module to obtain heat meter conversion data information, water meter conversion data information and gas meter conversion data information;
the multi-meter data information acquisition module is used for acquiring multi-meter data acquisition information according to the ammeter data acquisition information, the heat meter conversion data information, the water meter conversion data information and the gas meter conversion data information;
the model calling module is used for calling the CPU module to obtain a multi-table joint self-checking model;
the model analysis output module is used for inputting the multi-table data acquisition information into the multi-table combined self-checking model for analysis and outputting a multi-table combined self-checking result;
The display management module is used for carrying out display management on the multi-table combined self-checking result based on the liquid crystal display module;
The model calling module comprises:
The historical data information acquisition unit is used for acquiring historical ammeter data acquisition information, historical hotlist data acquisition information, historical watermeter data acquisition information and historical gas meter data acquisition information;
The characteristic analysis unit is used for respectively carrying out characteristic analysis on the historical ammeter data acquisition information, the historical hotlist data acquisition information, the historical watermeter data acquisition information and the historical gas meter data acquisition information to obtain ammeter operation characteristics, hotlist operation characteristics, watermeter operation characteristics and gas meter operation characteristics;
The model training unit is used for respectively carrying out self-checking model training according to the ammeter operation characteristics, the hotlist operation characteristics, the water meter operation characteristics and the gas meter operation characteristics to obtain an ammeter self-checking analysis model, a hotlist self-checking analysis model, a water meter self-checking analysis model and a gas meter self-checking analysis model;
the model parameter extraction unit is used for extracting model parameters of the ammeter self-checking analysis model, the hotlist self-checking analysis model, the water meter self-checking analysis model and the gas meter self-checking analysis model to obtain ammeter analysis model parameters, hotlist analysis model parameters, water meter analysis model parameters and gas meter analysis model parameters;
The multi-meter combined self-checking model construction unit is used for constructing the multi-meter combined self-checking model based on the ammeter analysis model parameter, the hotlist analysis model parameter, the water meter analysis model parameter and the gas meter analysis model parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211437692.7A CN115798184B (en) | 2022-11-17 | 2022-11-17 | Multi-module coordination-based multi-table joint self-checking method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211437692.7A CN115798184B (en) | 2022-11-17 | 2022-11-17 | Multi-module coordination-based multi-table joint self-checking method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115798184A CN115798184A (en) | 2023-03-14 |
| CN115798184B true CN115798184B (en) | 2024-05-07 |
Family
ID=85438366
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211437692.7A Active CN115798184B (en) | 2022-11-17 | 2022-11-17 | Multi-module coordination-based multi-table joint self-checking method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115798184B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107248271A (en) * | 2017-05-23 | 2017-10-13 | 国网湖南省电力公司 | Many master station acquisition systems of multiple-in-one |
| KR101896015B1 (en) * | 2018-01-25 | 2018-09-06 | (주)베스트인포텍 | Ai type remote meter reading system |
| CN109617628A (en) * | 2018-12-07 | 2019-04-12 | 国网山东省电力公司电力科学研究院 | A kind of multiple-in-one acquisition equipment multifunctional detecting device and method |
| CN208952991U (en) * | 2018-08-14 | 2019-06-07 | 国网辽宁省电力有限公司辽阳供电公司 | A kind of multiple-in-one acquisition terminal comprehensive detection device |
| CN114298863A (en) * | 2022-03-11 | 2022-04-08 | 浙江万胜智能科技股份有限公司 | Data acquisition method and system of intelligent meter reading terminal |
| CN114331761A (en) * | 2022-03-15 | 2022-04-12 | 浙江万胜智能科技股份有限公司 | Equipment parameter analysis and adjustment method and system for special transformer acquisition terminal |
| CN114418138A (en) * | 2021-12-06 | 2022-04-29 | 南通联拓信息科技有限公司 | Multi-device combined self-checking intelligent power grid operation and maintenance method and system |
-
2022
- 2022-11-17 CN CN202211437692.7A patent/CN115798184B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107248271A (en) * | 2017-05-23 | 2017-10-13 | 国网湖南省电力公司 | Many master station acquisition systems of multiple-in-one |
| KR101896015B1 (en) * | 2018-01-25 | 2018-09-06 | (주)베스트인포텍 | Ai type remote meter reading system |
| CN208952991U (en) * | 2018-08-14 | 2019-06-07 | 国网辽宁省电力有限公司辽阳供电公司 | A kind of multiple-in-one acquisition terminal comprehensive detection device |
| CN109617628A (en) * | 2018-12-07 | 2019-04-12 | 国网山东省电力公司电力科学研究院 | A kind of multiple-in-one acquisition equipment multifunctional detecting device and method |
| CN114418138A (en) * | 2021-12-06 | 2022-04-29 | 南通联拓信息科技有限公司 | Multi-device combined self-checking intelligent power grid operation and maintenance method and system |
| CN114298863A (en) * | 2022-03-11 | 2022-04-08 | 浙江万胜智能科技股份有限公司 | Data acquisition method and system of intelligent meter reading terminal |
| CN114331761A (en) * | 2022-03-15 | 2022-04-12 | 浙江万胜智能科技股份有限公司 | Equipment parameter analysis and adjustment method and system for special transformer acquisition terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115798184A (en) | 2023-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104794206B (en) | A kind of substation data QA system and method | |
| CN115170000B (en) | Remote monitoring method and system based on electric energy meter communication module | |
| CN110739686B (en) | Method and system for managing line loss of transformer area based on total table anomaly analysis | |
| CN115166619A (en) | Intelligent electric energy meter operation error monitoring system | |
| CN113032454A (en) | Interactive user power consumption abnormity monitoring and early warning management cloud platform based on cloud computing | |
| CN109767054A (en) | Efficiency cloud appraisal procedure and edge efficiency gateway based on deep neural network algorithm | |
| CN113111596B (en) | Carbon peak-reaching real-time visual measuring and calculating method based on electric brain center | |
| CN107589391B (en) | Method, device and system for detecting integral error of electric energy metering device | |
| CN103103570B (en) | Based on the aluminium cell condition diagnostic method of pivot similarity measure | |
| CN107067100A (en) | Wind power anomalous data identification method and device for identifying | |
| CN114004296A (en) | Method and system for reversely extracting monitoring points based on power load characteristics | |
| CN111598165A (en) | Density clustering outlier detection method based on extreme learning machine | |
| CN115293257A (en) | Detection method and system for abnormal electricity utilization user | |
| CN115617784A (en) | Data processing system and processing method for informationized power distribution | |
| CN114928168A (en) | Offshore platform unmanned data edge computing device | |
| CN115798184B (en) | Multi-module coordination-based multi-table joint self-checking method and system | |
| CN113985098A (en) | Method for improving electricity larceny prevention analysis accuracy based on real-time metering | |
| CN116154968A (en) | Power parameter monitoring system based on IEC104 protocol sensor | |
| CN117092390A (en) | Power grid electricity larceny monitoring and positioning method | |
| CN116247668A (en) | Power distribution network operation mode identification method based on measurement big data analysis | |
| CN114779154A (en) | Intelligent ammeter data time scale calibration method and device based on temporal analysis | |
| CN113640732A (en) | Electric energy meter metering accuracy estimation system and method based on Pareto distribution | |
| CN117249036B (en) | Pumped storage system, hydroelectric generating set state evaluation method and device | |
| CN117291317B (en) | AEM-based intelligent power monitoring and optimizing system | |
| CN117371726B (en) | Energy storage information substation state sensing and performance 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 | ||
| CB02 | Change of applicant information |
Address after: No. 109, Yongchang Road, Shifeng Street, Tiantai County, Taizhou City, Zhejiang Province 317200 Applicant after: ZHEJIANG WELLSUN INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: 317200 15 Xingye East Third Street, Fuxi street, Tiantai County, Taizhou, Zhejiang Applicant before: ZHEJIANG WELLSUN INTELLIGENT TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |