Metering production scheduling-based electric energy meter data interaction and management method and system

Abstract

The application discloses a meter data interaction and management method and system based on metering production scheduling, relates to the technical field of intelligent power metering, and comprises appearance inspection, electrical test and function check on the electric energy meter, real-time collection of detection data of the electric energy meter, analysis of the detection data by using edge computing, feature extraction by a deep learning model according to an analysis result, identification of a fault mode and a trend, early warning according to a fault prediction result, recording of a fault log, classification of abnormal conditions, isolation of a fault device, training of a detection model, evaluation of detection efficiency, a fault rate and equipment utilization, generation of optimization suggestions according to an analysis result, and adjustment of detection equipment parameters. The application integrates edge computing, a deep learning model and real-time data preprocessing, realizes all-round management of appearance inspection, electrical test and function check on the electric energy meter, and provides strong data support for power dispatching management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent power metering, in particular to an electric energy meter data interaction and management method and system based on metering production scheduling. BACKGROUND

[0002] With the gradual advancement of global smart grid construction, the technology development of electric energy meters has entered a stage of rapid evolution. Traditional electric energy meters mainly rely on mechanical principles for metering, which are subject to many limitations in accuracy and efficiency. In recent years, the widespread application of electronic electric energy meters has made significant improvements in hardware and software, enabling a qualitative leap in data acquisition and communication capabilities.

[0003] Modern electric energy meters not only can monitor power usage in real time, but also have remote communication functions, enabling data to be quickly and accurately transmitted to the backend management system. This makes electric energy meters play an increasingly important role in power company dispatching management, load forecasting, and fault elimination. However, despite the gradual development of existing electric energy meters towards intelligence and automation, there are still some shortcomings in fault detection and data management. For example, the current fault detection method often relies on simple threshold setting, which cannot effectively handle comprehensive analysis of multi-dimensional data, resulting in high delay and false alarm rate of fault identification. In addition, many systems lack intelligent learning and adaptive capabilities, making it difficult to capture gradually changing states. This makes detection and response capabilities insufficient when facing complex faults and emergencies. SUMMARY

[0004] In view of the above existing problems, the present application provides an electric energy meter data interaction and management method and system based on metering production scheduling, to solve the problems of high delay and false alarm rate of fault identification, and insufficient detection and response capabilities in the prior art.

[0005] To solve the above technical problems, an electric energy meter data interaction and management method based on metering production scheduling is proposed, which includes,

[0006] The electric energy meter is subjected to appearance inspection, electrical test and function check, real-time acquisition of detection data of the electric energy meter, and analysis of the detection data by edge computing. According to the analysis result, feature extraction is performed by a deep learning model to identify fault patterns and trends, and pre-warning is performed according to the fault prediction result, and fault logs are recorded. Abnormal conditions are classified, and faulty equipment is isolated. The detection model is trained to evaluate detection efficiency, fault rate and equipment utilization rate, and optimization suggestions are generated according to the analysis result to adjust the detection equipment parameters.

[0007] As a preferred scheme of the electric energy meter data interaction and management method based on metering production scheduling, the detection data of the electric energy meter is collected, which includes appearance inspection, electrical test and function check of the electric energy meter, and the detection data of the electric energy meter is collected in real time.

[0008] The appearance inspection includes checking the integrity of the shell, the definition of the display screen and the integrity of the identification information; the electrical test includes voltage test, current test and voltage resistance test of the voltage meter; and the function check includes reverse metering test, communication function test and fault alarm function test of the electric energy meter.

[0009] As a preferred scheme of the electric energy meter data interaction and management method based on metering production scheduling, the edge computing includes real-time collection of sensor and test data, and denoising, normalization and abnormal value detection of the detection data by using edge computing.

[0010] The collected data includes current, voltage, power, power factor, function state, temperature and historical detection data of the electric energy meter.

[0011] As a preferred scheme of the electric energy meter data interaction and management method based on metering production scheduling, the identification of the failure mode and trend includes feature extraction by a deep learning model according to the analysis result, setting of an abnormal detection threshold, abnormal detection, grading of the failure when it is determined to be a failure, and matching of measures.

[0012] The abnormal threshold is set as H th , when HI th , it is determined that the electric energy meter detection data is abnormal, and failure detection is performed.

[0013] As a preferred scheme of the electric energy meter data interaction and management method based on metering production scheduling, the failure detection includes failure judgment and grading of the failure when the electric energy meter data is detected to be abnormal, and matching of measures.

[0014] The failure judgment formula is:

[0015] F score = w1·I dev + w2·V dev + w3·PF dev + w4·T dev

[0016] Wherein, F score is the failure score, I dev is the current deviation, V dev is the voltage deviation, PF dev is the power factor deviation, and Tdev w1 is the current weight, w2 is the voltage weight, w3 is the power factor weight, and w4 is the temperature weight.

[0017] The grading of the fault includes setting a mild fault threshold value of 2, a moderate fault threshold value of 4, and a severe fault threshold value of 6, when F score <2, the fault is in a normal range, a state record is made, and the function of the electric energy meter is checked regularly, when 2 score <4, the electric energy meter is determined to be in a mild fault state, the electric energy meter can normally meter, but has an accuracy error, needs to be adjusted, and is regularly checked, when 4 score <6, the electric energy meter is determined to be in a moderate fault state, parts of the electric energy meter need to be replaced, a fault report is generated, and a technical personnel is arranged to perform on-site maintenance, and when F score ≥6, the electric energy meter is determined to be in a severe fault state, indicating that the electric energy meter is completely inoperable and cannot normally meter, an alarm is immediately sent out, and a comprehensive check and fault elimination are performed on the fault.

[0018] As a preferred scheme of the electric energy meter data interaction and management method based on metering production scheduling, wherein: the training of the detection model includes pre-processing the historical detection data of the electric energy meter as a training set and a test set, and performing feature extraction, selecting a long short-term memory network to process time series data and high-dimensional features according to data characteristics and analysis targets, and defining a loss function to measure differences.

[0019] The detection efficiency formula is:

[0020]

[0021] Wherein, DE is the detection efficiency, D t is the number of successfully detected electric energy meters, C d is a detection complexity adjustment factor, T t is the total detection time, T d is the fault detection time, T wr is the sum of the waiting time and the repeated detection time.

[0022] The fault rate formula is:

[0023]

[0024] Wherein, FR is the fault rate, F n is the number of faults found in the detection period, R d is a fault severity adjustment factor, T s is the total number of electric energy meters detected, C r is a usage response degree factor.

[0025] The device utilization rate formula is:

[0026]

[0027] Wherein, UR is the equipment utilization, U a is the actual running time, F u is the fault impact adjustment factor, S u is the planned maintenance time impact, T s is the total available time, T m is the maintenance time total, C u is the user demand fluctuation adjustment factor.

[0028] As a preferred scheme of the meter data interaction and management method based on metering production scheduling provided by the application, the generating optimization suggestions comprises setting detection efficiency, fault rate and equipment utilization threshold, generating optimization suggestions according to analysis results, and adjusting detection equipment parameters.

[0029] The detection efficiency threshold is set to 95%, the fault rate threshold is set to 2%, and the equipment utilization threshold is set to 80%. When DE<95%, FR≥2% and UR<80%, it is determined that the detection system has defects, and the defect reasons are analyzed. The training frequency and the automatic detection steps are increased, the equipment is regularly maintained and the vulnerable parts are replaced, the intelligent scheduling is performed, the equipment parameters are adjusted, the detection standards and processes are modified, and the detection equipment is optimized.

[0030] Another object of the application is to provide a meter data interaction and management system based on metering production scheduling. The application significantly improves work efficiency and reduces manual operation by integrating automated detection, real-time monitoring and data analysis. The system can identify the fault mode of the meter in advance and trigger an intelligent alarm mechanism to achieve rapid response and fault handling with the help of a deep learning model. In addition, the accumulated historical detection data provide a solid foundation for decision support, optimize resource allocation and operational efficiency. Through continuous monitoring, users can effectively manage power loss, control maintenance costs and extend the service life of equipment.

[0031] As a preferred scheme of the meter data interaction and management system based on metering production scheduling provided by the application, it is characterized by comprising a detection and data acquisition module, a data preprocessing module, a fault mode identification and early warning module, a detection model training and evaluation module, and a parameter optimization module.

[0032] The detection and data acquisition module is used for comprehensive appearance inspection, electrical test and function check of the meter, and real-time acquisition of detection data.

[0033] The data preprocessing module is used for processing the real-time acquired data by using edge computing technology.

[0034] The fault mode recognition and early warning module is used for extracting important features of historical data by using a deep learning algorithm, establishing a fault indication model, setting an anomaly detection threshold, judging the state of the electric energy meter by calculating an anomaly index, classifying faults according to the anomaly detection result, and triggering a warning mechanism.

[0035] The detection model training and evaluation module is used for using preprocessed historical detection data as a training set, applying a deep learning model to process time series data, optimizing the detection model by evaluating the detection efficiency and fault rate indicators.

[0036] The parameter optimization module is used for generating optimization suggestions according to real-time data analysis results and model evaluation, improving detection efficiency, and managing equipment.

[0037] A computer device includes a memory and a processor, the memory stores a computer program, characterized in that the processor executes the computer program to realize the steps of the method for electric energy meter data interaction and management based on metering production scheduling.

[0038] A computer readable storage medium stores a computer program, characterized in that the computer program is executed by a processor to realize the steps of the method for electric energy meter data interaction and management based on metering production scheduling.

[0039] The beneficial effects of the present application: the present application integrates edge computing, deep learning model and real-time data preprocessing, realizes the all-round management of appearance inspection, electrical test and function check of electric energy meter; by collecting detection data of multiple sensors in real time, using deep learning for fault mode recognition, so that early warning can be realized before fault occurs, and the efficiency of fault detection is significantly improved; in addition, by recording fault logs and classifying abnormal conditions, the maintenance and repair process becomes more systematic and intelligent. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings, wherein:

[0041] Figure 1 The overall flowchart of the electric energy meter data interaction and management method based on metering production scheduling provided by an embodiment of the present application.

[0042] Figure 2The system scheme flow chart of the electric energy meter data interaction and management system based on metering production scheduling provided by an embodiment of the present application is shown. DETAILED DESCRIPTION

[0043] In order to make the above objectives, features and advantages of the present application more apparent, specific embodiments of the present application are described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work should fall within the protection scope of the present application.

[0044] In the following description, a large number of specific details are set forth in order to facilitate a thorough understanding of the present application. However, the present application can be implemented in other different manners than those described, and those skilled in the art can make similar generalizations without departing from the spirit and scope of the present application. Therefore, the present application is not limited to the specific embodiments disclosed below.

[0045] Secondly, the term "one embodiment" or "an embodiment" as used herein means that a specific feature, structure or characteristic described can be included in at least one implementation of the present application. The term "in one embodiment" appearing in different places in the specification does not mean the same embodiment, nor does it mean that the embodiments are mutually exclusive or alternative to each other.

[0046] The present application is described in detail in conjunction with the schematic diagram. In the detailed description of the embodiments of the present application, the cross-sectional view of the device structure is locally enlarged without the general proportion for the convenience of description, and the schematic diagram is only an example, which should not limit the scope of protection of the present application. In addition, three-dimensional spatial dimensions including length, width and depth should be included in actual manufacture.

[0047] Meanwhile, in the description of the present application, it should be noted that the terms "upper, lower, inner and outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first, second or third" are only for the purpose of description, and cannot be understood as indicating or implying relative importance.

[0048] In the present application, unless otherwise explicitly specified and limited, the terms "mounting, connection, connection" should be understood broadly, for example: it can be fixed connection, detachable connection or integral connection; it can also be mechanical connection, electrical connection or direct connection, it can also be indirectly connected through an intermediate medium, or it can be the communication between two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0049] Embodiment 1, reference Figure 1 As a first embodiment of the present application, the embodiment provides an electricity meter data interaction and management method based on metering production scheduling, comprising:

[0050] S1: appearance inspection, electrical test and function check are performed on the electricity meter, detection data of the electricity meter is collected in real time, and the detection data is analyzed by using edge computing.

[0051] The collection of the detection data of the electricity meter comprises appearance inspection, electrical test and function check on the electricity meter, and real-time collection of the detection data of the electricity meter.

[0052] The appearance inspection comprises checking the integrity of the shell, the definition of the display screen and the integrity of the identification information; the electrical test comprises voltage test, current test and voltage resistance test on the voltage meter; and the function check comprises reverse metering test, communication function test and fault alarm function test on the electricity meter.

[0053] It should be noted that the edge computing comprises real-time collection of sensor and test data, and denoising, normalization and outlier detection of the detection data by using edge computing.

[0054] The collected data comprises current, voltage, power, power factor, function state, temperature and historical detection data of the electricity meter.

[0055] The denoising comprises calculating the sliding average value in the data window by using the mean filter, and the formula is:

[0056]

[0057] Wherein, N is the window size, x(t) is the original data, Z is the filtered data, and i is the variable index.

[0058] The normalization formula is:

[0059]

[0060] Wherein, x is the original data, x' is the normalized data, min(X) is the minimum value of the data set, and max(X) is the maximum value of the data set.

[0061] The outlier detection formula is:

[0062]

[0063] Wherein, A is the standard score, y is the new measurement value, μ is the mean value of the data set, σ is the standard deviation, when |Z|>3, it is determined that the data is abnormal and needs to be removed.

[0064] S2: According to the analysis result, and through the feature extraction of the deep learning model, the fault mode and trend are identified, the fault prediction result is warned, the fault log is recorded, the abnormal situation is classified, and the fault equipment is isolated.

[0065] Further, the identification of the fault mode and trend includes setting an abnormality detection threshold according to the analysis result and through the feature extraction of the deep learning model, and performing abnormality detection, when it is determined that there is a fault, classifying the fault and matching measures.

[0066] The abnormality detection formula is represented as:

[0067]

[0068] wherein HI is an abnormality index, m is the total number of features, Y j is the measured value of the jth feature, μ j is the historical mean, σ j is the historical standard deviation, and j is the variable index.

[0069] The abnormality threshold is set as H th , when HI < H th , it is determined that the electric energy meter detection data is abnormal, and fault detection is performed.

[0070] Further, the fault detection includes, when the electric energy meter data is detected to be abnormal, fault judgment is performed, the fault is classified, and measures are matched.

[0071] The fault judgment formula is:

[0072] F score = w1·I dev + w2·V dev + w3·PF dev + w4·T dev

[0073] wherein F score is a fault score, I dev is a current deviation, V dev is a voltage deviation, PF dev is a power factor deviation, T dev is a temperature deviation, w1 is a current weight, w2 is a voltage weight, w3 is a power factor weight, and w4 is a temperature weight.

[0074] The fault classification includes setting a mild fault threshold of 2, a moderate fault threshold of 4, and a severe fault threshold of 6, when F score < 2, the fault is in the normal range, the state is recorded, and the electric energy meter function is checked regularly, when 2 ≤ Fscore <4, the electric energy meter is determined to be a light fault, the electric energy meter can normally meter, but there is an accuracy error, adjustment is needed, and periodic detection is needed, when 4 score <6, the electric energy meter is determined to be a moderate fault, the electric energy meter needs to be replaced, a fault report is generated, and a technical personnel is arranged to carry out on-site maintenance, when F score ≥6, the electric energy meter is determined to be a severe fault, indicating that the electric energy meter is completely disabled and cannot normally meter, an alarm is immediately issued, and a comprehensive check and fault elimination is carried out.

[0075] S3: training the detection model, evaluating the detection efficiency, the fault rate and the device utilization rate, generating optimization suggestions according to the analysis results, and adjusting the detection device parameters.

[0076] Further, the training of the detection model includes pre-processing the electric energy meter historical detection data as a training set and a test set, and performing feature extraction, selecting a long short-term memory network to process time series data and high-dimensional features according to data characteristics and analysis targets, and defining a loss function to measure differences.

[0077] The detection efficiency formula is:

[0078]

[0079] Wherein, DE is the detection efficiency, D t is the number of successfully detected electric energy meters, C d is a detection complexity adjustment factor, T t is the total detection time, T d is the fault detection time, T wr is the sum of the waiting time and the repeated detection time.

[0080] The fault rate formula is:

[0081]

[0082] Wherein, FR is the fault rate, F n is the number of faults found in the detection period, R d is a fault severity adjustment factor, T s is the total number of detected electric energy meters, C r is a usage response degree factor.

[0083] The device utilization rate formula is:

[0084]

[0085] Wherein, UR is the device utilization rate, U a is the actual running time, F u is a fault impact adjustment factor, Su T is the planned maintenance time impact, s T is the total available time, m C is the sum of maintenance times, u is the user demand fluctuation adjustment factor.

[0086] Further, the generating optimization suggestions comprises setting detection efficiency, failure rate and equipment utilization rate thresholds, generating optimization suggestions according to the analysis results, and adjusting detection equipment parameters.

[0087] The detection efficiency threshold is set to 95%, the failure rate threshold is set to 2%, and the equipment utilization rate threshold is set to 80%. When DE<95%, FR≥2% and UR<80%, it is determined that the detection system has defects, and the defect reasons are analyzed. Increase the training frequency and the automatic detection step, regularly maintain the equipment and replace the vulnerable parts, and intelligently schedule, adjust the equipment parameters, modify the detection standards and processes, and optimize the detection equipment.

[0088] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application, which should be covered by the scope of the claims of the present application.

[0089] Embodiment 2, refer to Figure 2 The second embodiment of the present application provides an electric energy meter data interaction and management system based on metering production scheduling, which comprises a detection and data acquisition module 100, a data preprocessing module 200, a fault mode identification and early warning module 300, a detection model training and evaluation module 400 and a parameter optimization module 500.

[0090] The detection and data acquisition module 100 is used for comprehensive appearance inspection, electrical test and function test of the electric energy meter, and real-time acquisition of detection data.

[0091] The data preprocessing module 200 is used for processing the real-time collected data by using edge computing technology.

[0092] The fault mode identification and early warning module 300 is used for extracting important features of historical data by using deep learning algorithm, establishing fault indication model, setting abnormal detection threshold, judging the state of electric energy meter by calculating abnormal index, classifying faults according to abnormal detection results, and triggering early warning mechanism.

[0093] The detection model training and evaluation module 400 is configured to use the preprocessed historical detection data as a training set, apply a deep learning model to process time series data, and optimize the detection model by evaluating the detection efficiency and failure rate indicators.

[0094] The parameter optimization module 500 is configured to generate optimization suggestions according to real-time data analysis results and model evaluation, improve detection efficiency, and perform equipment management.

[0095] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and they should be covered in the scope of the claims of the present application.

[0096] Embodiment 3, the third embodiment of the present application, is different from the first two embodiments in that:

[0097] If the functions are realized in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts that essentially contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0098] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered a list of executable instructions for implementing logical functions, and can be specifically embodied in any computer-readable medium for use by an instruction execution system, device or apparatus, such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions, or in conjunction with these instructions execution system, device or apparatus. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transport programs for use by an instruction execution system, device or apparatus or in conjunction with these instruction execution system, device or apparatus.

[0099] More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection (electronic) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can also be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via an optical scanner, then compiled, interpreted, or otherwise processed, and stored in a computer memory in a form that is then employable by a computer. Examples of computer-readable media include but are not limited to prime and non-transitory computer-readable media. Non-transitory computer-readable media specifically include, but are not limited to, magnetic materials, optical media, and solid-state memories. Non- transitory computer-readable media do not include carrier waves.

[0100] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the embodiments described above, various steps or methods can be implemented, for example, by software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any forms of hardware, or combinations thereof, of the following can be employed: discrete logic circuitry having logic gates for implementing logic functions upon an application of data signals; application specific integrated circuits having appropriate combinational logic gates; programmable gate arrays (PGA), field programmable gate arrays (FPGA), and so forth.

Claims

1. A method for data interaction and management of electric energy meter based on metering production scheduling, characterized in that: Comprising, The appearance inspection, electrical test and function check of the electric energy meter are performed, the detection data of the electric energy meter is collected in real time, and the detection data is analyzed by using edge computing; According to the analysis result, and through the feature extraction of the deep learning model, the fault mode and trend are identified, the fault prediction result is warned, and the fault log is recorded, the abnormal condition is classified, and the fault equipment is isolated; The detection model is trained, the detection efficiency, fault rate and equipment utilization rate are evaluated, the optimization suggestion is generated according to the analysis result, and the detection equipment parameters are adjusted; The identification of the fault mode and trend includes, according to the analysis result, and through the feature extraction of the deep learning model, the abnormal detection threshold is set, and the abnormal detection is performed, when it is judged as a fault, the fault is graded, and the measures are matched; Set the abnormal threshold value as H th When HI < H th , determine that the electric energy meter detection data is abnormal, and perform fault detection; The fault detection includes, when the electric energy meter data is abnormal, the fault is judged, and the fault is graded, and the measures are matched; The fault judgment formula is: F score = w1 · I dev + w2 · V dev + w3 · PF dev + w4 · T dev where F score is a fault score, I dev is a current deviation, V dev is a voltage deviation, PF dev is a power factor deviation, T dev is a temperature deviation, wl is a current weight, w2 is a voltage weight, w3 is a power factor weight, and w4 is a temperature weight. The grading of the fault includes setting a mild fault threshold value of 2, a moderate fault threshold value of 4, and a severe fault threshold value of 6, when F score <2, the fault is normal, the state record is performed, and the function of the electric energy meter is checked periodically, when 2≤F score <4, the electric energy meter is determined to be a mild fault, the electric energy meter can normally meter, but has an accuracy error, needs to be adjusted, and is detected periodically, when 4≤F score <6, the electric energy meter is determined to be a moderate fault, electric energy meter parts need to be replaced, a fault report is generated, and a technical personnel is arranged to perform on-site maintenance, when F score ≥6, the electric energy meter is determined to be a severe fault, indicating that the electric energy meter is completely failed and cannot normally meter, an alarm is immediately sent out, a comprehensive check of the fault is performed, and the fault is eliminated.

2. The method for metering production scheduling based electric energy meter data interaction and management according to claim 1, characterized in that: The collection of the detection data of the electric energy meter includes, the appearance inspection, electrical test and function check of the electric energy meter are performed, and the detection data of the electric energy meter is collected in real time; The appearance inspection includes checking the integrity of the shell, the definition of the display screen and the integrity of the identification information; The electrical test includes voltage test, current test and voltage resistance test of the voltage meter; The function check includes reverse metering test, communication function test and fault alarm function test of the electric energy meter.

3. The method for metering production scheduling based electric energy meter data interaction and management according to claim 2, characterized in that: The edge computing includes, real-time collection of sensor and test data, and denoising, normalization and outlier detection of detection data by using edge computing; Among them, the collected data includes the current, voltage, power, power factor, function state, temperature and historical detection data of the electric energy meter.

4. The method for metering production scheduling based electric energy meter data interaction and management according to claim 3, characterized in that: The training of the detection model includes, the preprocessed electric energy meter historical detection data is used as the training set and the test set, and the feature extraction is performed, the long short-term memory network is selected to process time series data and high-dimensional features according to the data characteristics and analysis target, and the loss function is defined to measure the difference; The detection efficiency formula is: where DE is the detection efficiency, D t is the number of successfully detected power meters, C d is the detection complexity adjustment factor, T t is the total detection time, T d is the fault detection time, T wr is the sum of the waiting time and the repeated detection time; The fault rate formula is: where FR is the failure rate, F n is the number of failures found in the detection period, R d is the failure severity adjustment factor, T s is the total number of meters under detection, C r is the usage response level factor; The equipment utilization rate formula is: Where UR is the equipment utilization, U a is the actual run time, F u is the failure impact adjustment factor, S u is the planned maintenance time impact, T s is the total available time, T m is the maintenance time sum, C u is the user demand fluctuation adjustment factor.

5. The method for metering production scheduling based electric energy meter data interaction and management according to claim 4, characterized in that: The generation of the optimization suggestion includes, The detection efficiency, fault rate and equipment utilization rate threshold are set, the optimization suggestion is generated according to the analysis result, and the detection equipment parameters are adjusted; The detection efficiency threshold is set to 95%, the fault rate threshold is set to 2%, and the equipment utilization rate threshold is set to 80%, when DE<95%, FR≥2% and UR<80%, it is judged that the detection system has defects, the defect reasons are analyzed, the training frequency and automatic detection steps are increased, the equipment is regularly maintained and the vulnerable parts are replaced, intelligent scheduling is performed, the equipment parameters are adjusted, the detection standard and process are modified, and the detection equipment is optimized.

6. A system for data interaction and management of an electric energy meter based on metering production scheduling according to any one of claims 1 to 5, characterized in that: It includes a detection and data collection module, a data preprocessing module, a fault mode identification and warning module, a detection model training and evaluation module, and a parameter optimization module; The detection and data collection module is used for comprehensive appearance inspection, electrical test and function check of the electric energy meter, and real-time collection of detection data; The data preprocessing module is used for processing the real-time collected data by using edge computing technology; The fault mode identification and early warning module is configured to extract important features of historical data by using a deep learning algorithm, establish a fault indication model, set an abnormality detection threshold, judge the state of the electric energy meter by calculating an abnormality index, classify faults according to the abnormality detection result, and trigger an early warning mechanism. The detection model training and evaluation module is configured to use preprocessed historical detection data as a training set, apply a deep learning model to process time series data, evaluate detection efficiency and fault rate indicators, and optimize the detection model. The parameter optimization module is configured to generate optimization suggestions based on real-time data analysis results and model evaluation, improve detection efficiency, and perform device management. 7.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-6 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the electric energy meter data interaction and management method based on metering production scheduling in any one of claims 1 to 5.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the electric energy meter data interaction and management method based on metering production scheduling in any one of claims 1 to 5.

Images