Electric energy metering device working condition evaluation system and method based on cooperation of big data and cloud computing

Abstract

The invention discloses an electric energy metering device working condition evaluation system and method based on cooperation of big data and cloud computing, and the system comprises a data obtaining module which is used for obtaining multi-dimensional operation data of an electric energy metering device, and the multi-dimensional operation data comprises power consumption data, equipment operation state data and environment temperature and humidity data; the evaluation module is used for performing working condition evaluation on the multi-dimensional operation data based on the big data and cloud computing collaboration platform; and the output module is used for outputting the working condition evaluation result of the electric energy metering device. Management personnel are helped to find potential problems in time before equipment breaks down, and equipment outage and high maintenance cost are avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power system and automation technology, and in particular to an electric energy metering device working condition evaluation system and method based on big data and cloud computing. BACKGROUND

[0002] With the increasing demand for electricity, the role of electric energy metering devices in the power system is becoming increasingly important. Its health status is directly related to the economy, safety and stability of the power system. However, the traditional electric energy metering device mainly relies on periodic inspection and manual experience for maintenance and health assessment, which has many shortcomings. First, the periodicity of periodic inspection and the limitations of manual operation make it impossible to achieve real-time state monitoring of electric energy metering devices, and it is easy to miss early signs of potential failures or abnormal operation. Second, manual experience judgment is often difficult to accurately assess the health status of the equipment in complex fault conditions, resulting in low efficiency of equipment maintenance, and even potential risks to the safe operation of the power system.

[0003] In recent years, with the rapid development of big data and cloud computing technologies, more and more industries have begun to use these technologies for equipment health management and failure prediction. Big data technology can efficiently process and analyze the vast amount of data accumulated during the operation of electric energy metering devices, and cloud computing technology provides powerful computing support for data storage and processing. By applying big data and cloud computing to the health assessment of electric energy metering devices, real-time monitoring and accurate analysis of the equipment operating state can be achieved, thereby greatly improving the accuracy of equipment management and failure prediction.

[0004] However, existing electric energy metering device health assessment systems rely mainly on offline analysis and static models, lacking real-time monitoring and dynamic updating capabilities. In addition, traditional methods often fail to fully utilize the rich data accumulated during the actual operation of electric energy metering devices, making it difficult to form a comprehensive and accurate health assessment system. Therefore, the existing technology has obvious limitations in handling electric energy metering device working condition monitoring, fault diagnosis and health management, and cannot fully meet the needs of modern power systems for efficient and intelligent management. SUMMARY

[0005] The present application provides an electric energy metering device working condition evaluation system and method based on big data and cloud computing to solve the above problems in the prior art.

[0006] In order to achieve the above purpose, the present application provides the following technical solutions:

[0007] The electric energy metering device working condition evaluation system based on big data and cloud computing comprises:

[0008] The data acquisition module is configured to acquire multi-dimensional operation data of the electric energy metering device, the multi-dimensional operation data including power consumption data, equipment operation state data, and environmental temperature and humidity data.

[0009] The evaluation module is configured to evaluate the working condition of the electric energy metering device based on the big data and cloud computing collaborative platform.

[0010] The output module is configured to output the working condition evaluation result of the electric energy metering device.

[0011] The evaluation module includes:

[0012] The construction submodule is configured to construct the big data and cloud computing collaborative platform based on the basic attribute information of the electric energy metering device.

[0013] The working condition diagnosis submodule is configured to perform rapid analysis on the real-time multi-dimensional operation data and perform working condition diagnosis based on the big data and cloud computing collaborative platform.

[0014] The output module includes:

[0015] The analysis submodule is configured to quantitatively analyze the working condition evaluation result to obtain a working condition analysis index.

[0016] The first working condition analysis submodule is configured to provide a working condition analysis report to the user when the working condition analysis index is less than or equal to a preset threshold.

[0017] The second working condition analysis submodule is configured to generate a detailed fault warning report based on a data model and provide recommended maintenance suggestions for the user when the working condition analysis index is greater than the preset threshold.

[0018] The construction submodule includes:

[0019] The basic attribute information of the electric energy metering device is acquired.

[0020] The data processing template is generated based on the basic attribute information.

[0021] A plurality of historical multi-dimensional operation data samples are acquired.

[0022] Each historical operation data sample is processed in sequence based on the data processing template to obtain a processing result of each historical operation data sample.

[0023] The big data and cloud computing collaborative platform is constructed based on the historical operation data sample whose processing result meets a preset standard.

[0024] The data processing template is generated based on the basic attribute information, and includes:

[0025] The basic attribute information is subjected to feature extraction to obtain an attribute feature set.

[0026] Determine a processing rule corresponding to the attribute feature set from a preset knowledge base; the processing rule includes: a plurality of corresponding data mining rules and template generation rules;

[0027] Iterate through each data mining rule in turn, and at each iteration, extract a processing basis from the basic attribute information based on the iterated data mining rule;

[0028] Generate a sub-template according to the processing basis based on the template generation rule corresponding to the iterated data mining rule;

[0029] After iterating through each data mining rule, integrate the sub-templates generated at each iteration to obtain a data processing template.

[0030] The working condition diagnosis sub-module includes:

[0031] Compare the equipment running state data with the preset healthy working condition threshold interval, and if the equipment running state data exceeds the threshold interval, determine that it is an abnormal equipment node;

[0032] Obtain the multi-dimensional data time series curve of the abnormal equipment node, extract the dynamic correlation features of the power consumption data and the equipment running state data, calculate the correlation coefficient with the corresponding environmental temperature and humidity data, and determine the dominant abnormal factor;

[0033] Based on the correlation topology model, iterate through the associated equipment group of the abnormal equipment node, analyze the abnormal conduction path and the influence range according to the running coordination parameters, and determine the abnormal root equipment;

[0034] Call the historical fault database in the big data and cloud computing collaborative platform, use a deep learning model to perform fault pattern matching on the multi-dimensional running data of the abnormal root equipment, and generate a working condition diagnosis result and a confidence evaluation value.

[0035] After generating the working condition diagnosis result and the confidence evaluation value, the following includes:

[0036] If the confidence evaluation value is higher than a preset confidence threshold, generate an equipment shutdown maintenance instruction or a parameter optimization control instruction based on the fault pattern matching result;

[0037] If the confidence evaluation value is lower than the preset confidence threshold, trigger a dynamic re-inspection instruction:

[0038] Obtain the incremental change rate of the real-time running index of the abnormal root equipment, combine the predicted change trend of the environmental temperature and humidity data, and construct an equipment state degradation prediction model;

[0039] Based on the degradation prediction model, simulate the evolution path of the equipment running index under different control strategies, select the optimal control strategy, and generate an adaptive parameter adjustment instruction;

[0040] The regulation instruction is sent to the target device, and the running coordination parameter in the associated topology model is synchronously updated.

[0041] The detailed fault warning report is generated, including:

[0042] If the working condition of the electric energy metering device changes and the change trend conforms to the known abnormal mode, a warning prompt is pushed to the user, and a fault elimination scheme is automatically generated;

[0043] After the user confirms, the suggested execution of the fault elimination measure is automatically performed.

[0044] The electric energy metering device working condition evaluation method based on big data and cloud computing comprises:

[0045] S101: acquiring multi-dimensional running data of the electric energy metering device;

[0046] S102: based on a cloud computing platform, using big data analysis technology to perform real-time processing and working condition evaluation analysis on the multi-dimensional running data;

[0047] S103: outputting the working condition evaluation result of the electric energy metering device.

[0048] The S102 step comprises:

[0049] S1021: based on the basic attribute information of the electric energy metering device, a big data and cloud computing collaborative platform is constructed;

[0050] S1022: the real-time multi-dimensional running data is quickly analyzed, and the working condition is diagnosed based on the big data and cloud computing collaborative platform.

[0051] Compared with the prior art, the present application has the following advantages:

[0052] The electric energy metering device working condition evaluation system based on big data and cloud computing comprises: a data acquisition module for acquiring multi-dimensional running data of the electric energy metering device, the multi-dimensional running data comprising power consumption data, equipment running state data and environmental temperature and humidity data; an evaluation module for performing working condition evaluation on the multi-dimensional running data based on a big data and cloud computing collaborative platform; and an output module for outputting the working condition evaluation result of the electric energy metering device. This helps the management personnel to discover potential problems in time before the equipment fails, and avoids equipment downtime and high maintenance costs.

[0053] Other features and advantages of the present application will be described in the following description, and some will become apparent from the description, or will be understood by those skilled in the art from the description, or will be understood by those skilled in the art by practicing the present application.

[0054] The technical solutions of the present application will be further described in detail below with the aid of the drawings and examples. BRIEF DESCRIPTION OF DRAWINGS

[0055] The accompanying drawings are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and are used to explain the application, but are not intended to limit the application. In the drawings:

[0056] Figure 1 A structure diagram of the power metering device working condition evaluation system based on big data and cloud computing in the embodiment of the application;

[0057] Figure 2 A structure diagram of the evaluation module in the embodiment of the application;

[0058] Figure 3 A flowchart of the power metering device working condition evaluation system based on big data and cloud computing in the embodiment of the application. DETAILED DESCRIPTION

[0059] The preferred embodiments of the application are described below in conjunction with the accompanying drawings, and it should be understood that the preferred embodiments described herein are only used to explain and illustrate the application, and are not intended to limit the application.

[0060] The embodiment of the application provides a power metering device working condition evaluation system based on big data and cloud computing as shown in the figure, which comprises: Figure 1

[0061] A data acquisition module is configured to acquire multi-dimensional operation data of the power metering device, wherein the multi-dimensional operation data comprises power consumption data, equipment operation state data and environmental temperature and humidity data.

[0062] An evaluation module is configured to perform working condition evaluation on the multi-dimensional operation data based on a big data and cloud computing cooperation platform.

[0063] An output module is configured to output the working condition evaluation result of the power metering device.

[0064] The working principle of the above technical solution is as follows: the data acquisition module acquires multi-dimensional operation data of the power metering device in real time, including power consumption data (such as power, load distribution, etc.), equipment operation state data (such as voltage, current and other parameters) and environmental temperature and humidity data; the multi-dimensional data is transmitted to a cloud storage system through a special sensing network to form a real-time data stream of the power metering device. The working condition evaluation of the power metering device is processed based on an evaluation model constructed on the cloud computing platform, and the evaluation model is obtained by pre-training machine learning using a large amount of historical operation state data with labeled tags. The evaluation model evaluates the health condition of the power metering device in real time according to the real-time acquisition of the multi-dimensional operation data, and obtains the working condition evaluation result. The evaluation result includes equipment health score, potential fault warning and corresponding maintenance suggestions, etc.

[0065] ​The system can select a direct response mode or an optimized response mode. The direct response refers to immediately conveying the working condition evaluation result to the relevant operation and maintenance personnel or directly triggering a preset automated maintenance process. The equipment impact risk refers to the potential impact on the stability of the power grid and the accuracy of electricity metering due to the direct implementation of maintenance measures, for example, maintenance operations causing metering interruption, data anomalies, or affecting the normal operation of related power supply systems.

[0066] The risk index represents the severity of the equipment impact risk. When the risk index is lower than a preset threshold, the system executes a direct response strategy, guiding the operation and maintenance personnel to immediately perform maintenance operations according to the working condition evaluation result. When the risk index is higher than the threshold, the system starts an optimized response mechanism, generates an optimized maintenance plan by adjusting the maintenance time window, refining the maintenance steps, or adjusting the maintenance priority, etc., so as to minimize the impact on the normal operation of the electricity metering system while ensuring the health of the equipment.

[0067] The above technical solution has the following beneficial effects: based on real-time collected multi-dimensional operation data of the electricity metering device, through the cooperation of big data analysis and cloud computing technology, the working condition of the electricity metering device is accurately evaluated; at the same time, according to the equipment impact risk that may be caused by the evaluation result, the response strategy is intelligently decided to ensure the reliability and accuracy of the electricity metering system, effectively improve the operation efficiency of the electricity metering device, prolong the service life, and reduce the maintenance cost. When an abnormal working condition is found, the system can intelligently judge the impact degree of the maintenance operation, select the best response time and method, avoid unnecessary metering interruption or power grid fluctuation, and ensure the continuity and reliability of the electricity data.

[0068] In another embodiment, as shown in Figure 2 the evaluation module includes:

[0069] The construction submodule is configured to construct a big data and cloud computing collaborative platform based on the basic attribute information of the electricity metering device.

[0070] The working condition diagnosis submodule is configured to quickly analyze the real-time multi-dimensional operation data and diagnose the working condition based on the big data and cloud computing collaborative platform.

[0071] The working principle of the technical solution is that the construction submodule digitizes and integrates the static basic attribute information of the electric energy metering device, forms a standardized data structure, and constructs a big data and cloud computing collaborative platform. The platform uses a distributed storage architecture and uniformly manages heterogeneous data sources through a standardized protocol conversion interface. During construction, the system first parses the asset identification of various types of electric energy metering devices (such as smart meters and power distribution monitoring terminals) that are accessed, and then extracts their inherent parameters (such as model specifications, accuracy levels, and rated voltage ranges) to form a device profile base. The collaborative platform automatically allocates computing nodes based on data processing needs through a flexible computing resource scheduling mechanism, ensuring efficient operation even under peak load conditions. When evaluating and making decisions about working conditions, the system relies on pre-trained evaluation models (obtained by training on large historical metering device operating state data sets) to accurately assess the current state of the electric energy metering device. The evaluation results include key indicators such as device health index, expected service life, and potential risk level.

[0072] The working condition diagnosis submodule continuously collects real-time operating data streams of the electric energy metering device, including voltage fluctuation curves, current phase relationships, power factor changes, and internal temperature multi-dimensional parameters. The diagnosis engine uses a hybrid analysis mode combining stream computing and batch processing to monitor abnormal fluctuations in short time windows in real time, while periodically performing deep analysis tasks to assess long-term performance trends. When the system detects abnormal working conditions, it triggers a multi-level diagnosis process: it screens common failure modes through a fast rule engine, then calls specialized field models for detailed analysis, and finally forms a working condition diagnosis report.

[0073] The beneficial effects of the above technical solution are that through the collaborative operation of the construction and diagnosis core modules, intelligent management of the entire life cycle of the electric energy metering device is achieved. The standardized integration of basic attribute information provides a static reference benchmark for working condition evaluation, while the rapid analysis of real-time multi-dimensional operating data captures the dynamic characteristics of the device.

[0074] In another embodiment, the output module includes:

[0075] The analysis submodule is configured to quantitatively analyze the working condition evaluation results to obtain a working condition analysis index.

[0076] The first working condition analysis submodule is configured to provide a working condition analysis report to the user when the working condition analysis index is less than or equal to a preset threshold.

[0077] The second working condition analysis submodule is configured to generate a detailed fault warning report based on a data model and provide recommended maintenance suggestions to the user when the working condition analysis index is greater than the preset threshold.

[0078] The working principle of the technical solution is that the analysis sub-module converts the operation parameters (including insulation performance change rate, three-phase imbalance degree, and temperature and humidity environment index) of the electric energy metering device collected from the field into standardized working condition analysis indexes through multi-dimensional feature extraction technology, and then generates a working condition evaluation index value in the range of 0-100 based on the analytic hierarchy process by combining the basic attribute information library of the metering device (including device protection level, installation environment type, and use time parameters) with real-time monitoring data, thereby realizing quantitative operation of the device state.

[0079] The system automatically flows to the corresponding working condition analysis processing path according to the comparison result of the working condition analysis index and the preset threshold value. When the working condition analysis index is lower than or equal to the preset threshold value, it indicates that the device operating state is within an acceptable range, the first working condition analysis submodule is activated, and the system automatically generates a standardized working condition analysis report, including device health state score, performance trend chart, and routine maintenance recommendations.

[0080] When the working condition analysis index exceeds the preset threshold value, it indicates that the device has a high risk or has abnormal symptoms, the second working condition analysis submodule is triggered to start, the second working condition analysis submodule calls the analysis capability in the cloud platform, performs deep correlation analysis and fault evolution simulation based on the device historical operation library, and determines the potential fault root cause by combining the static data of manufacturing batch information, material characteristics, and historical maintenance records in the device basic attribute library with the real-time monitored dynamic operation parameters through fault tree analysis algorithm, thereby generating a detailed fault warning report including risk level, predicted development trend, maintenance priority, and specific implementation suggestions.

[0081] The beneficial effects of the above technical solution are that by establishing an analysis system for electric energy metering device working condition evaluation, accurate evaluation and early warning of the operating state of the power grid metering device are realized; according to the severity grading of the working condition analysis index, the efficiency of routine monitoring is ensured while the deep diagnosis and prediction ability of abnormal working conditions are emphasized, thereby effectively improving the operating reliability and life cycle management level of the electric energy metering device.

[0082] In another embodiment, the construction submodule includes:

[0083] Obtaining the basic attribute information of the electric energy metering device;

[0084] Generating a data processing template based on the basic attribute information;

[0085] Obtaining a plurality of historical multi-dimensional operation data samples;

[0086] Processing each historical operation data sample in turn based on the data processing template to obtain the processing result of each historical operation data sample;

[0087] Based on the historical operation data samples meeting the preset standards, a big data and cloud computing collaborative platform is constructed.

[0088] The working principle of the technical solution is as follows: the power asset management library is connected, and the intrinsic attribute parameter set of the electric energy metering device is extracted, including inherent characteristic elements such as equipment model specification identification, rated operating parameter range, precision level division, communication interface type, and spatial deployment position. Based on the extracted intrinsic attribute parameter set, the system automatically constructs a corresponding data processing framework template, which is configured for the data structure characteristics of different types of metering equipment. The system obtains the operation data samples generated by the electric energy metering device in multiple historical periods through the time series database, and the samples cover multidimensional information such as electrical parameter fluctuation curve, environmental influence factor, and communication state index. Using the data processing framework template generated in the early stage, the system standardizes and quality assesses each historical operation data sample, and selects the effective data set meeting the preset standards. Finally, the system constructs a comprehensive evaluation platform based on the big data analysis engine and the cloud computing resource pool.

[0089] A multi-level data processing architecture is adopted to ensure the accuracy and real-time performance of the electric energy metering device working condition evaluation. During the generation of the processing framework template, the system dynamically configures data parsing rules, abnormal value identification thresholds, and quality scoring algorithms according to the characteristic differences of different types of metering devices. For example, for a certain type of intelligent electric meter, the system will automatically adjust the effective data fluctuation tolerance according to the measurement accuracy level in its basic attributes; and for a load record type terminal, the system will focus on the stability index of its sampling period. During the processing of historical operation data, the system will intelligently identify and correct abnormal situations such as incomplete data, misplaced timestamps, or parameter mutations, to ensure that the data samples finally included in the analysis have sufficient representativeness and reliability.

[0090] The big data and cloud computing collaborative platform constructed by the system has self-adaptive resource scheduling capability. When facing the massive data generated by a large number of electric energy metering devices, the system can dynamically allocate computing resources to ensure the efficient execution of the evaluation process. The platform uses a distributed computing framework to process time series feature extraction, working condition mode identification, and other computationally intensive tasks, and uses cloud storage technology to realize long-term data storage and fast retrieval. By deeply mining the historical data samples meeting the quality standards, the system can establish a normal operation benchmark model of the electric energy metering device, and based on this model, it can perform real-time evaluation on the current operation state and timely detect potential abnormalities.

[0091] The beneficial effects of the above technical solutions are: by establishing the association mapping between the basic attributes of the electric energy metering device and the operation data, the precise evaluation of the equipment working condition is realized; by flexible configuration of the data processing template, the standardized processing of equipment data of different types and different manufacturers is ensured; based on the collaborative application of big data analysis technology and cloud computing resources, the system can support parallel evaluation of a large number of metering equipment, and provide comprehensive and reliable technical support for power metering asset management. The full-dimensional analysis from static attributes to dynamic operation data is realized, and the limitation of isolated evaluation in the traditional metering device management is broken.

[0092] In another embodiment, based on the basic attribute information, a data processing template is generated, including:

[0093] The basic attribute information is subjected to feature extraction to obtain an attribute feature set;

[0094] The processing rules corresponding to the attribute feature set are determined from a preset knowledge base; the processing rules include: a plurality of corresponding data mining rules and template generation rules;

[0095] Each data mining rule is traversed in turn, and at each traversal, the processing basis is extracted from the basic attribute information based on the traversed data mining rule;

[0096] Based on the template generation rule corresponding to the traversed data mining rule, a sub-template is generated according to the processing basis;

[0097] After the traversal of each data mining rule is completed, the sub-templates generated at each traversal are integrated to obtain a data processing template.

[0098] The working principle of the above technical solution is: the device basic attributes are subjected to structured analysis, and the attribute refers to the technical parameters and design features fixed at the factory of the device, for example, a three-phase cost control intelligent electric meter of DTSY1234 type, the basic attributes include metering chip model identification, communication protocol version information, mechanical structure protection level and other static parameters, these information and dynamic monitoring data such as voltage harmonic content or environmental vibration spectrum collected in real time during the operation of the device form essential difference.

[0099] The system extracts features from the basic attribute information, obtains an attribute feature set containing key information such as device type, installation time, and voltage level. The system then accesses the processing rules in the preset knowledge base, which are composed of multiple pairs of data mining rules and template generation rules, embodying the experience of domain experts. The system sequentially traverses each data mining rule, extracting specific processing basis from the basic attribute information each time, including the standard parameter interval corresponding to the device model. Based on the template generation rule corresponding to the current traversed rule, the system generates a sub-template for a specific attribute according to the extracted processing basis. After traversing all rules, the system integrates each sub-template to form a complete data processing template, which serves as the basic framework for subsequent working condition evaluation.

[0100] The above technical solution has the beneficial effects of improving the flexibility and expandability of the system through modular processing, and making the working condition evaluation of the electric energy metering device more accurate.

[0101] In another embodiment, the working condition diagnosis sub-module includes:

[0102] Comparing the device running state data with the preset health working condition threshold interval, if the device running state data exceeds the threshold interval, it is determined as an abnormal device node;

[0103] Obtaining the multi-dimensional data time series curve of the abnormal device node, extracting the dynamic correlation features of the power consumption data and the device running state data, calculating the correlation coefficient with the corresponding environmental temperature and humidity data, and determining the dominant abnormal factor;

[0104] Based on the correlation topology model, traversing the associated device group of the abnormal device node, analyzing the abnormal conduction path and the influence range according to the running coordination parameters, and determining the abnormal root device;

[0105] Calling the historical fault database in the big data and cloud computing collaborative platform, using a deep learning model to match the fault mode of the multi-dimensional running data of the abnormal root device, and generating a working condition diagnosis result and a confidence evaluation value.

[0106] The working principle of the above technical solution is that the system compares the collected equipment running state data with the pre-set health working condition threshold interval, and when the monitoring data exceeds the safe running range, the system marks the related equipment as an abnormal node. For the identified abnormal equipment, the system obtains the time sequence change curve of the multi-dimensional data, analyzes the dynamic correlation characteristics between the power consumption data and the running state data, calculates the correlation coefficient of these characteristics and the environmental temperature and humidity data, and determines the main factors causing the abnormality. The system iteratively analyzes the associated equipment group of the abnormal equipment node based on the pre-established correlation topology model, evaluates the conduction path and influence range of the abnormality through the running coordination parameters, and finally locks the root cause equipment. After determining the root cause equipment, the system calls the historical fault database in the big data and cloud computing collaborative platform, applies a deep learning model to the multi-dimensional running data of the root cause equipment for fault pattern matching, and generates specific working condition diagnosis results and corresponding confidence evaluation values.

[0107] The beneficial effects of the above technical solution are that the accuracy and intelligence of equipment fault detection are improved through multi-dimensional data analysis, and the efficiency and response speed of fault diagnosis are greatly improved through the cloud computing and big data collaborative platform.

[0108] In another embodiment, generating the working condition diagnosis result and the confidence evaluation value comprises:

[0109] If the confidence evaluation value is higher than the pre-set confidence threshold value, a device shutdown maintenance instruction or a parameter optimization control instruction is generated based on the fault pattern matching result;

[0110] If the confidence evaluation value is lower than the pre-set confidence threshold value, a dynamic re-inspection instruction is triggered:

[0111] The incremental change rate of the real-time running index of the abnormal root cause equipment is obtained, and a device state degradation prediction model is constructed in combination with the predicted change trend of the environmental temperature and humidity data;

[0112] Based on the degradation prediction model, the evolution path of the equipment running index under different control strategies is simulated, the optimal control strategy is selected, and an adaptive parameter adjustment instruction is generated;

[0113] The control instruction is sent to the target equipment, and the running coordination parameters in the correlation topology model are updated synchronously.

[0114] The working principle of the above technical solution is that: according to the confidence evaluation value of the working condition diagnosis result, a differentiated response strategy is implemented. When the confidence evaluation value is higher than the preset confidence threshold, it indicates that the system has high certainty in judging the fault, at this time the system directly generates device shutdown maintenance instructions or parameter optimization control instructions based on the fault mode matching result, to quickly respond to the confirmed abnormal situation. When the confidence evaluation value is lower than the preset confidence threshold, it indicates that the system has great uncertainty in judging the abnormality, at this time the dynamic re-inspection mechanism is triggered: the system first obtains the real-time running index increment change rate of the abnormal root device, and combines the predicted change trend of the environment temperature and humidity data to construct a prediction model reflecting the device state degradation process. Based on the degradation prediction model, the system simulates and analyzes the possible evolution path of the device running index under different control strategies, selects the control strategy that can make the device return to normal operating state and optimizes the resource consumption, and generates the corresponding adaptive parameter adjustment instruction.

[0115] The beneficial effects of the above technical solution are: the control instruction is then issued to the target device for execution, and the system synchronously updates the running coordination parameters in the associated topology model, ensuring the coordinated operation of the overall system.

[0116] In another embodiment, a detailed fault warning report is generated, including:

[0117] If the working condition of the electric energy metering device changes and the change trend conforms to the known abnormal mode, a warning prompt is pushed to the user, and a fault elimination scheme is automatically generated;

[0118] After the user confirms, the suggested execution of the fault elimination measures is automatically performed.

[0119] The working principle of the above technical solution is: when the working condition parameters of the electric energy metering device change, and the change trend conforms to the abnormal mode recorded in the system knowledge base, the system will push a warning prompt information to the user, reminding the possible impending fault condition. At the same time, the system generates a targeted fault elimination scheme based on the analysis of the current working condition state, combined with the processing experience of historical similar cases, including possible fault causes, impact range and detailed information of recommended handling measures. After receiving the warning information, the user can review the fault elimination scheme provided by the system and confirm the execution through the system interface. Once the user confirms, the system will provide specific execution suggestions for the fault elimination measures according to the preset process, guiding the maintenance personnel to efficiently complete the fault handling.

[0120] The beneficial effects of the above technical solution are: the man-machine cooperative warning processing mode not only fully utilizes the advantages of the system in big data analysis and fault prediction, but also retains the flexibility and adaptability of manual decision-making, improving the reliability and maintenance efficiency of the electric energy metering device.

[0121] In another embodiment, as shown in Figure 3 The power metering device working condition evaluation method cooperating with cloud computing and big data includes:

[0122] S101: Obtain multi-dimensional operation data of the power metering device.

[0123] S102: Based on the cloud computing platform, use big data analysis technology to perform real-time processing and working condition evaluation analysis on the multi-dimensional operation data.

[0124] S103: Output the working condition evaluation result of the power metering device.

[0125] The working principle of the above technical solution is as follows: real-time collection of multi-dimensional operation data of the power metering device, including power consumption data (such as power, load distribution, etc.), equipment operation state data (such as voltage, current, etc. Parameters) and environmental temperature and humidity data; the multi-dimensional data is transmitted to the cloud storage system through a special sensing network to form a real-time data stream of the power metering device.

[0126] The evaluation model constructed based on the cloud computing platform is processed, and the evaluation model is obtained by pre-training using a large amount of historical operation state data with labeled tags. The evaluation model evaluates the health condition of the power metering device in real time according to the real-time collected multi-dimensional operation data, and obtains the working condition evaluation result. The evaluation result includes device health score, potential fault warning and corresponding maintenance suggestion, etc.

[0127] The system can select a direct response or an optimized response mode. Direct response refers to immediately conveying the working condition evaluation result to the relevant operation and maintenance personnel or directly triggering the preset automatic maintenance process. The device impact risk refers to the potential impact on the stability of the power grid and the accuracy of the power metering caused by directly implementing maintenance measures, for example: maintenance operation causes metering interruption, data anomaly or affects the normal operation of the related power supply system, etc.

[0128] The risk index represents the severity of the device impact risk. When the risk index is lower than the preset threshold, the system executes the direct response strategy, and guides the operation and maintenance personnel to immediately perform maintenance operation according to the working condition evaluation result; when the risk index is higher than the threshold, the system starts the optimized response mechanism, generates an optimized maintenance scheme by adjusting the maintenance time window, refining the maintenance steps or adjusting the maintenance priority, so as to minimize the impact on the normal operation of the power metering system while ensuring the health of the device.

[0129] The beneficial effects of the above technical solution are: based on the real-time collected multi-dimensional operation data of the electric energy metering device, through the cooperation of big data analysis and cloud computing technology, the working condition of the electric energy metering device is accurately evaluated; at the same time, according to the equipment influence risk that the evaluation result may bring, the intelligent decision response strategy is ensured to ensure the reliability and accuracy of the electric energy metering system, effectively improve the operation efficiency of the electric energy metering device, prolong the service life, and reduce the maintenance cost. When an abnormal working condition is found, the system can intelligently judge the influence degree of the maintenance operation, select the best response opportunity and mode, avoid unnecessary metering interruption or power grid fluctuation, and ensure the continuity and reliability of the power consumption data.

[0130] In another embodiment, the S102 step includes:

[0131] S1021: based on the basic attribute information of the electric energy metering device, a big data and cloud computing collaborative platform is constructed;

[0132] S1022: the real-time multi-dimensional operation data is quickly analyzed, and the working condition is diagnosed based on the big data and cloud computing collaborative platform.

[0133] The working principle of the above technical solution is: the static basic attribute information of the electric energy metering device is digitized and integrated to form a standardized data structure, and a big data and cloud computing collaborative platform is constructed. The platform uses a distributed storage architecture to uniformly manage heterogeneous data sources through a standardized protocol conversion interface. During the construction process, the system first parses the asset identification of various types of electric energy metering devices (such as smart meters, power distribution monitoring terminals, etc.), and then extracts their inherent parameters (such as model specifications, accuracy levels, and rated voltage ranges) to form a device file base. The collaborative platform automatically allocates computing nodes according to data processing needs through a flexible computing resource scheduling mechanism to ensure efficient operation even under peak load conditions. When making working condition evaluation decisions, the system relies on pre-trained evaluation models (obtained by training a large-scale historical metering device operation state data set) to accurately evaluate the current electric energy metering device state. The evaluation results include device health index, expected service life, and potential risk level, and other key indicators.

[0134] The real-time operation data stream of the electric energy metering device is continuously collected, including voltage fluctuation curve, current phase relationship, power factor change, and multi-dimensional parameters of internal temperature. The diagnosis engine uses a hybrid analysis mode combining stream computing and batch processing to monitor abnormal fluctuations in a short time window in real time, while periodically performing deep analysis tasks to evaluate long-term performance trends. When the system detects an abnormal working condition, a multi-level diagnosis process is triggered: common failure modes are screened through a fast rule engine, and then a professional field model is called for detailed analysis, and finally a working condition diagnosis report is formed.

[0135] The above technical scheme has the beneficial effects that: through the cooperative operation of the two core modules of construction and diagnosis, the intelligent management of the whole life cycle of the electric energy metering device is realized. The standardized integration of the basic attribute information provides a static reference benchmark for the working condition evaluation, and the rapid analysis of the real-time multi-dimensional operation data captures the dynamic change characteristics of the equipment.

[0136] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application.

Claims

1. A big data and cloud computing-based operating condition evaluation system for electric energy metering devices, comprising: A data acquisition module is used to obtain multi-dimensional operating data of the electric energy metering device, the multi-dimensional operating data including power consumption data, equipment operating status data and ambient temperature and humidity data; Evaluation module, used to evaluate the working condition of multi-dimensional operating data based on the collaborative platform of big data and cloud computing; The output module is used to output the working condition evaluation results of the electric energy metering device.

2. The big data and cloud computing collaborative electric energy metering device operating condition evaluation system according to claim 1 is characterized in that: The evaluation modules include: Construct submodules for building a big data and cloud computing collaborative platform based on the basic attribute information of the electric energy metering device; The operating condition diagnosis submodule is used to quickly analyze real-time multi-dimensional operating data and perform operating condition diagnosis based on a collaborative platform of big data and cloud computing.

3. The big data and cloud computing collaborative electric energy metering device operating condition evaluation system according to claim 1 is characterized in that: Output modules include: The analytical submodule is used to quantitatively analyze the working condition evaluation results and obtain the working condition analysis index; The first operating condition analysis submodule is configured to provide an operating condition analysis report to the user when the operating condition analysis index is less than or equal to a preset threshold; The second operating condition analysis submodule is used to generate a detailed fault warning report based on the data model when the operating condition analysis index is greater than a preset threshold, and provide recommended maintenance suggestions to the user.

4. The big data and cloud computing collaborative electric energy metering device operating condition evaluation system according to claim 2 is characterized in that: The building blocks include: Obtain basic attribute information of electric energy metering devices; Generate data processing template based on basic attribute information; Obtain multiple historical multi-dimensional operating data samples; Based on the data processing template, each historical operation data sample is processed in sequence to obtain the processing results of each historical operation data sample; Based on historical operation data samples whose processing results meet the preset standards, a big data and cloud computing collaborative platform is built.

5. The big data and cloud computing collaborative electric energy metering device operating condition evaluation system according to claim 4 is characterized in that: Generate data processing templates based on basic attribute information, including: Extract features from basic attribute information to obtain attribute feature sets; Determine processing rules corresponding to attribute feature sets from a preset knowledge base; the processing rules include: multiple sets of corresponding data mining rules and template generation rules; Traverse each data mining rule in turn, and extract processing basis from basic attribute information based on the traversed data mining rule each time; Based on the template generation rules corresponding to the traversed data mining rules, a sub-template is generated according to the processing basis; After traversing each data mining rule, the sub-templates generated in each traversal are integrated to obtain a data processing template.

6. The big data and cloud computing collaborative electric energy metering device operating condition evaluation system according to claim 2, characterized in that: The operating condition diagnosis submodule includes: Compare the device operating status data with the preset healthy operating condition threshold range. If the device operating status data exceeds the threshold range, it is determined to be an abnormal device node; Obtain the multi-dimensional data time series change curve of abnormal device nodes, extract the dynamic correlation characteristics of power consumption data and equipment operation status data, calculate the correlation coefficient with the corresponding environmental temperature and humidity data, and determine the dominant abnormal factor; Based on the associated topology model, the system traverses the associated device groups of the abnormal device node, analyzes the abnormal transmission path and impact range according to the operation coordination parameters, and determines the root cause of the abnormality. The historical fault database in the big data and cloud computing collaborative platform is called, and a deep learning model is used to match the fault patterns of the multi-dimensional operating data of the abnormal root equipment to generate working condition diagnosis results and confidence assessment values.

7. The big data and cloud computing collaborative electric energy metering device operating condition evaluation system according to claim 6 is characterized in that: After generating the working condition diagnosis results and confidence assessment values, they include: If the confidence assessment value is higher than the preset confidence threshold, an equipment shutdown maintenance instruction or parameter optimization control instruction is generated based on the fault mode matching result; If the confidence assessment value is lower than the preset confidence threshold, a dynamic recheck instruction is triggered: Obtain the incremental change rate of the real-time operating indicators of the abnormal root device, combine it with the predicted change trend of the ambient temperature and humidity data, and build a device status degradation prediction model; Based on the degradation prediction model, the evolution path of equipment operating indicators under different control strategies is simulated, the optimal control strategy is selected, and adaptive parameter adjustment instructions are generated; The control instructions are sent to the target device, and the operation coordination parameters in the associated topology model are updated synchronously.

8. The big data and cloud computing collaborative electric energy metering device operating condition evaluation system according to claim 3 is characterized in that: Generate detailed fault warning reports, including: If the operating conditions of the energy metering device change and the trend of the change conforms to a known abnormal pattern, an early warning will be pushed to the user and a troubleshooting plan will be automatically generated; After user confirmation, the recommended troubleshooting measures are automatically executed.

9. A method for evaluating the working condition of an electric energy metering device based on the collaboration of big data and cloud computing, characterized in that: include: S101: Acquire multi-dimensional operating data of the electric energy metering device; S102: Based on the cloud computing platform, using big data analysis technology, real-time processing of multi-dimensional operation data and working condition evaluation and analysis are carried out; S103: Outputting the operating condition evaluation result of the electric energy metering device.

10. The method for evaluating the working condition of an electric energy metering device based on the collaboration of big data and cloud computing according to claim 9, characterized in that: Step S102 includes: S1021: Build a big data and cloud computing collaborative platform based on the basic attribute information of electric energy metering devices; S1022: Rapidly analyze real-time multi-dimensional operating data and perform operating condition diagnosis based on a collaborative platform of big data and cloud computing.

Images