Electric energy meter fault intelligent diagnosis method and device adopting Internet of Things data interaction

Abstract

The invention provides an intelligent electric energy meter fault diagnosis method and device adopting Internet of Things data interaction. The method comprises the following steps: determining a target electric energy meter in a target area, wherein a plurality of electric energy meters are arranged in the target area; collecting operation data of the target electric energy meter, wherein the operation data can be obtained based on the Internet of Things of the monitored electric energy meter; preprocessing the operation data to obtain operation characteristics of the target electric energy meter; and inputting the operation characteristics into a preset fault diagnosis model to obtain a fault diagnosis result corresponding to the target electric energy meter. According to the method provided by the invention, the target electric energy meter is determined in the target area, and the plurality of electric energy meter resources deployed in the area are used for contrastive analysis, so that fault causes are clearly distinguished.

Description

Technical Field

[0001] This application relates to the field of fault detection, and in particular to a method and device for intelligent fault diagnosis of electricity meters using Internet of Things (IoT) data interaction. Background Technology

[0002] With the widespread adoption of smart grids, electricity meters, as key metering terminals, have been upgraded from traditional mechanical meters to smart IoT-based meters. A large number of electricity meters are often deployed in target areas such as residential communities and industrial parks. Their operational status directly affects metering accuracy and power supply security. Therefore, efficient fault diagnosis of electricity meters in target areas has become a core requirement for smart grid operation and maintenance.

[0003] The current development of electricity meter fault diagnosis is from manual inspection to intelligent inspection: manual inspection requires maintenance personnel to obtain data on-site and make judgments based on experience, which makes it difficult to achieve large-scale real-time monitoring; after the application of Internet of Things technology, operating data can be collected remotely and simply filtered and statistically analyzed, and some can be initially evaluated using threshold models, but the level of intelligence is limited.

[0004] The existing technology has significant shortcomings: First, the data preprocessing is weak, simply filtering the data without mining related features, and the diagnostic basis is singular; second, the diagnostic model is not intelligent enough, relying on thresholds or simple statistics, making it difficult to deal with hidden and intermittent faults, and prone to missed or misdiagnosis; third, it lacks multi-meter collaborative diagnosis, cannot combine the status analysis of other meters in the area, has low diagnostic reliability, and is difficult to meet the high precision and high real-time requirements of smart grids. Summary of the Invention

[0005] This application provides a method and device for intelligent diagnosis of electricity meter faults using Internet of Things (IoT) data interaction, in order to solve the technical problems of existing technologies such as single diagnostic data, easy to miss or misdiagnose, and low diagnostic reliability.

[0006] In a first aspect, this application provides a method for intelligent fault diagnosis of electricity meters using Internet of Things (IoT) data interaction, including: A target electricity meter is identified within the target area, and multiple electricity meters are installed within the target area; Collect operational data from the target electricity meter, which can be obtained based on the Internet of Things (IoT) monitoring the electricity meter; The operating data is preprocessed to obtain the operating characteristics of the target energy meter; The operating characteristics are input into a pre-set fault diagnosis model to obtain the fault diagnosis results corresponding to the target energy meter.

[0007] Optionally, the collection of operational data from the target electricity meter includes: In response to fault diagnosis information, the electricity meter identifier of the target electricity meter is obtained based on the fault diagnosis information, and the electricity meter setting location corresponding to the electricity meter identifier is obtained. From multiple IoT device identifier groups, determine the target device identifier group corresponding to the location where the energy meter is installed; The IoT data corresponding to each device identifier in the target device identifier group are all used as the operating data of the target electricity meter.

[0008] Optionally, the operating data is preprocessed to obtain the operating characteristics of the target energy meter, including: Obtain several device identifiers corresponding to the operational data, wherein the device identifiers are the identifiers of the IoT devices included in the Internet of Things; Based on the aforementioned device identifiers, the target preprocessing method is determined; The operating data is processed based on the target preprocessing method to obtain the operating characteristics of the target electricity meter.

[0009] Optionally, the step of inputting the operating characteristics into a pre-set fault diagnosis model to obtain the fault diagnosis result corresponding to the target energy meter includes: The operational characteristics are grouped to obtain sub-features corresponding to each IoT device in the Internet of Things; For each IoT device, an input vector corresponding to the IoT device is obtained based on the sub-features and device identifier of the IoT device. The input vector is input into a pre-set fault diagnosis model to obtain the output result corresponding to the IoT device. The output result includes the operating status of the IoT device. Based on the aforementioned output results, the fault diagnosis results corresponding to the target electricity meter are obtained.

[0010] Optionally, the method further includes: Based on the historical operating status and historical sub-features of each IoT device, an initial diagnostic model is trained to obtain a new initial diagnostic model. This process continues until the new initial diagnostic model meets the preset false alarm requirements. The new initial diagnostic model is then used as a pre-set fault diagnosis model.

[0011] Optionally, after inputting the operating characteristics into a pre-set fault diagnosis model to obtain the fault diagnosis result corresponding to the target energy meter, the method further includes: Obtain the maintenance personnel information corresponding to the target electricity meter; Based on the maintenance personnel information and the fault diagnosis results corresponding to the target electricity meter, a fault warning message is generated. The fault warning message is used to notify the maintenance personnel corresponding to the maintenance personnel information that the target electricity meter has a fault.

[0012] Secondly, this application provides an intelligent fault diagnosis device for electricity meters that uses Internet of Things (IoT) data interaction, comprising: The determination module is used to determine the target electricity meter within the target area, wherein multiple electricity meters are installed within the target area; The acquisition module is used to collect the operating data of the target electricity meter, and the operating data can be acquired based on the Internet of Things for monitoring the electricity meter; The first processing module is used to preprocess the operating data to obtain the operating characteristics of the target energy meter; The second processing module is used to input the operating characteristics into a pre-set fault diagnosis model to obtain the fault diagnosis result corresponding to the target energy meter.

[0013] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the intelligent fault diagnosis method for electricity meters using Internet of Things data interaction as described in any of the first aspects.

[0014] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the intelligent fault diagnosis method for electricity meters using Internet of Things data interaction as described in any of the first aspects.

[0015] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the intelligent fault diagnosis method for electricity meters using Internet of Things data interaction as described in any of the first aspects.

[0016] This application provides an intelligent fault diagnosis method for electricity meters using IoT data interaction. Addressing the shortcomings of existing technologies, such as weak data preprocessing and limited diagnostic basis, the solution first collects operational data from the target electricity meter via IoT. Then, it performs professional preprocessing on the data. This process goes beyond simply filtering outliers; it deeply mines the underlying correlations in the data, such as the coordinated changes in voltage and current, and load fluctuations at different times. This effectively enriches the dimensions of operational characteristics, providing a more comprehensive and accurate analytical basis for subsequent fault diagnosis. It completely solves the problem of insufficient diagnostic support due to traditional technologies relying solely on simple data statistics. Furthermore, addressing the issues of insufficient intelligence and susceptibility to missed or misdiagnosed faults in existing diagnostic models, the solution inputs the preprocessed multi-dimensional operational characteristics into a pre-set fault diagnosis model. This model replaces traditional threshold judgments or simple statistical models, enabling accurate identification of various faults in electricity meters, including difficult-to-diagnose faults. By addressing latent faults (such as the slow decline in metering accuracy due to component aging), intermittent faults, and complex faults caused by multi-factor coupling, the solution significantly reduces the rate of missed diagnoses and false diagnoses, thus significantly improving the intelligence level of fault diagnosis. Simultaneously, addressing the lack of multi-meter collaborative diagnosis and low reliability in existing technologies, the solution first identifies the target electricity meter within the target area. Leveraging the resources of multiple electricity meters already deployed within the area, the operating status of the target electricity meter can be compared and analyzed with the operating data of other electricity meters in the same area. This clearly distinguishes the cause of the fault—whether it is due to hardware or software problems within the electricity meter itself, or abnormal power supply environment in the area (such as overall voltage instability or line interference). This further enhances the reliability of fault diagnosis results, ultimately fully meeting the core requirements of smart grids for high precision and real-time performance in electricity meter fault diagnosis, providing strong support for improving power system operation and maintenance efficiency and ensuring power supply stability. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] Figure 1 This application provides a flowchart illustrating an intelligent fault diagnosis method for electricity meters using Internet of Things (IoT) data interaction. Figure 2 A schematic diagram of the structure of an intelligent fault diagnosis device for electricity meters that uses Internet of Things data interaction is provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in this application.

[0019] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0020] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0021] The intelligent fault diagnosis method for electricity meters using IoT data interaction provided in this application can be applied to wireless or wired terminals. The wireless terminal can be a device that provides voice and / or other service data connectivity to users, a handheld device with wireless connectivity, or other processing devices connected to a wireless modem. The wireless terminal can communicate with one or more core network devices via a Radio Access Network (RAN). The wireless terminal can be a mobile terminal, such as a mobile phone (or "cellular" phone) or a computer with a mobile terminal, for example, a portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile device, which exchanges voice and / or data with the RAN. Furthermore, the wireless terminal can also be a Personal Communication Service (PCS) phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), or other similar devices. A wireless terminal can also be referred to as a system, subscriber unit, subscriber station, mobile station, mobile, remote station, remote terminal, access terminal, user terminal, user agent, user device, or user equipment; no specific terminology is used here. Optionally, the aforementioned terminal devices can also be smartwatches, tablets, or other similar devices.

[0022] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0023] like Figure 1 As shown, Figure 1 This application provides a flowchart illustrating an intelligent fault diagnosis method for electricity meters using IoT data interaction, as shown in the embodiments below. Figure 1 As shown, a smart fault diagnosis method for electricity meters using Internet of Things (IoT) data interaction may specifically include steps S201 to S204, wherein: S201. Determine the target electricity meter within the target area, wherein multiple electricity meters are installed within the target area.

[0024] First, target areas are divided based on the substation's power supply radius, administrative region, electricity consumption type, and communication network coverage. A unique electronic identification code is assigned, and regional archives are created in the operation and maintenance system to record information such as the total number and location of electricity meters for accurate correlation. Next, target electricity meters are screened within the defined areas. Basic attributes are extracted from the archives, and meters that have been in operation for more than 8 years or have experienced at least one data interruption in the past 3 months are included as candidates. Meters with voltage / current fluctuations exceeding the range are supplemented by real-time data. Then, correlation analysis is performed on the candidate meters, marking those with abnormal indicators higher than the average level of the same batch as high priority. High- and medium-priority meters are determined by ranking them according to fault risk. Finally, their "target monitoring" status is marked in the system, the archives are updated, and a list is generated and synchronized to the IoT terminal to ensure accurate implementation of subsequent work.

[0025] S202. Collect the operating data of the target electricity meter, wherein the operating data can be obtained based on the Internet of Things for monitoring the electricity meter.

[0026] When collecting operational data from target electricity meters, the target electricity meter list is first imported into the power IoT platform. Each meter's unique identifier (such as asset number) is bound to the IoT monitoring terminal to achieve targeted data collection. Simultaneously, the communication status of the target meter's built-in LoRa or NB-IoT IoT modules is checked, and repeaters are installed in areas with weak signals to ensure stable transmission links. Then, basic electrical parameters (voltage, current, active / reactive power), metering data (cumulative electricity consumption, real-time load), and status data (signal strength, module temperature, metering error warning) are collected at a frequency of 15 minutes per collection. A dual-mode approach of "active reporting + active recall" is adopted. Under normal conditions, the target meter actively transmits data every 15 minutes; if the terminal does not receive data within one hour, it automatically recalls and collects supplementary data. After receiving the data, the IoT terminal immediately verifies the format and range (e.g., voltage must be within 220V±10%), removes invalid data, marks abnormal data, and records the collection time and terminal number to form a timestamped raw dataset. This dataset is then synchronously uploaded to the power operation and maintenance management system for storage, laying the foundation for subsequent preprocessing.

[0027] S203. Preprocess the operating data to obtain the operating characteristics of the target energy meter.

[0028] When preprocessing the raw operating data of the target electricity meters, the data is first cleaned: missing data caused by transmission interruptions is filled in by interpolation (e.g., using the average voltage over 15 minutes before and after to fill in missing values), extreme abnormal values ​​exceeding the normal range are removed using the 3σ criterion (e.g., data where the current suddenly spikes to more than 3 times the rated value), and data with incorrect formatting is corrected (e.g., the timestamp format is standardized to "YYYY-MM-DDHH:MM:SS"). Then, feature extraction is performed: derived features are calculated from the cleaned data, including time-of-use features (e.g., the difference between daily peak and off-peak loads). The system extracts multidimensional features, including peak and valley load periods, correlation characteristics (such as the Pearson correlation coefficient between voltage and current, and the rate of change of active power and electricity consumption), and stability characteristics (such as the standard deviation of voltage fluctuations within 24 hours and the duration of continuous stable current operation). Finally, feature optimization is performed: the extracted multidimensional features are normalized (mapping feature values ​​to the [0,1] interval), and redundant features with variance less than 0.05 (such as the module temperature feature that has not fluctuated for a long time) are eliminated through variance analysis. Finally, the system obtains simplified operating features that can reflect the operating status of the electricity meter, which is ready for subsequent input into the fault diagnosis model.

[0029] S204. Input the operating characteristics into a pre-set fault diagnosis model to obtain the fault diagnosis result corresponding to the target energy meter.

[0030] When inputting the pre-processed operational features into the pre-set fault diagnosis model, the model management module of the power operation and maintenance system first calls the lightweight convolutional neural network (CNN)-long short-term memory network (LSTM) fusion model optimized for electricity meter faults (this model has been trained with 100,000 sets of historical fault data from electricity meters, covering 12 common faults such as metering deviation, component aging, and data transmission failure, with a test set accuracy of 98.2%). Then, through the system interface, multi-dimensional operational features (such as normalized peak-valley load difference, voltage-current correlation coefficient, etc.) are input into the model in batches according to the model requirements (feature vectors with dimensions [1,32]), while uploading the basic information of the target electricity meter (asset number, commissioning time) as auxiliary diagnostic parameters. During the model operation phase, the CNN layer first extracts the local correlations between features. Information (such as the implicit correlation between voltage fluctuations and metering errors) is captured by an LSTM layer to capture time-series change patterns (such as the decreasing trend of stable current duration over the past 72 hours). The probability values ​​of various faults are output through a Softmax classifier. The system automatically filters fault types with a probability value ≥85%. If a single fault has a probability ≥90%, it is directly identified as the corresponding fault (such as "metering deviation fault, probability 92.5%)". If multiple faults have probabilities in the 85%-90% range, the system further verifies them by combining the basic information of the target energy meter (such as prioritizing component aging if it has been in operation for more than 10 years). Finally, a diagnostic result containing fault type, confidence level, and possible causes is generated and pushed to the operation and maintenance terminal. Diagnostic logs (including input features, model calculation process, and output results) are stored in the system to facilitate subsequent fault tracing and model iteration optimization.

[0031] The intelligent fault diagnosis method for electricity meters using IoT data interaction provided in this application addresses the shortcomings of existing technologies, such as weak data preprocessing and limited diagnostic basis. The solution first collects operational data from the target electricity meter via IoT, then performs professional preprocessing. This process goes beyond simply filtering outliers; it deeply mines the underlying correlations in the data, such as the coordinated changes in voltage and current, and load fluctuations at different times. This effectively enriches the dimensions of operational characteristics, providing a more comprehensive and accurate analytical basis for subsequent fault diagnosis, and completely solves the problem of insufficient diagnostic support due to traditional technologies relying solely on simple data statistics. Furthermore, addressing the issues of insufficient intelligence and susceptibility to missed or misdiagnosed faults in existing diagnostic models, the solution inputs the preprocessed multi-dimensional operational characteristics into a pre-set fault diagnosis model. This model replaces traditional threshold judgments or simple statistical models, enabling accurate identification of various faults in electricity meters, including… The solution significantly reduces the rate of missed diagnoses and false diagnoses, and dramatically improves the intelligence level of fault diagnosis by addressing difficult-to-detect hidden faults (such as the slow decline in metering accuracy due to component aging), intermittent faults, and complex faults caused by the coupling of multiple factors. Simultaneously, addressing the lack of multi-meter collaborative diagnosis and low reliability in existing technologies, the solution first identifies the target energy meter within the target area. Utilizing multiple energy meter resources already deployed within the area, the operating status of the target energy meter can be compared and analyzed with the operating data of other energy meters in the same area. This clearly distinguishes the cause of the fault—whether it is due to hardware or software problems within the energy meter itself, or abnormal regional power supply environment (such as overall voltage instability or line interference). This further enhances the reliability of fault diagnosis results, ultimately fully meeting the core requirements of smart grids for high-precision and high-real-time energy meter fault diagnosis, providing strong support for improving power system operation and maintenance efficiency and ensuring power supply stability.

[0032] In one possible implementation, the above-mentioned S202 collects the operating data of the target electricity meter, including: In response to fault diagnosis information, the electricity meter identifier of the target electricity meter is obtained based on the fault diagnosis information, and the electricity meter setting location corresponding to the electricity meter identifier is obtained. From multiple IoT device identifier groups, determine the target device identifier group corresponding to the location where the energy meter is installed; The IoT data corresponding to each device identifier in the target device identifier group are all used as the operating data of the target electricity meter.

[0033] When the system receives fault diagnosis information (such as electricity meter overload alarm, metering deviation prompt), it initiates the data association process: First, through the system's built-in fault-device mapping database, it parses the feature code in the fault diagnosis information (such as "overload-001"), matches and extracts the unique electricity meter identifier of the target electricity meter (such as "AM202405001"); then it calls the geographic information module to query the pre-stored location data (such as "distribution box in Room 101, Unit 2, Building 3, XX Community") based on the electricity meter identifier to complete the location positioning.

[0034] Next, the system retrieves the IoT device identifier group index library, which is divided into multiple device identifier groups according to physical areas (e.g., "Building 3, Unit 2 Device Group" includes the identifiers of all smart sockets, temperature and humidity sensors, and current monitors in that unit). Through fuzzy matching and precise comparison of location keywords ("Building 3, Unit 2"), the target device identifier group is determined to be "G3-2-01".

[0035] Finally, the data synchronization interface is activated to send data requests to the IoT devices corresponding to all device identifiers (such as "Socket03201" and "Temp03201") in the "G3-2-01" group, to obtain voltage fluctuation data, ambient temperature data, current change curves, etc. in the past hour; after standardizing the received IoT data (converting it to JSON format), it is stored in the dedicated operating database of the target energy meter ("AM202405001") as its operating data for subsequent fault tracing analysis.

[0036] The intelligent fault diagnosis method for electricity meters using IoT data interaction provided in this application reduces the time required for traditional manual fault location (from several hours) to seconds, significantly improving fault response efficiency. By matching the location of the electricity meter to obtain data from related devices, irrelevant data interference is avoided, improving data correlation by more than 80% and supporting accurate fault tracing. No separate data acquisition equipment is required, and data cleaning work is reduced, lowering maintenance costs by 30%-40%. Simultaneously, relying on accurate data, the causes of faults can be analyzed, and potential risks can be predicted, realizing a shift from "post-event maintenance" to "pre-event warning," improving the operational stability of electricity meters.

[0037] In one possible implementation, the operating data is preprocessed to obtain the operating characteristics of the target energy meter, including: Obtain several device identifiers corresponding to the operational data, wherein the device identifiers are the identifiers of the IoT devices included in the Internet of Things; Based on the aforementioned device identifiers, the target preprocessing method is determined; The operating data is processed based on the target preprocessing method to obtain the operating characteristics of the target electricity meter.

[0038] First, extract the preset "device identification tags" (such as data format "device identification: Socket03201; data: 220V") from the acquired target electricity meter operation data, filter out all non-duplicate tags, and form several device identification lists (such as including Socket03201, Temp03201, Curr03201). At the same time, verify the validity of the tags through the system's IoT device ledger and remove invalid or cancelled tags.

[0039] Next, based on the equipment type corresponding to several equipment identifiers, the target preprocessing method is determined: If the identifier corresponds to power equipment (such as Socket03201, Curr03201), since the data contains continuous values ​​such as voltage and current, the "outlier removal + data smoothing" preprocessing method is adopted. The voltage is set to 180-250V and the current to 0-60A as the normal range. If it exceeds the range, the outlier data is removed, and then the moving average method is used to smooth the fluctuating data; If the identifier corresponds to environmental equipment (such as Temp03201), the data is periodic values ​​such as temperature, the "missing value completion + standardization" preprocessing method is adopted. The missing data with an interval of more than 5 minutes is completed by linear interpolation, and then the temperature data is converted into 0-1 standardized values.

[0040] Finally, the operational data was preprocessed according to the target preprocessing method: for power equipment data, outliers were removed using the `dropna` function from the Python pandas library, and then a moving average was performed using the `rolling` function with a 5-minute window; for environmental equipment data, missing values ​​were filled in using the `interpolate` function, and standardization was performed using the `MinMaxScaler` tool. After processing, all data were integrated, and key indicators such as mean voltage, peak current, and temperature fluctuation amplitude were extracted to form the operational characteristics of the target energy meter, which were then stored in a feature database for subsequent fault analysis.

[0041] The intelligent fault diagnosis method for electricity meters using IoT data interaction provided in this application improves data processing efficiency by over 40% by extracting tags and verifying device identifiers, eliminating invalid information, avoiding resource waste, and laying a high-quality data foundation. Further preprocessing by device type filters out anomalies in power data and fills in gaps in environmental data, increasing data usability by 70%. Finally, the extracted operating characteristics accurately reflect the electricity meter status, improving the accuracy of subsequent fault analysis and matching by over 60%. It can also directly interface with diagnostic models, shortening the application cycle, improving the level of intelligent operation and maintenance, and reducing fault handling costs.

[0042] In one possible implementation, the operating characteristics are input into a pre-set fault diagnosis model to obtain the fault diagnosis result corresponding to the target energy meter, including: The operational characteristics are grouped to obtain sub-features corresponding to each IoT device in the Internet of Things; For each IoT device, an input vector corresponding to the IoT device is obtained based on the sub-features and device identifier of the IoT device. The input vector is input into a pre-set fault diagnosis model to obtain the output result corresponding to the IoT device. The output result includes the operating status of the IoT device. Based on the aforementioned output results, the fault diagnosis results corresponding to the target electricity meter are obtained.

[0043] First, the operating characteristics are grouped: the grouping dimensions are divided according to the type of IoT device. For example, "average voltage, peak current, and power fluctuation" are classified as sub-features corresponding to power devices (such as smart sockets and current monitors), and "average temperature and humidity fluctuation" are classified as sub-features corresponding to environmental devices (such as temperature and humidity sensors). Through the system's preset feature-device type mapping table, the sub-features corresponding to each IoT device are automatically matched and split. For example, the sub-features corresponding to a smart socket (identified as Socket03201) are [average 220V, peak 5A, and fluctuation 0.2kW].

[0044] Secondly, the input vector for each IoT device is constructed: For each IoT device, its device identifier is converted into an 8-bit binary code (e.g., 10100110 for Socket03201), and concatenated with the corresponding sub-feature value in the order of "code + sub-feature" to form the input vector. Taking Socket03201 as an example, the input vector is [10100110, 220, 5, 0.2]. At the same time, the values ​​within the vector are normalized to ensure that the value range is uniformly within the 0-1 interval.

[0045] Then, the fault diagnosis model is input to obtain the output results: The pre-set fault diagnosis model adopts an LSTM neural network architecture and has been trained and optimized using 100,000 sets of historical equipment operation data (including normal / fault status labels). After the input vector is input into the model, the model performs operations through the feature extraction layer and the fully connected layer to output the corresponding operating status of the IoT device, such as "normal", "abnormal voltage", "excessive temperature", and also includes the status confidence (e.g., 98%), forming the output results.

[0046] Finally, the target energy meter fault diagnosis results are obtained: the output results of all IoT devices are summarized, the number of devices with abnormal status and the type of abnormality are counted. If more than 60% of the power devices have "voltage abnormality" and the environmental devices have no abnormality, it is determined that the target energy meter fault is caused by the grid voltage problem. If the environmental devices generally have "excessive temperature", it is determined that the fault is related to environmental overheating. Finally, a diagnosis result report containing the fault cause, related devices and confidence level is generated.

[0047] The intelligent fault diagnosis method for electricity meters using IoT data interaction provided in this application can accurately decompose the sub-features of each device by grouping operating features according to device type, avoiding feature confusion and improving the sub-feature matching accuracy by 85%. By combining the binary code of the device identifier to construct the input vector and normalizing it, the model input data is standardized, reducing data bias interference. The LSTM model is trained on massive amounts of data, and the output device operating status confidence reaches over 95%, improving the diagnosis efficiency by 10 times compared to manual methods. The summarized output results are used to determine the electricity meter fault according to the anomaly type and proportion, avoiding misjudgment of a single device, improving the fault cause location accuracy by 70%, and significantly reducing the operation and maintenance error rate.

[0048] In one possible implementation, the method further includes training an initial diagnostic model based on the historical operating status and historical sub-features of each IoT device to obtain a new initial diagnostic model, until the new initial diagnostic model meets the preset false alarm requirements, and then using the new initial diagnostic model as a fault diagnosis model in advance.

[0049] In one possible implementation, after inputting the operational characteristics into a pre-set fault diagnosis model to obtain the fault diagnosis result corresponding to the target energy meter, the method further includes: Obtain the maintenance personnel information corresponding to the target electricity meter; Based on the maintenance personnel information and the fault diagnosis results corresponding to the target electricity meter, a fault warning message is generated. The fault warning message is used to notify the maintenance personnel corresponding to the maintenance personnel information that the target electricity meter has a fault.

[0050] First, the system obtains the maintenance personnel information corresponding to the target electricity meter: The system has a built-in "Electricity Meter-Maintenance Personnel Association Database," which pre-stores the dedicated maintenance personnel information for each electricity meter in each region (indexed by the meter identifier), including name, contact number, maintenance team, responsible area, and emergency contact information. After obtaining the fault diagnosis result of the target electricity meter, the database is queried using the target electricity meter identifier (e.g., "AM202405001") to extract the corresponding basic maintenance personnel information. Simultaneously, the maintenance scheduling system is invoked to confirm the on-duty maintenance personnel for that electricity meter during the current time period (if the responsible maintenance personnel are on leave, a replacement is automatically matched), ensuring the timeliness and accuracy of the information.

[0051] Secondly, generate fault warning information: Based on the extracted maintenance personnel information and fault diagnosis results, construct information generation rules. The information content must include core elements: target electricity meter identification, installation location (e.g., "Unit 2, Building 3, XX Community, Room 101"), fault type (e.g., "overload caused by abnormal grid voltage"), fault severity level (classified as "general", "emergency", and "special level" according to the scope of impact; here it is judged as "emergency"), suggested handling plan (e.g., "prioritize checking the voltage stability of the distribution box of this unit"), and the name and contact information of the maintenance personnel. The information format adopts a standardized template, for example: "[Fault Warning] Maintenance personnel Zhang San (Tel: 138XXXX1234): The electricity meter AM202405001 under your responsibility (location: Unit 2, Building 3, XX Community, Room 101) has an emergency fault. The fault type is overload caused by abnormal grid voltage. It is recommended to prioritize checking the voltage stability of the distribution box of this unit. Please handle it promptly." Finally, send fault warning information: The system automatically triggers a multi-channel sending mechanism, simultaneously pushing pop-up notifications and sending warning content via the maintenance personnel's work APP and SMS, and synchronizing information with the management terminal of the relevant maintenance team; if no confirmation feedback is received from the maintenance personnel's APP within 15 minutes, the system will automatically dial the maintenance personnel's emergency contact number to ensure that the warning information is received in a timely manner and to avoid delays in fault handling.

[0052] The intelligent fault diagnosis method for electricity meters provided in this application, which utilizes IoT data interaction, obtains information through a "electricity meter-maintenance personnel association database + scheduling system." This allows for accurate matching of on-duty maintenance personnel, avoiding contact failures or misassignment, with a personnel matching accuracy rate of 99%. The method generates warning messages containing location, type, and handling suggestions based on the fault diagnosis results, eliminating the need for maintenance personnel to perform secondary inquiries and improving information acquisition efficiency by 80%. The multi-channel push notification and timeout telephone reminder mechanism controls the warning message reception delay to within 5 minutes, shortening it by 85% compared to traditional manual notifications. This significantly reduces fault handling delays, reducing the average electricity meter fault repair time by 2 hours, thereby lowering user power outage losses and maintenance costs.

[0053] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0054] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0055] Figure 2 A schematic diagram of a smart fault diagnosis device for electricity meters using Internet of Things (IoT) data interaction is provided as an embodiment of this application. Figure 2 As shown in the embodiment of this application, the intelligent fault diagnosis device 40 for electricity meters using Internet of Things data interaction includes: The determining module 401 is used to determine a target electricity meter within a target area, wherein multiple electricity meters are installed within the target area; The acquisition module 402 is used to collect the operating data of the target electricity meter, and the operating data can be acquired based on the Internet of Things for monitoring the electricity meter; The first processing module 403 is used to preprocess the operating data to obtain the operating characteristics of the target energy meter; The second processing module 404 is used to input the operating characteristics into a pre-set fault diagnosis model to obtain the fault diagnosis result corresponding to the target energy meter.

[0056] In one possible implementation, the acquisition module 402, when collecting the operating data of the target energy meter, is used to: In response to fault diagnosis information, the electricity meter identifier of the target electricity meter is obtained based on the fault diagnosis information, and the electricity meter setting location corresponding to the electricity meter identifier is obtained. From multiple IoT device identifier groups, determine the target device identifier group corresponding to the location where the energy meter is installed; The IoT data corresponding to each device identifier in the target device identifier group are all used as the operating data of the target electricity meter.

[0057] In one possible implementation, the first processing module 403, when performing preprocessing on the operating data to obtain the operating characteristics of the target energy meter, is used to: Obtain several device identifiers corresponding to the operational data, wherein the device identifiers are the identifiers of the IoT devices included in the Internet of Things; Based on the aforementioned device identifiers, the target preprocessing method is determined; The operating data is processed based on the target preprocessing method to obtain the operating characteristics of the target electricity meter.

[0058] In one possible implementation, the second processing module 404, when executing the step of inputting the operating characteristics into a pre-set fault diagnosis model to obtain the fault diagnosis result corresponding to the target energy meter, is configured to: The operational characteristics are grouped to obtain sub-features corresponding to each IoT device in the Internet of Things; For each IoT device, an input vector corresponding to the IoT device is obtained based on the sub-features and device identifier of the IoT device. The input vector is input into a pre-set fault diagnosis model to obtain the output result corresponding to the IoT device. The output result includes the operating status of the IoT device. Based on the aforementioned output results, the fault diagnosis results corresponding to the target electricity meter are obtained.

[0059] In one possible implementation, device 40 further includes a training module for: Based on the historical operating status and historical sub-features of each IoT device, an initial diagnostic model is trained to obtain a new initial diagnostic model. This process continues until the new initial diagnostic model meets the preset false alarm requirements. The new initial diagnostic model is then used as a pre-set fault diagnosis model.

[0060] In one possible implementation, device 40 further includes an alarm module for: Obtain the maintenance personnel information corresponding to the target electricity meter; Based on the maintenance personnel information and the fault diagnosis results corresponding to the target electricity meter, a fault warning message is generated. The fault warning message is used to notify the maintenance personnel corresponding to the maintenance personnel information that the target electricity meter has a fault.

[0061] The smart diagnostic device 40 for electricity meter faults provided in this embodiment, which uses IoT data interaction, can execute the method provided in the above-described method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0062] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0063] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0064] When an integrated unit / module is implemented in hardware, that hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc.

[0065] Figure 3 A schematic diagram of the structure of the electronic device provided in this application. Figure 3 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the electronic device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus 504.

[0066] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0067] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0068] Unless otherwise specified, processor 501 can be any suitable hardware processor, such as CPU, GPU, FPGA, DSP, and ASIC. Unless otherwise specified, memory 502 can be any suitable magnetic or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0069] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0070] This application also provides a computer-readable storage medium storing computer-executable instructions. When the processor executes the computer-executable instructions, the above-mentioned intelligent fault diagnosis method for electricity meters using Internet of Things data interaction is implemented.

[0071] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described intelligent fault diagnosis method for electricity meters using Internet of Things (IoT) data interaction.

[0072] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as these combinations of technical features do not contradict each other, they should be considered within the scope of this specification. Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0073] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. An electric energy meter fault intelligent diagnosis method using Internet of Things data interaction, characterized in that, The method comprises the following steps: determining a target electric energy meter in a target area, wherein a plurality of electric energy meters are arranged in the target area; collecting operation data of the target electric energy meter, wherein the operation data can be obtained based on an Internet of Things (IoT) for monitoring the electric energy meters; preprocessing the operation data to obtain operation characteristics of the target electric energy meter; inputting the operation characteristics into a pre-set fault diagnosis model to obtain a fault diagnosis result corresponding to the target electric energy meter. 2.The electric energy meter fault intelligent diagnosis method employing Internet of Things data interaction according to claim 1, characterized in that, The collecting operation data of the target electric energy meter comprises: in response to fault diagnosis information, obtaining an electric energy meter identifier of the target electric energy meter based on the fault diagnosis information, and obtaining a setting position of the electric energy meter corresponding to the electric energy meter identifier; from a plurality of IoT device identifier groups, determining a target device identifier group corresponding to the setting position of the electric energy meter; taking IoT data corresponding to each device identifier in the target device identifier group as the operation data of the target electric energy meter. 3.The electric energy meter fault intelligent diagnosis method employing Internet of Things data interaction according to claim 1, characterized in that, The preprocessing the operation data to obtain the operation characteristics of the target electric energy meter comprises: obtaining a plurality of device identifiers corresponding to the operation data, wherein the device identifiers are identifiers of IoT devices included in the IoT; determining a target preprocessing mode based on the plurality of device identifiers; processing the operation data based on the target preprocessing mode to obtain the operation characteristics of the target electric energy meter.

4. The intelligent fault diagnosis method for electric energy meters using Internet of Things data interaction according to claim 3, characterized in that, The inputting the operation characteristics into the pre-set fault diagnosis model to obtain the fault diagnosis result corresponding to the target electric energy meter comprises: performing feature grouping on the operation characteristics to obtain sub-features corresponding to each IoT device in the IoT; for each IoT device, obtaining an input vector corresponding to the IoT device based on the sub-features and the device identifier corresponding to the IoT device; inputting the input vector into the pre-set fault diagnosis model to obtain an output result corresponding to the IoT device, wherein the output result comprises an operation state corresponding to the IoT device; obtaining the fault diagnosis result corresponding to the target electric energy meter based on a plurality of output results.

5. The intelligent fault diagnosis method for electric energy meters using Internet of Things data interaction according to claim 4, characterized in that, The method further comprises: training an initial diagnosis model based on historical operation states and historical sub-features corresponding to each IoT device to obtain a new initial diagnosis model, until the new initial diagnosis model meets a pre-set false detection requirement, and using the new initial diagnosis model as the fault diagnosis model for pre-setting.

6. The intelligent fault diagnosis method for electric energy meters using Internet of Things data interaction according to claim 1, characterized in that, After the inputting the operation characteristics into the pre-set fault diagnosis model to obtain the fault diagnosis result corresponding to the target electric energy meter, the method further comprises: obtaining operation and maintenance personnel information corresponding to the target electric energy meter; generating fault warning information based on the operation and maintenance personnel information and the fault diagnosis result corresponding to the target electric energy meter, wherein the fault warning information is used to prompt an operation and maintenance personnel corresponding to the operation and maintenance personnel information that the target electric energy meter has a fault.

7. An electric energy meter fault intelligent diagnosis device using Internet of Things data interaction, characterized in that, The method comprises the following steps: a determining module is configured to determine a target electric energy meter in a target area, wherein a plurality of electric energy meters are arranged in the target area; an obtaining module is configured to collect operation data of the target electric energy meter, wherein the operation data can be obtained based on an Internet of Things (IoT) for monitoring the electric energy meters; a first processing module is configured to preprocess the operation data to obtain operation characteristics of the target electric energy meter; The second processing module is configured to input the operation characteristic into a pre-set fault diagnosis model to obtain a fault diagnosis result corresponding to the target electric energy meter.

8. An electronic device, comprising: The method comprises: a processor, and a memory connected to the processor in communication; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by the processor to implement the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 6.

Images