Electric energy meter battery fault detection method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to an electric energy meter battery fault detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: establishing communication connection with a to-be-detected electric energy meter, and reading operation state information and battery data of the to-be-detected electric energy meter through the communication connection; according to the operation state information and the battery data, determining a battery fault preliminary judgment result of the to-be-detected electric energy meter; under the condition that the battery fault preliminary judgment result is that the battery is suspected to be abnormal, acquiring battery impedance data of the to-be-detected electric energy meter through communication connection; and obtaining a battery fault detection result of the to-be-detected electric energy meter according to the battery impedance data and a pre-trained electric energy meter battery fault detection model. The method can improve the battery fault detection efficiency of the electric energy meter.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for detecting battery faults in an electric energy meter. Background Art

[0002] The energy meter is an important metering device in the power system, and the performance of its battery directly affects the working state and metering accuracy of the energy meter. However, various faults may occur in the energy meter battery during actual operation, such as battery aging, insufficient power, poor contact, etc., causing the energy meter to stop working or metering data to be wrong.

[0003] Traditional methods for detecting battery faults in electric energy meters mainly rely on regular manual inspections, which have problems such as low detection efficiency and untimely fault detection. Summary of the invention

[0004] Based on this, it is necessary to provide an energy meter battery fault detection method, device, computer equipment, computer readable storage medium and computer program product that can improve the efficiency of energy meter battery fault detection in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for detecting battery failure in an electric energy meter, comprising:

[0006] Establishing a communication connection with the electric energy meter to be detected, and reading the operating status information and battery data of the electric energy meter to be detected through the communication connection;

[0007] Determine a preliminary battery fault determination result of the electric energy meter to be detected according to the operating status information and the battery data;

[0008] When the preliminary judgment result of the battery fault is that the battery is suspected to be abnormal, obtaining the battery impedance data of the electric energy meter to be detected through the communication connection;

[0009] According to the battery impedance data and the pre-trained electric energy meter battery fault detection model, a battery fault inspection result of the electric energy meter to be detected is obtained.

[0010] In one embodiment, determining a preliminary result of a battery fault determination of the electric energy meter to be detected according to the operating status information and the battery data includes:

[0011] Acquire current environment information, and acquire corresponding preset judgment standard information according to the current environment information;

[0012] A preliminary judgment result of a battery failure of the electric energy meter to be detected is determined according to the judgment standard information, the operating status information and the battery data.

[0013] In one embodiment, obtaining the battery fault inspection result of the electric energy meter to be inspected according to the battery impedance data and the pre-trained electric energy meter battery fault detection model includes:

[0014] Extracting mathematical characteristic data of the battery impedance data from the battery impedance data using a preset extraction method;

[0015] Using a preset statistical method to obtain mathematical statistical data of the battery impedance data;

[0016] The battery impedance data, the mathematical characteristic data and the mathematical statistical data are input into the pre-trained electric energy meter battery fault detection model to obtain the battery fault inspection result of the electric energy meter to be detected.

[0017] In one embodiment, after obtaining the battery fault inspection result of the electric energy meter to be inspected, the method further includes:

[0018] When the battery fault inspection result is a fault, obtaining historical impedance data of the battery in the electric energy meter to be detected within a target time period; the target time period is a time period before the battery fault in the electric energy meter to be detected is detected;

[0019] The cause of the battery failure of the electric energy meter to be detected is predicted based on the historical impedance data.

[0020] In one embodiment, predicting the cause of the battery failure of the electric energy meter to be detected based on the historical impedance data includes:

[0021] Determining a battery failure time point of the electric energy meter to be detected according to the historical impedance data;

[0022] Acquire the operating condition data of the electric energy meter to be detected at the time point of the battery failure;

[0023] The cause of the battery failure of the electric energy meter to be detected is predicted based on the operating condition data.

[0024] In one embodiment, after obtaining the battery fault inspection result of the electric energy meter to be inspected, the method further includes:

[0025] Obtaining a user inspection result corresponding to the battery fault inspection result;

[0026] The pre-trained electric energy meter battery fault detection model is dynamically updated according to the battery fault inspection result and the user inspection result to obtain an updated pre-trained electric energy meter battery fault detection model.

[0027] In a second aspect, the present application also provides an electric energy meter battery fault detection device, comprising:

[0028] An initial data acquisition module, used to establish a communication connection with the electric energy meter to be detected, and read the operating status information and battery data of the electric energy meter to be detected through the communication connection;

[0029] A preliminary fault judgment module, used to determine a preliminary fault judgment result of the battery of the electric energy meter to be detected according to the operating status information and the battery data;

[0030] An impedance data acquisition module, used for acquiring the battery impedance data of the electric energy meter to be detected through the communication connection when the preliminary judgment result of the battery fault is that the battery is suspected to be abnormal;

[0031] The fault result determination module is used to obtain the battery fault inspection result of the electric energy meter to be detected based on the battery impedance data and the pre-trained electric energy meter battery fault detection model.

[0032] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Establishing a communication connection with the electric energy meter to be detected, and reading the operating status information and battery data of the electric energy meter to be detected through the communication connection;

[0034] Determine a preliminary battery fault determination result of the electric energy meter to be detected according to the operating status information and the battery data;

[0035] When the preliminary judgment result of the battery fault is that the battery is suspected to be abnormal, obtaining the battery impedance data of the electric energy meter to be detected through the communication connection;

[0036] According to the battery impedance data and the pre-trained electric energy meter battery fault detection model, a battery fault inspection result of the electric energy meter to be detected is obtained.

[0037] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0038] Establishing a communication connection with the electric energy meter to be detected, and reading the operating status information and battery data of the electric energy meter to be detected through the communication connection;

[0039] Determine a preliminary battery fault determination result of the electric energy meter to be detected according to the operating status information and the battery data;

[0040] When the preliminary judgment result of the battery fault is that the battery is suspected to be abnormal, obtaining the battery impedance data of the electric energy meter to be detected through the communication connection;

[0041] According to the battery impedance data and the pre-trained electric energy meter battery fault detection model, a battery fault inspection result of the electric energy meter to be detected is obtained.

[0042] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0043] Establishing a communication connection with the electric energy meter to be detected, and reading the operating status information and battery data of the electric energy meter to be detected through the communication connection;

[0044] Determine a preliminary battery fault determination result of the electric energy meter to be detected according to the operating status information and the battery data;

[0045] When the preliminary judgment result of the battery fault is that the battery is suspected to be abnormal, obtaining the battery impedance data of the electric energy meter to be detected through the communication connection;

[0046] According to the battery impedance data and the pre-trained electric energy meter battery fault detection model, a battery fault inspection result of the electric energy meter to be detected is obtained.

[0047] The above-mentioned electric energy meter battery fault detection method, device, computer equipment, computer-readable storage medium and computer program product first establish a communication connection with the electric energy meter to be detected, read the operating status information and battery data of the electric energy meter to be detected through the communication connection, and realize remote monitoring and data acquisition of the electric energy meter through the communication connection. It is no longer dependent on manual inspections and can read the operating status and battery data of the electric energy meter in real time, thereby improving the efficiency of detection, and timely obtaining basic parameters such as battery voltage and current, providing a preliminary basis for subsequent fault judgment, and being able to quickly discover potential battery problems; then, based on the operating status information and battery data, determine the preliminary judgment result of the battery fault of the electric energy meter to be detected, and by analyzing the operating data such as battery voltage and current, quickly judge whether the battery is in an abnormal state, such as low voltage, abnormal current, etc. In this way, batteries that may have problems can be preliminarily screened out, saving a lot of detection resources; then, when the preliminary judgment result of the battery fault is that the battery is suspected to be abnormal, the battery impedance data of the electric energy meter to be tested is obtained through the communication connection. The impedance data can reflect the internal health status of the battery. Compared with conventional parameters such as voltage and current, impedance can provide more in-depth diagnostic information. By obtaining impedance data, it is possible to more accurately identify faults such as performance degradation or poor contact inside the battery. The automatic acquisition of impedance data does not require human intervention, which further improves the accuracy and efficiency of detection, especially in the scenario of large-scale electric meter deployment; finally, based on the battery impedance data and the pre-trained electric energy meter battery fault detection model, the battery fault inspection result of the electric energy meter to be tested is obtained. The pre-trained battery fault detection model can automatically analyze the impedance data based on a large amount of historical data through algorithms such as machine learning, and quickly draw an accurate conclusion on whether the battery has a fault. In the above method, the system automatically completes the entire process from data collection to fault judgment, which greatly reduces manual intervention and improves detection efficiency. Through the combination of impedance data and pre-trained models, it can accurately identify potential faults inside the battery, avoiding errors in traditional judgments based on simple parameters such as voltage and current. It is especially suitable for detecting complex battery problems, such as increased internal impedance and aging, reducing the frequency and workload of manual inspections. The automated fault detection system reduces maintenance costs and reduces subsequent repair costs caused by battery problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0049] FIG1 is a schematic diagram of a flow chart of a method for detecting battery failure in an electric energy meter according to an embodiment;

[0050] FIG2 is a schematic flow chart of a battery failure cause prediction step in one embodiment;

[0051] FIG3 is a schematic flow chart of a method for detecting battery failure in an electric energy meter according to another embodiment;

[0052] FIG4 is a structural block diagram of a battery fault detection device for an electric energy meter in one embodiment;

[0053] FIG. 5 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] In one embodiment, as shown in FIG1 , a method for detecting battery faults in an electric energy meter is provided. This embodiment uses the method applied to a terminal as an example for illustration. It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, and tablet computers. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. In this embodiment, the method includes the following steps:

[0056] Step S101, establishing a communication connection with the electric energy meter to be detected, and reading the operating status information and battery data of the electric energy meter to be detected through the communication connection.

[0057] Among them, communication connection refers to the remote data interaction channel established through standardized communication protocols (such as DL / T 645-2007 protocol or other applicable wireless / wired protocols) for data transmission between the energy meter and the external system. Operation status information refers to the current working status parameters of the energy meter, including key indicators required during the operation of the energy meter, such as voltage, current, temperature, etc. Battery data refers to performance parameters related to the battery inside the energy meter, such as battery voltage, current, temperature, impedance, etc.

[0058] Exemplarily, the terminal first performs a handshake operation with the electric energy meter to be detected through a communication protocol to ensure the stability and security of the communication. Then, the terminal sends a data reading instruction to the electric energy meter through a communication connection to obtain the operating status information and battery data of the electric energy meter. In actual implementation, the terminal can also establish communication connections with multiple electric energy meters at the same time in a multi-threaded manner to achieve batch data collection and improve detection efficiency. Through the collected operating status information and battery data, the terminal will provide basic data support for subsequent fault judgment and further detection steps.

[0059] Step S102: determining a preliminary result of a battery failure judgment of the electric energy meter to be detected according to the operating status information and the battery data.

[0060] The preliminary judgment result of battery failure is based on the preliminary analysis of the operating status information and battery data to determine whether the battery has a potential failure. This judgment does not require in-depth impedance analysis, but rather draws a conclusion on whether further testing is needed based on the abnormalities of basic data such as voltage, current, and temperature.

[0061] Exemplarily, after the terminal receives the operating status information and battery data of the energy meter, it first quickly filters the data through built-in logical rules or preset thresholds. In the case where the battery voltage is lower than the threshold, the current fluctuates abnormally, or the temperature is too high, the terminal will immediately mark the battery of the energy meter as a suspected faulty battery, that is, a preliminary judgment of the battery failure. At this time, the terminal can automatically generate a judgment report, marking the abnormal parameters and their corresponding threshold differences as a basis for further analysis of the fault. In addition, the terminal will not only judge the fault based on the abnormality of a single parameter, but also improve the accuracy of the judgment through multi-parameter joint analysis (such as the comprehensive changes of voltage, current, and temperature). In this way, the terminal can quickly identify potential problems with the battery without performing complex impedance analysis, which is convenient for subsequent deep fault detection and maintenance operations.

[0062] Step S103, when the preliminary judgment result of the battery fault is that the battery is suspected to be abnormal, the battery impedance data of the electric energy meter to be detected is obtained through the communication connection.

[0063] Among them, battery impedance data refers to the impedance value calculated by measuring the voltage and current response of the battery at a specific frequency. This data can reflect the health of the battery, especially the aging of the internal materials or poor contact of the battery. Battery impedance measurement usually involves multi-frequency signal excitation to obtain more comprehensive impedance spectrum data.

[0064] For example, when the terminal makes a preliminary judgment on the battery failure and marks it as "suspected abnormality", the terminal will automatically send an impedance measurement request to the electric energy meter through the existing communication connection. The electric energy meter responds to the request and activates its internal impedance measurement module (such as an impedance spectrum sensor), or measures through an external device to start collecting the impedance data of the battery. The measurement process usually includes applying AC signals of different frequencies, measuring the voltage and current of the battery at each frequency, and calculating the impedance value through Fourier transform or other signal processing techniques. The terminal will compare the acquired battery impedance data with the preset impedance reference model.

[0065] Step S104, obtaining a battery fault detection result of the electric energy meter to be detected according to the battery impedance data and the pre-trained electric energy meter battery fault detection model.

[0066] Among them, the pre-trained electric energy meter battery fault detection model refers to a model trained based on historical battery data and machine learning algorithms (such as support vector machines, random forests, neural networks, etc.). By learning the impedance data characteristics of normal and faulty batteries, the model can automatically identify whether the battery is faulty and output the corresponding fault type and probability. The battery fault inspection result refers to the conclusion of the battery health status drawn after model analysis, usually expressed as "normal" or "faulty", and may include detailed information of the fault and recommended treatment measures.

[0067] Exemplarily, after receiving the impedance data of the battery, the terminal will input these data into the pre-trained battery fault detection model for analysis. The model identifies whether the impedance data of the battery is consistent with the known fault mode by pattern matching the multi-dimensional features of the input data (such as impedance amplitude, phase angle, frequency response, etc.). For example, if the impedance increases significantly at high frequencies and performs normally at low frequencies, the model may determine that the battery has internal polarization or material aging problems. In addition, after obtaining the fault inspection results output by the model, the terminal will generate a specific fault report based on the analysis results. The report not only includes the conclusion of whether the battery is faulty, but also may include detailed fault types (such as too high internal resistance, too strong polarization) and corresponding maintenance suggestions (such as replacing the battery or reducing the charging rate). The terminal can automatically push the inspection results to the maintenance system or relevant operators to facilitate timely follow-up maintenance measures. Through this automated process, the terminal can significantly improve the accuracy and efficiency of fault detection.

[0068] In the above-mentioned method for detecting battery faults in electric energy meters, first, a communication connection is established with the electric energy meter to be detected, and the operating status information and battery data of the electric energy meter to be detected are read through the communication connection. Remote monitoring and data acquisition of the electric energy meter are realized through the communication connection, and manual inspections are no longer relied on. The operating status and battery data of the electric energy meter can be read in real time, thereby improving the efficiency of detection, and basic parameters such as battery voltage and current can be obtained in time, providing a preliminary basis for subsequent fault judgment, and being able to quickly discover potential battery problems; then, based on the operating status information and battery data, the preliminary judgment result of the battery fault of the electric energy meter to be detected is determined, and by analyzing the operating data such as the battery voltage and current, it is quickly determined whether the battery is in an abnormal state, such as low voltage, abnormal current, etc. In this way, batteries that may have problems can be preliminarily screened out, saving a lot of detection resources; then, when the preliminary judgment result of the battery fault is that the battery is suspected to be abnormal, the battery impedance data of the electric energy meter to be tested is obtained through the communication connection. The impedance data can reflect the internal health status of the battery. Compared with conventional parameters such as voltage and current, impedance can provide more in-depth diagnostic information. By obtaining impedance data, it is possible to more accurately identify faults such as performance degradation or poor contact inside the battery. The automatic acquisition of impedance data does not require human intervention, which further improves the accuracy and efficiency of detection, especially in the scenario of large-scale electric meter deployment; finally, based on the battery impedance data and the pre-trained electric energy meter battery fault detection model, the battery fault inspection result of the electric energy meter to be tested is obtained. The pre-trained battery fault detection model can automatically analyze the impedance data based on a large amount of historical data through algorithms such as machine learning, and quickly draw an accurate conclusion on whether the battery has a fault. In the above method, the system automatically completes the entire process from data collection to fault judgment, which greatly reduces manual intervention and improves detection efficiency. Through the combination of impedance data and pre-trained models, it can accurately identify potential faults inside the battery, avoiding errors in traditional judgments based on simple parameters such as voltage and current. It is especially suitable for detecting complex battery problems, such as increased internal impedance and aging, reducing the frequency and workload of manual inspections. The automated fault detection system reduces maintenance costs and reduces subsequent repair costs caused by battery problems.

[0069] In an exemplary embodiment, the above-mentioned step S102 determines the preliminary judgment result of the battery fault of the electric energy meter to be detected based on the operating status information and the battery data, and also includes: obtaining current environmental information, and obtaining corresponding preset judgment standard information based on the current environmental information; determining the preliminary judgment result of the battery fault of the electric energy meter to be detected based on the judgment standard information, the operating status information and the battery data.

[0070] The current environmental information refers to the environmental conditions at the location of the electric energy meter, including but not limited to external parameters that affect battery performance, such as temperature, humidity, and air pressure. The preset judgment standard information is a fault judgment standard preset according to different environmental conditions, which is used to make reasonable judgments on the battery status in different environments. The judgment standard information combines the actual working conditions and environmental factors of the battery to make a more accurate analysis of the battery's health status.

[0071] Exemplarily, after obtaining the operating status information and battery data of the battery, the terminal will simultaneously obtain the current environmental information, such as ambient temperature, humidity, etc., through built-in sensors or from an external meteorological system. The terminal matches this environmental information with the preset judgment criteria stored in the system. For example, in a high temperature environment, the normal voltage range of the battery may need to be adjusted upward to avoid misjudgment as a fault. The terminal analyzes the operating status information and battery data based on this adjusted judgment standard to determine whether there is a preliminary judgment result of a battery fault. The terminal incorporates different environmental factors into the fault judgment logic to ensure that the battery status can be accurately analyzed under various environmental conditions. For example, if the battery voltage is slightly lower than the normal value range in a high temperature environment, but the impedance data is not abnormal, the terminal may not immediately determine it as a fault, but continue to monitor its state changes in the next few tests.

[0072] In this embodiment, by introducing environmental information and preset judgment criteria, the battery fault can be judged more accurately, avoiding misjudgment caused by environmental changes. The fault judgment criteria are dynamically adjusted according to environmental changes to ensure the accuracy of fault judgment and improve the adaptability and flexibility of the system.

[0073] In an exemplary embodiment, the above-mentioned step S104 obtains the battery fault inspection result of the electric energy meter to be inspected based on the battery impedance data and the pre-trained electric energy meter battery fault detection model, and also includes: using a preset extraction method to extract the mathematical characteristic data of the battery impedance data from the battery impedance data; using a preset statistical method to obtain the mathematical statistical data of the battery impedance data; inputting the battery impedance data, the mathematical characteristic data and the mathematical statistical data into the pre-trained electric energy meter battery fault detection model to obtain the battery fault inspection result of the electric energy meter to be inspected.

[0074] Among them, mathematical characteristic data refers to characteristic values ​​extracted from battery impedance data, such as impedance amplitude, phase angle, frequency response, etc., which can describe the performance of the battery at different frequencies.

[0075] Among them, mathematical statistical data is the result obtained by statistical analysis of impedance data, such as mean, standard deviation, confidence interval, etc., which is used to measure the distribution characteristics of impedance data within a certain range and can reflect the stability and reliability of the battery status.

[0076] Exemplarily, the terminal first extracts mathematical characteristic data such as impedance amplitude, phase angle, and frequency response from the acquired battery impedance data through the built-in feature extraction module according to a preset algorithm. These characteristic data can describe in detail the impedance changes of the battery under different frequency conditions, which helps to capture subtle changes in the internal health of the battery. Then, the terminal calculates mathematical statistics such as the mean, standard deviation, and confidence interval of the impedance data through the statistical analysis module to quantify the overall performance of the battery impedance data. Through these statistics, the terminal can better understand the range of changes in battery impedance and the possibility of abnormal fluctuations. The terminal inputs the battery impedance data, mathematical characteristic data, and mathematical statistics together into a pre-trained battery fault detection model. The model automatically determines the failure probability and fault type of the battery based on the input multi-dimensional features and the historical fault mode. For example, the model can identify situations where the amplitude in the impedance data increases significantly and the frequency response is abnormal, and give fault diagnosis results.

[0077] In this embodiment, by combining the mathematical characteristic data and statistical data of the battery impedance data, not only can the accuracy of fault detection be improved, but also the state changes of the battery under different working conditions can be more comprehensively reflected. The mathematical characteristic data can capture the key physical characteristics of the battery impedance, while the mathematical statistical data can quantify the range and stability of these characteristics, thereby providing richer input information for the model and further improving the accuracy and reliability of battery fault diagnosis.

[0078] In an exemplary embodiment, as shown in FIG2 , after obtaining the battery fault inspection result of the electric energy meter to be inspected in the above step S104, the method further includes:

[0079] Step S201, when the battery fault inspection result is that a fault occurs, obtain historical impedance data of the battery in the electric energy meter to be inspected within a target time period.

[0080] The target time period is the time period before the battery fault in the electric energy meter to be detected is detected.

[0081] Step S202: predicting the cause of the battery failure of the electric energy meter to be tested based on the historical impedance data.

[0082] The target time period refers to a specific time range before the battery failure is detected, usually a time window of several days to several weeks, which is used to analyze the trend and changes of the battery impedance data. By obtaining the historical impedance data within the target time period, a more comprehensive understanding of the performance changes of the battery before the failure gradually occurs can be obtained.

[0083] Exemplarily, the terminal performs battery failure detection of the energy meter periodically or in response to user needs, which can save computing resources in the case of large quantities of energy meters. Then, during the detection, the battery may have failed for a period of time. Then, after determining the battery failure, the terminal will automatically query and download the historical impedance data of the energy meter. The data is usually stored in the internal memory of the energy meter or in the remote monitoring system, covering the multi-frequency impedance measurement records of the battery within the target time period. The terminal accurately extracts relevant historical data according to the set target time period parameters, such as impedance data within the past 30 days. After obtaining the historical impedance data, the terminal will conduct an in-depth analysis of the data to identify the trends and patterns of battery failures. Through trend analysis of historical data, such as observing the gradual increase in impedance, the terminal can infer the root cause of the battery failure. Common causes of failure include internal polarization of the battery, material aging, or poor contact. The terminal will apply an algorithm based on time series analysis to predict the trend of historical impedance data. By calculating the rate, amplitude, and periodic fluctuations of impedance change, the terminal can identify the transition process of the battery from a normal state to a faulty state. Combined with the pre-trained model, the terminal matches these trends with known failure modes and ultimately outputs the predicted cause of the battery failure.

[0084] In this embodiment, by analyzing the historical impedance data of the battery within the target time period, the occurrence process of the battery failure can be traced and the cause of the failure can be accurately predicted. This can not only provide a strong basis for decision-making for maintenance personnel, but also help further optimize the battery management strategy to avoid the recurrence of similar failures. Through a comprehensive analysis of historical data, battery problems can be diagnosed more accurately, improving the efficiency of energy meter maintenance and the intelligent level of battery management.

[0085] In an exemplary embodiment, the above-mentioned step S202 predicts the cause of the battery failure of the electric energy meter to be detected based on the historical impedance data, and also includes: determining the battery failure time point of the electric energy meter to be detected based on the historical impedance data; obtaining the operating condition data of the electric energy meter to be detected at the battery failure time point; and predicting the cause of the battery failure of the electric energy meter to be detected based on the operating condition data.

[0086] Among them, the operating condition data refers to the operating status information of the electric energy meter at that point in time, including the external environment related to the battery operation such as load current, voltage, temperature, and the operating conditions of the electric energy meter itself.

[0087] Exemplarily, when the terminal determines that there is a fault in the battery, it first extracts the historical impedance change trend data of the battery. By analyzing these impedance data through a clustering algorithm (such as K-means), the terminal can identify that the impedance has a sudden change or abnormal fluctuation at a certain time point (such as the 45th day). At this time, it can be determined that the time point is the battery failure time point. Specifically, the clustering clusters are divided based on the clustering algorithm to obtain at least two clusters, and the clusters with earlier sample times are usually when no fault occurs. Then, the clusters with later time represent the samples with faults, thereby determining the time point of the fault. Subsequently, the terminal extracts the operating condition data at that time point from the stored historical records to obtain key parameters such as the operating voltage, load current, and ambient temperature of the electric energy meter at that time. Then, based on these operating condition data, the terminal further applies a decision tree algorithm to classify and diagnose the type of battery fault. For example, if it is detected that the battery is running under a high load current at the time of the fault, and the ambient temperature is high at the same time, the terminal may infer that the cause of the fault is related to the internal polarization of the battery caused by overload operation or high temperature. Based on this diagnosis, the specific cause of the fault is output and corresponding maintenance suggestions are given, such as replacing the battery or optimizing the operating conditions of the energy meter.

[0088] In this embodiment, by combining the trend analysis of historical impedance data with the operating condition data, not only can the time point of battery failure be accurately identified, but also the root cause of the failure can be clarified through in-depth analysis of the operating condition data. This helps to locate the fault more accurately and formulate targeted maintenance plans, avoid repeated failures, and extend the service life of batteries and electric energy meters.

[0089] In an exemplary embodiment, after obtaining the battery fault inspection result of the electric energy meter to be inspected in the above step S104, it also includes: obtaining the user inspection result corresponding to the battery fault inspection result; dynamically updating the pre-trained electric energy meter battery fault detection model according to the battery fault inspection result and the user inspection result to obtain an updated pre-trained electric energy meter battery fault detection model.

[0090] Among them, the user inspection results refer to the inspection results of the electric energy meter and battery conducted by manual inspection or maintenance personnel on site, including the actual battery status, external environmental conditions and other data of on-site detection.

[0091] Exemplarily, the terminal first obtains the inspection report provided by the user inspection or on-site maintenance personnel after the battery fault inspection. The report usually contains the actual operation of the battery, whether there are any abnormalities, the working conditions on site, and the readings of the detection equipment. Then, the terminal compares and analyzes these user inspection results with the battery fault inspection results automatically generated by the system to identify the differences between the model judgment and the actual detection results. For example, the model may predict that the battery impedance is increased, but the user inspection results show that the actual battery condition is good, indicating that there may be a misjudgment. Based on the above difference analysis, the terminal applies a dynamic update algorithm (such as an online learning algorithm or incremental learning) to adjust the parameters of the pre-trained electric energy meter battery fault detection model to make it closer to the actual detection situation. By adding new inspection data and the continuous accumulation of historical fault data, the terminal can update and optimize the performance of the model to ensure the robustness and accuracy of the model in different environments and working conditions.

[0092] In this embodiment, by combining the user inspection results and the automatic fault inspection results generated by the system, the battery fault detection model is dynamically updated to make it more accurate and reliable in subsequent detections. This process not only reduces the model's misjudgment and missed judgment, but also improves the model's prediction performance through continuous learning, which helps to further improve the intelligent level and detection efficiency of electric energy meter battery maintenance.

[0093] In another exemplary embodiment, as shown in FIG3 , the present application provides a method for detecting battery failure in an electric energy meter, the method comprising the following steps:

[0094] Step S301, performing electric energy meter communication.

[0095] Step S302, reading voltage data items.

[0096] Step S303, reading the status word data item of the electric energy meter.

[0097] Step S304, determining whether the battery voltage is normal.

[0098] Step S305: perform impedance analysis to obtain impedance data.

[0099] Step S306: using a big data model to make a judgment.

[0100] Exemplarily, a standard communication protocol (such as DL / T 645-2007 or other applicable protocols) is used to establish a connection with the electric energy meter. The operating status word and battery voltage data items are read from the electric energy meter. Based on the comparison of the battery voltage with the standard voltage range, it is determined whether the battery is in a normal state. The impedance data of the suspected faulty electric meter is input into a pre-trained big data model. The model analyzes the input impedance data and outputs a prediction result. Based on the prediction results of the model, a threshold or confidence interval is set to determine whether the battery is damaged. If the prediction results of the model show that the impedance data exceeds the threshold or does not conform to the normal mode, it is determined that the battery may be damaged. Based on the prediction results of the model, targeted maintenance suggestions are made, such as replacing the battery or conducting further inspections.

[0101] In addition, the training steps of the model can be: First, a certain number of impedance data of normal energy meters under different working conditions need to be collected. These data should cover the typical operating conditions of the energy meter, including different loads, temperatures and voltage levels. Next, collect the impedance data of the faulty energy meter and ensure that the measurement is carried out under the same test conditions so as to compare with the data of the normal energy meter. Remove noise and outliers to ensure the quality and accuracy of the data. Since the measurement conditions of different meters may be different, the data needs to be standardized to make it comparable. Extract key features from the impedance data, such as the amplitude, phase angle, frequency response, etc. of the impedance. Select the features that best reflect the health of the battery for subsequent analysis. Use statistical methods (such as mean, standard deviation, confidence interval, etc.) to analyze the differences in impedance characteristics between normal meters and suspected faulty meters. Divide the collected data into training sets and test sets. Select appropriate machine learning algorithms, such as support vector machines, random forests, neural networks, etc. Use the training set data to train the model, adjust the model parameters, and optimize the model performance. Use the test set data to verify the accuracy and generalization ability of the model.

[0102] Furthermore, as more data is accumulated, the big data model is updated regularly to improve the accuracy and adaptability of the model. The actual maintenance results are fed back to the model to continuously optimize the performance of the model.

[0103] In this embodiment, the operation status and battery voltage data of the energy meter can be quickly read through the automatic communication between the energy meter calibration device and the energy meter, which greatly improves the efficiency of fault detection and solves the problem of inefficient manual detection. The introduction of an impedance analyzer to perform accurate impedance analysis on the battery, combined with a big data model, can accurately determine whether the battery is damaged, solving the problem of insufficient fault judgment accuracy in traditional methods. Automated fault detection and accurate fault location reduce unnecessary maintenance work and maintenance costs, and improve the work efficiency of the maintenance team. By ensuring the reliability of the battery in the energy meter, it helps to improve the stability and reliability of the entire power grid and reduce the failure of the energy meter caused by battery failure. By timely detecting and preventing battery failures, the service life of the battery can be extended and the frequency of battery replacement can be reduced. It is suitable for the deployment of large-scale energy meters, can effectively manage and monitor a large number of energy meters, and solves the problem of battery fault detection and management during large-scale deployment. Efficient and accurate detection and location of battery faults are achieved, providing strong technical support for the stable operation of the energy meter and the reliability of the power grid.

[0104] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0105] Based on the same inventive concept, the embodiment of the present application also provides an electric energy meter battery fault detection device for implementing the electric energy meter battery fault detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the electric energy meter battery fault detection device provided below can refer to the limitations of the electric energy meter battery fault detection method above, and will not be repeated here.

[0106] In an exemplary embodiment, as shown in FIG4 , a battery fault detection device for an electric energy meter is provided, comprising: an initial data acquisition module 401, a preliminary fault judgment module 402, an impedance data acquisition module 403 and a fault result determination module 404, wherein:

[0107] The initial data acquisition module 401 is used to establish a communication connection with the electric energy meter to be detected, and read the operating status information and battery data of the electric energy meter to be detected through the communication connection;

[0108] A preliminary fault judgment module 402 is used to determine a preliminary fault judgment result of a battery of the electric energy meter to be detected according to the operation status information and the battery data;

[0109] The impedance data acquisition module 403 is used to acquire the battery impedance data of the electric energy meter to be detected through the communication connection when the preliminary judgment result of the battery fault is that the battery is suspected to be abnormal;

[0110] The fault result determination module 404 is used to obtain the battery fault inspection result of the electric energy meter to be inspected according to the battery impedance data and the pre-trained electric energy meter battery fault detection model.

[0111] In one of the embodiments, the above-mentioned preliminary fault judgment module 402 is also used to obtain current environmental information, and obtain corresponding preset judgment standard information based on the current environmental information; determine the preliminary judgment result of the battery fault of the electric energy meter to be tested based on the judgment standard information, operating status information and battery data.

[0112] In one embodiment, the fault result determination module 404 is further used to extract mathematical characteristic data of the battery impedance data from the battery impedance data using a preset extraction method; obtain mathematical statistical data of the battery impedance data using a preset statistical method; and input the battery impedance data, mathematical characteristic data and mathematical statistical data into a pre-trained electric energy meter battery fault detection model to obtain the battery fault inspection result of the electric energy meter to be detected.

[0113] In one of the embodiments, the above-mentioned electric energy meter battery fault detection device also includes a fault identification module, which is used to obtain historical impedance data of the battery in the electric energy meter to be detected within a target time period when the battery fault inspection result is a fault; the target time period is the time period before the battery fault in the electric energy meter to be detected is detected; based on the historical impedance data, predict the cause of the battery failure of the electric energy meter to be detected.

[0114] In one of the embodiments, the above-mentioned fault identification module is also used to determine the battery failure time point of the electric energy meter to be detected based on historical impedance data; obtain the operating condition data of the electric energy meter to be detected at the battery failure time point; and predict the cause of the battery failure of the electric energy meter to be detected based on the operating condition data.

[0115] In one of the embodiments, the above-mentioned electric energy meter battery fault detection device also includes a model update module, which is used to obtain a user inspection result corresponding to the battery fault inspection result; based on the battery fault inspection result and the user inspection result, the pre-trained electric energy meter battery fault detection model is dynamically updated to obtain an updated pre-trained electric energy meter battery fault detection model.

[0116] Each module in the above-mentioned electric energy meter battery fault detection device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0117] In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG5. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for detecting battery faults in an electric energy meter is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0118] Those skilled in the art will understand that the structure shown in FIG. 5 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0119] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0120] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0121] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0122] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0123] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0124] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0125] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting battery failure in an electric energy meter, characterized in that: The method comprises: Establishing a communication connection with the electric energy meter to be detected, and reading the operating status information and battery data of the electric energy meter to be detected through the communication connection; Determine a preliminary battery fault determination result of the electric energy meter to be detected according to the operating status information and the battery data; When the preliminary judgment result of the battery fault is that the battery is suspected to be abnormal, obtaining the battery impedance data of the electric energy meter to be detected through the communication connection; According to the battery impedance data and the pre-trained electric energy meter battery fault detection model, a battery fault inspection result of the electric energy meter to be detected is obtained.

2. The method according to claim 1, characterized in that The step of determining a preliminary battery fault determination result of the electric energy meter to be detected according to the operating status information and the battery data includes: Acquire current environment information, and acquire corresponding preset judgment standard information according to the current environment information; A preliminary judgment result of a battery failure of the electric energy meter to be detected is determined according to the judgment standard information, the operating status information and the battery data.

3. The method according to claim 1, characterized in that: The method of obtaining the battery fault inspection result of the electric energy meter to be inspected according to the battery impedance data and the pre-trained electric energy meter battery fault detection model comprises: Extracting mathematical characteristic data of the battery impedance data from the battery impedance data using a preset extraction method; Using a preset statistical method to obtain mathematical statistical data of the battery impedance data; The battery impedance data, the mathematical characteristic data and the mathematical statistical data are input into the pre-trained electric energy meter battery fault detection model to obtain the battery fault inspection result of the electric energy meter to be detected.

4. The method according to claim 1, characterized in that: After obtaining the battery fault inspection result of the electric energy meter to be inspected, the method further includes: When the battery fault inspection result is a fault, obtaining historical impedance data of the battery in the electric energy meter to be detected within a target time period; the target time period is a time period before the battery fault in the electric energy meter to be detected is detected; The cause of the battery failure of the electric energy meter to be detected is predicted based on the historical impedance data.

5. The method according to claim 4, characterized in that The predicting the cause of the battery failure of the electric energy meter to be detected according to the historical impedance data includes: Determining a battery failure time point of the electric energy meter to be detected according to the historical impedance data; Acquire the operating condition data of the electric energy meter to be detected at the time point of the battery failure; The cause of the battery failure of the electric energy meter to be detected is predicted based on the operating condition data.

6. The method according to any one of claims 1 to 5, characterized in that: After obtaining the battery fault inspection result of the electric energy meter to be inspected, the method further includes: Obtaining a user inspection result corresponding to the battery fault inspection result; The pre-trained electric energy meter battery fault detection model is dynamically updated according to the battery fault inspection result and the user inspection result to obtain an updated pre-trained electric energy meter battery fault detection model.

7. An electric energy meter battery fault detection device, characterized in that: The device comprises: An initial data acquisition module, used for establishing a communication connection with the electric energy meter to be detected, and reading the operating status information and battery data of the electric energy meter to be detected through the communication connection; A preliminary fault judgment module, used to determine a preliminary fault judgment result of the battery of the electric energy meter to be detected according to the operating status information and the battery data; An impedance data acquisition module, used for acquiring the battery impedance data of the electric energy meter to be detected through the communication connection when the preliminary judgment result of the battery fault is that the battery is suspected to be abnormal; The fault result determination module is used to obtain the battery fault inspection result of the electric energy meter to be detected based on the battery impedance data and the pre-trained electric energy meter battery fault detection model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images