Three-phase electric energy meter automatic detection method and detection system

Abstract

According to the three-phase electric energy meter automatic detection method and system, an AGV trolley is used for transporting a three-phase electric energy meter, and transmission information data are recorded; testing the conveyed three-phase electric energy meter to obtain an actual detection result; the trained performance prediction model is used to carry out performance testing on a to-be-detected three-phase electric energy meter, and a performance prediction model feedback result is obtained; calculating relative entropy data in combination with an actual detection result and a feedback result of the performance prediction model; based on the relative entropy data and the corresponding transmission information data of the three-phase electric energy meter, outputting periodic feedback data of the three-phase electric energy meter; and forming a built-in factory nameplate of the three-phase electric energy meter based on the periodic feedback data, and registering the built-in factory nameplate in the cloud database to form a data traceability channel. According to the invention, human factors can be effectively eliminated, the test accuracy is improved, data traceability is ensured, and the reliability and efficiency of quality control and performance verification are improved.

Description

Technical Field

[0001] This invention belongs to the field of automated testing technology for electricity meters, and particularly relates to an automated testing method and system for three-phase electricity meters. Background Technology

[0002] With the rapid development of smart grids, smart meters, as key metering devices in power systems, have expanded their functions from traditional energy measurement to advanced applications such as data acquisition, remote communication, two-way interaction, and load control. To ensure the metering accuracy, functional reliability, and long-term stability of smart meters, manufacturers must conduct rigorous testing before shipment, covering multiple dimensions including electrical performance, communication protocols, environmental adaptability, and safety protection. Traditional manual testing methods rely on manual operation, visual inspection, and dispersed testing equipment, resulting in low efficiency, high error rates, and inconsistent testing standards. Especially in mass production scenarios, manual testing struggles to meet the requirements of high precision and high reliability, potentially leading to substandard products entering the market and impacting power grid company metering and settlement, as well as user electricity experience.

[0003] In recent years, the introduction of automated testing technology has provided an efficient solution for smart meter testing. Through computer-controlled transport, preset standard testing procedures, and automatic analysis and storage of test data, it enables parallel testing of multiple meters and automatic recording of test data. For example, patent document CN106501753A describes an automated testing line that completes the testing process of three-phase meters. This line includes multiple units such as a loading robot, a withstand voltage testing unit, a functional testing unit, pre- and post-verification buffer units, a multi-functional verification unit, laser marking, sealing, and labeling, automatically completing the testing, coding, packaging, labeling, and pass / fail sorting of the meters. Another example is patent document CN102721940A, which provides a fully automated testing system including an intelligent storage interface, a loading unit, appearance inspection, withstand voltage testing, functional error detection, load testing, zeroing / keying, automatic sealing, and labeling units. The system automatically adjusts the meter position and completes various testing tasks through robots and robotic arms. However, current testing methods lack specific analytical procedures for the testing cycle of electricity meters after they leave the factory; instead, they rely on fixed factory nameplate records. During the automated testing process, transportation, securing, and disassembly often cause wear and tear on the electricity meters, leading to discrepancies between subsequent testing cycles and laboratory testing cycles, resulting in a lack of sufficient data support.

[0004] Therefore, there is an urgent need for an automated testing method for three-phase energy meters that can combine transportation parameters, changes in testing cycles, and loss prediction. By precisely controlling the testing process, automatically recording data, and providing a basis for cycle adjustment, this method can ensure that the testing process of energy meters is more stable and efficient, avoid the influence of human factors on test results, and achieve comprehensive and accurate performance verification and quality control. Summary of the Invention

[0005] To address the technical problems in existing technologies, such as the lack of flexibility and data support due to the failure to set testing cycles based on the actual conditions of the electricity meter, this invention provides an automated testing system and method for three-phase electricity meters.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution.

[0007] This invention proposes an automated detection method for three-phase energy meters, comprising: S1. Use an AGV (Automated Guided Vehicle) to transport three-phase energy meters and record the transport information data; test the transported three-phase energy meters to obtain the actual test results. S2, Use the trained performance prediction model to perform performance tests on the three-phase energy meter to be tested, and obtain the feedback results of the performance prediction model; Combine the actual test results and the feedback results of the performance prediction model to calculate the relative entropy data; S3, based on relative entropy data and the corresponding transmission information data of the three-phase energy meter, outputs the periodic feedback data of the three-phase energy meter; S4, based on periodic feedback data, forms the built-in factory nameplate of the three-phase energy meter, which is registered in the cloud database to form a data traceability channel.

[0008] Further, in S1, the transmitted information data includes: Using a single day as a cycle, the battery level of the AGV vehicle during each transport process in each cycle, the load value of the AGV vehicle during each transport process in each cycle, and the transport sequence of the AGV vehicle in the current cycle. The battery level of the AGV is taken as the average of the battery level at the start of transport and the battery level at the end of transport during each transport process in each cycle.

[0009] Furthermore, in S2, historical transmission information and corresponding historical actual detection results are used as inputs to the performance prediction model for training; the output of the performance prediction model is the performance prediction model feedback result, including the power supply status, power consumption, and electrical performance of the three-phase energy meter.

[0010] Furthermore, in S2, based on the distribution of the result set, the distribution of the actual detection results and the distribution of the predicted detection results from the feedback results of the performance prediction model are obtained respectively. The relative entropy data for each period is generated based on the actual detection result distribution and the predicted detection result distribution: ; in, represent The relative entropy data between them, where q refers to the actual detection model and p refers to the performance prediction model of the automated detection system. Represents the i-th three-phase energy meter The actual distribution of test results; Represents the i-th three-phase energy meter The predicted distribution of test results; N refers to the total number of three-phase energy meters tested in each cycle.

[0011] Furthermore, in S3, based on the relative entropy data of the three-phase energy meters for each cycle, and combined with the transmission information data corresponding to each relative entropy data, a data combination between the transmission information data and the relative entropy data is established. ,in, This refers to the battery level of the AGV (Automated Guided Vehicle) during transportation. This refers to the load capacity of the AGV (Automated Guided Vehicle) during transportation. This refers to the AGV cart's current transport belonging to the [number]th [period] of the current cycle. Secondary transport, Refers to the corresponding relative entropy data; Based on several data combinations To form relative entropy data and Linear fitting function between:

[0012] in, , , These refer to the regression parameters corresponding to each transmitted information data. This represents the error term.

[0013] Furthermore, in S3, if three-phase energy meters from the same batch but different cycles show different relative entropy data, that is, the relative entropy data calculated in the later cycle is increasing relative to the relative entropy data calculated in the previous cycle, it is determined that the transmission information data caused the three-phase energy meter to be defective; where "same batch" refers to the same batch of energy meters produced by the same equipment, and the three-phase energy meters from the same batch are transported in multiple cycles. If the different situations do not occur in three-phase energy meters of the same batch but different cycles, the cycle feedback data of the three-phase energy meter to be tested shall be recorded as the first maintenance cycle time after leaving the factory.

[0014] Furthermore, in S3, if three-phase energy meters of different cycles in the same batch show different relative entropy data, the periodic feedback data of the three-phase energy meters is adjusted based on the transmission information data of the three-phase energy meters.

[0015] Furthermore, in S3, the periodic feedback data is initialized to the first maintenance cycle time after leaving the factory; based on the transmission information data, the three-phase energy meters under the same transmission information data are selected from the historical data to obtain their first alarm maintenance time. If the first alarm maintenance time is earlier than the built-in first maintenance cycle time of the defective three-phase energy meter, the difference between the first alarm maintenance time and the built-in first maintenance cycle time is calculated and combined with the transmission information data to form a new data combination. After obtaining several new data combinations, cross-validation is used to obtain multiple linear fitting function models. Among all the models obtained through training, the linear fitting function with the optimal mean squared error loss function and parameters are selected and retained to obtain the linear fitting function of the interpolated data with respect to the transmitted information data.

[0016] Furthermore, in S3, the selected linear fitting function and the transmission information data of the three-phase energy meter are used to output the periodic feedback data of the three-phase energy meter.

[0017] On the other hand, the present invention also proposes an automated detection system for three-phase energy meters, comprising an AGV conveying module 101, an intelligent detection module 102, a periodic correlation module 103, and a marking module 104, characterized in that: AGV conveying module 101 is used to construct an AGV trolley work line to transport three-phase energy meters to the entrance of the automated detection system, while uploading conveying information data; The intelligent detection module 102, based on the transmitted information data, marks the corresponding three-phase energy meters, calls the performance prediction model feedback result of the automated detection system, and outputs the loss function value between the performance prediction model feedback result and the actual detection result; The periodic correlation module 103 outputs the periodic feedback data of the three-phase energy meter based on the loss function value between the performance prediction model feedback result and the actual detection result and the corresponding transmission information data of the three-phase energy meter. The marking module 104, based on periodic feedback data, forms the built-in factory nameplate of the three-phase energy meter, which is registered in the cloud database to form a data traceability channel.

[0018] Compared with the prior art, the beneficial effects of the present invention are as follows: 1. The intelligent testing module 102 of this invention enables comprehensive testing of various performance aspects of the electricity meter, avoiding the inefficiency and inaccuracy of traditional manual testing. This module can accurately test the electrical performance of the electricity meter, reducing human error and improving test repeatability and reliability. The intelligent testing module not only significantly improves testing efficiency but also records and analyzes test data in real time, providing detailed data for subsequent quality management. This highly efficient automated testing greatly shortens the testing cycle and provides the necessary accuracy for mass production, ensuring that the electricity meter quality meets standards and reducing the risk of substandard products entering the market.

[0019] 2. The periodic correlation module 103 of this invention provides a dynamic adjustment basis during the testing process of smart energy meters by accurately monitoring the meter's testing cycle, transportation parameters, and potential losses during use. Based on the actual usage of the energy meter and historical testing data, this module predicts its performance change trends, thereby effectively adjusting the testing cycle to ensure that the energy meter maintains high accuracy and stability throughout its use. This periodic correlation not only optimizes the maintenance and inspection process of the energy meter but also reduces errors from manual judgment, ensuring the accuracy of the energy meter after long-term operation. Attached Figure Description

[0020] Figure 1 This is a flowchart of an automated testing method for a three-phase energy meter according to the present invention; Figure 2 This is a system structure diagram of an automated detection system for three-phase energy meters according to the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of this invention. The embodiments described in this application are merely some embodiments of this invention, and not all embodiments. Based on the spirit of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of this invention.

[0022] Example 1 This invention provides an automated detection method for three-phase energy meters, such as... Figure 1 As shown, the testing process for electricity meters is precisely controlled through automated detection and periodic adjustments, combined with transportation parameters and loss prediction. This effectively eliminates human error, improves testing accuracy, ensures data traceability, and enhances the reliability and efficiency of quality control and performance verification. The specific solution is as follows.

[0023] S1. Use an AGV (Automated Guided Vehicle) to transport three-phase energy meters and record the transport information data; test the transported three-phase energy meters to obtain the actual test results.

[0024] Specifically, each AGV is equipped with a three-phase power meter; when the AGV is working on the AGV track, the current power status, load, and number of transports made that day are recorded.

[0025] Furthermore, the transmitted information data includes: Using a single day as a cycle, the battery level of the AGV vehicle during each transport process in each cycle, the load value of the AGV vehicle during each transport process in each cycle, and the transport sequence of the AGV vehicle in the current cycle. The battery level of the AGV is taken as the average of the battery level at the start of transport and the battery level at the end of transport during each transport process in each cycle.

[0026] Furthermore, the three-phase energy meter was tested, including connection and disconnection tests, appearance tests, power-on inspection tests, power consumption tests, and electrical performance tests, to obtain actual test results. Among them, the electrical performance tests included voltage influence tests, frequency influence tests, harmonic influence tests, and short-time overcurrent influence tests.

[0027] S2, use the trained performance prediction model to perform performance testing on the three-phase energy meter to be tested, and obtain the feedback result of the performance prediction model; combine the actual test results and the feedback result of the performance prediction model to calculate the loss function value.

[0028] Specifically, the performance prediction model can be any existing technology, including but not limited to regression models and deep learning models. The structure of the performance prediction model will not be elaborated upon here. To train the performance prediction model, historical transmission information and corresponding historical actual detection results are required. The performance prediction model output includes various performance parameters of the three-phase energy meter, such as power supply status, power consumption, and electrical performance.

[0029] Furthermore, based on the distribution of the result set, the distribution of the actual detection results and the distribution of the predicted detection results from the feedback results of the performance prediction model are obtained respectively.

[0030] The relative entropy data for each period is generated based on the distribution of actual detection results and the distribution of predicted detection results. This data serves as the loss function value between the output performance prediction model feedback result and the actual detection result. ; in, represent The relative entropy data between them, where q refers to the actual detection model and p refers to the performance prediction model of the automated detection system. Represents the i-th three-phase energy meter The actual distribution of test results; Represents the i-th three-phase energy meter The predicted distribution of test results; N refers to the total number of three-phase energy meters tested in each cycle.

[0031] Specifically, due to and These are probability distributions for four types of tests, such as those in relative entropy. This item, extract respectively and Each element in the algorithm is processed individually. After all elements have been processed, the results of all processed elements are summed to obtain the final result. The calculation results.

[0032] After further processing, when the performance prediction model is fixed, If the data is in a constant state, calculating the minimum relative entropy data simplifies to calculating... The maximum value is sufficient.

[0033] S3, based on the loss function value and the corresponding transmission information data of the three-phase energy meter, outputs the periodic feedback data of the three-phase energy meter.

[0034] Specifically, based on the loss function value of the three-phase energy meter in each cycle, i.e., the relative entropy data, and combined with the corresponding transmission information data for each relative entropy data, a data combination between the transmission information data and the relative entropy data is established. ,in, This refers to the battery level of the AGV (Automated Guided Vehicle) during transportation. This refers to the load capacity of the AGV (Automated Guided Vehicle) during transportation. This refers to the AGV cart's current transport belonging to the [number]th [period] of the current cycle. Secondary transport, Refers to the corresponding relative entropy data; Based on several data combinations To form relative entropy data and Linear fitting function between:

[0035] in, , , These refer to the regression parameters corresponding to each transmitted information data. This represents the error term.

[0036] Furthermore, the fitted relative entropy data The magnitude of the relative entropy reflects the accuracy of the performance prediction model of the automated testing system. Without changing the performance prediction model, if three-phase energy meters from the same batch but different cycles show different relative entropy data (i.e., the relative entropy data calculated in the later cycle is increasing compared to the relative entropy data calculated in the previous cycle), it is determined that the transmitted information data caused a defect in the three-phase energy meter. Here, "same batch" refers to energy meters produced by the same equipment in the same batch, which can be considered as completely identical energy meters. Three-phase energy meters from the same batch are transported in multiple cycles. If three-phase energy meters from the same batch but different cycles do not show the above situation, the cycle feedback data of the three-phase energy meter to be tested is recorded as the first maintenance cycle time after leaving the factory.

[0037] Furthermore, based on the transmitted information data and the judgment results of defects in the three-phase energy meters, the periodic feedback data of the three-phase energy meters are adjusted.

[0038] Specifically, the periodic feedback data is initialized to the first maintenance cycle time after leaving the factory. Based on the transmission information data, three-phase energy meters with the same transmission information data are selected from historical data to obtain their first alarm maintenance time. If the first alarm maintenance time is earlier than the built-in first maintenance cycle time of the defective three-phase energy meter, the difference between the first alarm maintenance time and the built-in first maintenance cycle time is calculated and recorded as a new data combination. ,in, This refers to the difference between the time of the first alarm inspection and the built-in first inspection cycle time, and several sets of data combinations are obtained. Subsequently, to obtain a linear fitting function of the interpolated data with respect to the transmission information data, a dataset U is established. Dataset U is randomly divided into S mutually exclusive subsets of equal size, where S is a system-defined constant. Each time, S-1 subsets are randomly selected as the training set for the linear fitting function, and the remaining subset is used as the test set. After training, S-1 subsets are randomly selected again for training, with the number of training iterations set to be less than S. Random selection stops after reaching the required number of training iterations. Among all trained models, the model with the optimal loss function and parameters are selected and retained to obtain the linear fitting function of the interpolated data with respect to the transmission information data. In a preferred embodiment of this invention, the mean squared error loss function is used. Using the selected linear fitting function and the transmission information data from the three-phase energy meter, the periodic feedback data of the three-phase energy meter is output.

[0039] S4, based on periodic feedback data, forms the built-in factory nameplate of the three-phase energy meter, and at the same time, it is registered in the cloud database at the system end to form a data traceability channel.

[0040] Specifically, the system acquires periodic feedback data without altering the actual nameplate data on the three-phase energy meter, adjusts the periodic detection time, generates a built-in factory nameplate, and records the modification process as a digital path, storing it on the system's built-in storage chip to form data traceability.

[0041] Example 2 This invention provides an automated detection system for three-phase energy meters, such as... Figure 2 As shown, the system includes an AGV conveying module 101, an intelligent detection module 102, a periodic correlation module 103, and a marking module 104.

[0042] Specifically, the AGV conveying module 101 is used to construct the AGV trolley work line, convey the three-phase energy meter to be tested to the entrance of the automated testing system, and upload the conveying information data at the same time.

[0043] The construction of the AGV (Automated Guided Vehicle) work line includes: A three-phase energy meter storage platform is provided. This platform is externally connected to several AGV (Automated Guided Vehicle) tracks, each connected to the entrance of an automated detection system. Each AGV track has a built-in cloud chip. When an AGV operates on a track, the cloud chip records the AGV's current battery status, load capacity, and the number of trips made that day. As an example of this invention, when any AGV is operating on its track, data such as its current battery status (60%), load capacity (1 kg), and the number of trips made that day can be obtained. The AGV cart work line also includes several empty box carts, which are used to accommodate several AGV carts equipped with three-phase power meters; specifically, the bottom area of ​​the several empty box carts should be compatible with the AGV cart's cargo box, and they are equipped with connecting devices to achieve mutual connection; one AGV cart corresponds to one three-phase power meter.

[0044] The three-phase energy meter storage platform is also connected to a robot control system, with a robotic arm fixed at the top. The robot control system controls the robotic arm to grab the three-phase energy meters in the three-phase energy meter storage platform. The robotic arm identifies the position of the AGV trolley based on the identification device and places the grabbed three-phase energy meters into the empty box of the AGV trolley.

[0045] The transmitted information data includes: Using a single day as a cycle, the battery level of the AGV vehicle during each transport process in each cycle, the load value of the AGV vehicle during each transport process in each cycle, and the transport sequence of the AGV vehicle in the current cycle. The battery level of the AGV is taken as the average of the battery level at the start of transport and the battery level at the end of transport during each transport process in each cycle.

[0046] The automated detection system specifically includes: The hardware port is used for automated hardware-related testing of three-phase energy meters. Instructions are issued through the intelligent detection module 102, received by the transmission layer, and then transmitted to the subordinate control units, including a feeding unit, a wiring connection / disconnection unit, and an appearance observation unit. The feeding unit interfaces with the automated testing system's entry point to automatically feed the three-phase energy meters to be tested. The wiring connection / disconnection unit implements the wiring connection and disconnection functions of the three-phase energy meters. The appearance observation unit is used to identify and observe whether the three-phase energy meters have any external damage. Specifically, the intelligent detection module can be, but is not limited to, embedded systems, IoT, and PLC technologies, as long as it can achieve the functions of an intelligent detection module; further details on existing technologies are omitted here.

[0047] The software port is used to perform new functional checks on the three-phase energy meter connected via the hardware port. Specifically, it includes a power-on check unit, a power consumption test unit, and an electrical performance test unit. The power-on check unit checks the power supply of the three-phase energy meter's circuit. The power consumption test unit tests the power consumption of the three-phase energy meter. The electrical performance test unit implements voltage influence testing, frequency influence testing, harmonic influence testing, and short-time overcurrent influence testing through test programming. Specifically, the power consumption test unit can use digital energy metering chips, analog power supply load systems, etc.; the voltage influence test can use adjustable power supplies, voltage sensors, etc.; the frequency influence test can use frequency generators, oscilloscopes, etc.; the harmonic influence test can use digital signal processing technologies; and the short-time overcurrent influence test can use overcurrent testing devices, relays, and circuit breakers, etc. These existing technologies will not be elaborated further here.

[0048] The software port is connected to an execution layer, which is used to summarize test results, select products that fail the test, and simultaneously summarize the test pass rate and feed it back to the performance prediction model port.

[0049] Furthermore, the intelligent detection module 102, based on the transmitted information data tagging of the corresponding three-phase energy meter, calls the performance prediction model feedback result of the automated detection system, and outputs the loss function value between the performance prediction model feedback result and the actual detection result.

[0050] Specifically, the inputs to the performance prediction model include historical data of the transmission information and historical detection data of the corresponding automated detection system. The output feedback results of the performance prediction model include various performance parameters of the three-phase energy meter, such as power supply status, power consumption, and electrical performance. The performance prediction model can be any existing technology, including but not limited to regression models and deep learning models, which will not be elaborated upon here.

[0051] Specifically, the test results of each three-phase energy meter on different tests are obtained, and the actual test result distribution is formed based on the result set distribution; the performance prediction model of the automated testing system is used to obtain the predicted results of each three-phase energy meter on different tests, and the predicted test result distribution is formed based on the result set distribution. The relative entropy data for each period is generated based on the distribution of actual detection results and the distribution of predicted detection results. This data serves as the loss function value between the output performance prediction model feedback result and the actual detection result. ; in, represent The relative entropy data between them, where q refers to the actual detection model and p refers to the performance prediction model of the automated detection system. Represents the i-th three-phase energy meter The actual distribution of test results; Represents the i-th three-phase energy meter The predicted distribution of test results; N refers to the total number of three-phase energy meters tested in each cycle; Specifically, the softmax regression principle is used to... and The data is processed, and the log calculation is base 10, i.e., lg, to form the relative entropy data of each detected three-phase energy meter.

[0052] Taking partial data as an example, the actual detection result distribution is set to include: voltage influence test, frequency influence test, harmonic influence test, and short-time overcurrent influence test; the predicted detection result distribution is set to be the same as the actual detection result distribution, and the distributed data is processed based on the softmax regression principle to form a single data, namely relative entropy data.

[0053] The formula for calculating relative entropy data is: ; Specifically, due to and These are probability distributions for four types of tests, such as those in relative entropy. This item, extract respectively and Each element in the algorithm is processed individually. After all elements have been processed, the results of all processed elements are summed to obtain the final result. The calculation results. After further processing, when the performance prediction model is fixed, If the data is in a constant state, calculating the minimum relative entropy data simplifies to calculating... The maximum value is sufficient.

[0054] The intelligent testing module 102 achieves efficient testing of electricity meters through automated control of the testing process. This module can monitor and record data in real time, automatically analyze test results, reduce manual intervention, and lower the false positive rate. By precisely controlling each testing step, it ensures consistency and high accuracy in testing, thus contributing to improved product quality.

[0055] Furthermore, the periodic correlation module 103 outputs the periodic feedback data of the three-phase energy meter based on the loss function value between the performance prediction model feedback result and the actual detection result and the corresponding transmission information data of the three-phase energy meter.

[0056] Specifically, based on the loss function value of the three-phase energy meter in each cycle, i.e., the relative entropy data, and combined with the corresponding transmission information data for each relative entropy data, a data combination between the transmission information data and the relative entropy data is established. ,in, This refers to the battery level of the AGV (Automated Guided Vehicle) during transportation. This refers to the load capacity of the AGV (Automated Guided Vehicle) during transportation. This refers to the AGV cart's current transport belonging to the [number]th [period] of the current cycle. Secondary transport, Refers to the corresponding relative entropy data; Based on several data combinations To form relative entropy data and Linear fitting function between:

[0057] in, , , These refer to the regression parameters corresponding to each transmitted information data. This represents the error term.

[0058] Furthermore, the fitted relative entropy data The magnitude of the relative entropy reflects the accuracy of the performance prediction model of the automated testing system. Without changing the performance prediction model, if three-phase energy meters from the same batch but different cycles show different relative entropy data (i.e., the relative entropy data calculated in the later cycle is increasing compared to the relative entropy data calculated in the previous cycle), it is determined that the transmitted information data caused a defect in the three-phase energy meter. Here, "same batch" refers to energy meters produced by the same equipment in the same batch, which can be considered as completely identical energy meters. Three-phase energy meters from the same batch are transported in multiple cycles. If three-phase energy meters from the same batch but different cycles do not show the above situation, the cycle feedback data of the three-phase energy meter to be tested is recorded as the first maintenance cycle time after leaving the factory.

[0059] Furthermore, based on the transmitted information data and the judgment results that led to the defects in the three-phase energy meter, the periodic feedback data of the three-phase energy meter is adjusted.

[0060] Specifically, the periodic feedback data is initialized to the first maintenance cycle time after leaving the factory. Based on the transmission information data, three-phase energy meters with the same transmission information data are selected from historical data to obtain their first alarm maintenance time. If the first alarm maintenance time is earlier than the built-in first maintenance cycle time of the defective three-phase energy meter, the difference between the first alarm maintenance time and the built-in first maintenance cycle time is calculated and recorded as a new data combination. ,in, This refers to the difference between the time of the first alarm inspection and the built-in first inspection cycle time, and several sets of data combinations are obtained. Subsequently, to obtain a linear fitting function of the interpolated data with respect to the transmission information data, a dataset U is established. Dataset U is randomly divided into S mutually exclusive subsets of equal size, where S is a system-defined constant. Each time, S-1 subsets are randomly selected as the training set for the linear fitting function, and the remaining subset is used as the test set. After training, S-1 subsets are randomly selected again for training, with the number of training iterations set to be less than S. Random selection stops after reaching the required number of training iterations. Among all trained models, the model with the optimal loss function and parameters are selected and retained to obtain the linear fitting function of the interpolated data with respect to the transmission information data. In a preferred embodiment of this invention, the mean squared error loss function is used. Using the linear fitting function and the transmission information data of the three-phase energy meter under test, the periodic feedback data of the three-phase energy meter is output.

[0061] The cycle correlation module 103 can dynamically adjust the detection cycle of the electricity meter by combining transportation parameters, detection cycle, and loss prediction. This module analyzes the usage and transportation of the electricity meter through intelligent algorithms, accurately predicts its status changes, and adjusts the detection strategy in a timely manner to avoid deviations caused by transportation or loss, thereby improving the long-term stability and accuracy of the electricity meter.

[0062] Furthermore, the marking module 104, based on periodic feedback data, forms a built-in factory nameplate for the three-phase energy meter, and simultaneously registers it in the cloud database at the system end, forming a data traceability channel.

[0063] Specifically, the system acquires periodic feedback data without altering the actual nameplate data on the three-phase energy meter, adjusts the periodic detection time within the system, generates a built-in factory nameplate, and records the modification process as a digital path, storing it on the system's built-in storage chip to form data traceability.

[0064] The tagging module 104 generates a built-in factory nameplate for the three-phase energy meter based on periodic feedback data and registers it in the cloud database, forming a data traceability channel. This effectively traces the energy meter's testing process and adjustment history, ensuring accurate recording of each periodic adjustment without modifying the actual nameplate data. Digital path recording provides reliable support for subsequent quality management and data verification, improving data transparency and traceability, and enhancing the system's credibility and security.

[0065] This application also provides a computer program product, which includes computer program code. When the computer program code is run on a computer, it enables the computer to implement the contents of the above embodiments of this application. This application also provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the contents of the above embodiments of this application. Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the platforms, devices, and units described above can be referred to the corresponding processes in the foregoing embodiments, and will not be repeated here.

[0066] The use of prefixes such as "first" and "second" in this application embodiment is solely for distinguishing different descriptive objects and does not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes to distinguish descriptive objects in this application embodiment does not constitute a limitation on the described objects. The description of the described objects is found in the claims or the context of the embodiments, and the use of such prefixes should not constitute unnecessary restrictions. In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms. In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between the various embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0067] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0068] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An automated detection method for three-phase energy meters, characterized in that, include: S1. Use an AGV (Automated Guided Vehicle) to transport three-phase energy meters and record the transport information data; test the transported three-phase energy meters to obtain the actual test results. S2, Use the trained performance prediction model to perform performance tests on the three-phase energy meter to be tested, and obtain the feedback results of the performance prediction model; Combine the actual test results and the feedback results of the performance prediction model to calculate the relative entropy data; S3, based on relative entropy data and the corresponding transmission information data of the three-phase energy meter, outputs the periodic feedback data of the three-phase energy meter; S4, based on periodic feedback data, forms the built-in factory nameplate of the three-phase energy meter, which is registered in the cloud database to form a data traceability channel.

2. The automated detection method for a three-phase energy meter according to claim 1, characterized in that: In S1, the transmitted information data includes: Using a single day as a cycle, the battery level of the AGV vehicle during each transport process in each cycle, the load value of the AGV vehicle during each transport process in each cycle, and the transport sequence of the AGV vehicle in the current cycle. The battery level of the AGV is taken as the average of the battery level at the start of transport and the battery level at the end of transport during each transport process in each cycle.

3. The automated detection method for a three-phase energy meter according to claim 1, characterized in that: In S2, historical transmission information and corresponding historical actual detection results are used as inputs to the performance prediction model for training; the output of the performance prediction model is the performance prediction model feedback result, including the power supply status, power consumption, and electrical performance of the three-phase energy meter.

4. An automated detection method for a three-phase energy meter according to claim 1 or 3, characterized in that: In S2, based on the distribution of the result set, the distribution of the actual detection results and the distribution of the predicted detection results from the feedback results of the performance prediction model are obtained respectively. The relative entropy data for each period is generated based on the actual detection result distribution and the predicted detection result distribution: ； in, represent The relative entropy data between them, where q refers to the actual detection model and p refers to the performance prediction model of the automated detection system. Represents the i-th three-phase energy meter The actual distribution of test results; Represents the i-th three-phase energy meter The predicted distribution of test results; N refers to the total number of three-phase energy meters tested in each cycle.

5. The automated detection method for a three-phase energy meter according to claim 1, characterized in that: In S3, based on the relative entropy data of the three-phase energy meters for each cycle, and combined with the corresponding transmission information data for each relative entropy data, a data combination between the transmission information data and the relative entropy data is established. ,in, This refers to the battery level of the AGV (Automated Guided Vehicle) during transportation. This refers to the load capacity of the AGV (Automated Guided Vehicle) during transportation. This refers to the AGV cart's current transport belonging to the [number]th [period] of the current cycle. Secondary transport, Refers to the corresponding relative entropy data; Based on several data combinations To form relative entropy data and Linear fitting function between: in, , , These refer to the regression parameters corresponding to each transmitted information data. This represents the error term.

6. An automated detection method for a three-phase energy meter according to claim 1 or 5, characterized in that: In S3, if three-phase energy meters from the same batch but different cycles show different relative entropy data, that is, the relative entropy data calculated in the later cycle is increasing relative to the relative entropy data calculated in the previous cycle, it is judged that the transmission information data caused the three-phase energy meter to be defective; where "same batch" refers to the same batch of energy meters produced by the same equipment, and the three-phase energy meters in the same batch are transported in multiple cycles. If the different situations do not occur in three-phase energy meters of the same batch but different cycles, the cycle feedback data of the three-phase energy meter to be tested shall be recorded as the first maintenance cycle time after leaving the factory.

7. The automated detection method for a three-phase energy meter according to claim 6, characterized in that: In S3, if three-phase energy meters of different cycles in the same batch show different relative entropy data, the periodic feedback data of the three-phase energy meters is adjusted based on the transmission information data of the three-phase energy meters.

8. The automated detection method for a three-phase energy meter according to claim 7, characterized in that: In S3, the periodic feedback data is initialized to the time of the first maintenance cycle after leaving the factory; Based on the transmission information data, select the factory-made three-phase energy meters with the same transmission information data in the historical data, and obtain the time of their first alarm maintenance. If the time of the first alarm maintenance is earlier than the built-in first maintenance cycle time of the defective three-phase energy meter, calculate the difference between the time of the first alarm maintenance and the built-in first maintenance cycle time, and combine it with the transmission information data to form a new data combination. After obtaining several new data combinations, cross-validation is used to obtain multiple linear fitting function models. Among all the models obtained through training, the linear fitting function with the optimal mean squared error loss function and parameters are selected and retained to obtain the linear fitting function of the interpolated data with respect to the transmitted information data.

9. The automated detection method for a three-phase energy meter according to claim 8, characterized in that: In S3, the selected linear fitting function and the transmission information data of the three-phase energy meter are used to output the periodic feedback data of the three-phase energy meter.

10. An automated testing system for a three-phase energy meter based on the automated testing method according to any one of claims 1-9, comprising an AGV conveying module (101), an intelligent testing module (102), a periodic correlation module (103), and a marking module (104), characterized in that: The AGV conveying module (101) is used to construct the AGV trolley work line, conveying the three-phase energy meter to the entrance of the automated detection system, and uploading the conveying information data at the same time; The intelligent detection module (102) marks the corresponding three-phase energy meters based on the transmitted information data, calls the performance prediction model feedback result of the automated detection system, and outputs the loss function value between the performance prediction model feedback result and the actual detection result; The periodic correlation module (103) outputs the periodic feedback data of the three-phase energy meter based on the loss function value between the performance prediction model feedback result and the actual detection result and the corresponding transmission information data of the three-phase energy meter. The marking module (104) forms the built-in factory nameplate of the three-phase energy meter based on the periodic feedback data, and registers it in the cloud database to form a data traceability channel.

Images