Smart meter disconnection timing analysis system

Abstract

The present invention relates to a smart meter disconnection timing analysis system, including: an induction prediction device, which is used to use an AI prediction body to intelligently predict the predicted value of the induction current of the target meter at the next moment of the current moment based on the respective induction currents corresponding to the target meter at each past moment before the current moment, the configuration data of the target meter user's current load, multiple reference information of the target meter, and the number of loads currently used by the target meter user; a timing judgment device, which is used to judge whether the next moment of the current moment is a high-risk disconnection moment of the target meter based on the predicted value. Through the present invention, a customized AI prediction body can be used to intelligently predict the predicted value of the induction current of the target meter at the next moment of the current moment, and then judge whether the next moment of the current moment is a high-risk disconnection moment of the target meter, thereby completing the intelligent prejudgment of whether each meter's future moment is a high-risk opportunity.

Description

Technical Field

[0001] The present invention relates to the field of smart electric meters, and in particular to a disconnection timing analysis system for smart electric meters. Background Art

[0002] Smart meters are important devices for measuring electric energy, and the timing of smart meter disconnection is somewhat accidental. For example, when the coil and core of the smart meter are affected by the electromagnetic field to generate magnetic flux, an induced current will be generated. When the load is too large, the induced current will exceed the rated current of the smart meter, causing the smart meter to disconnect. However, since the rated power of each load is different and the working current of each load fluctuates, when the working currents of multiple loads fluctuate by different amplitudes, it is difficult to predict the induced current generated by the smart meter in the future, and thus it is difficult to predict the disconnection timing of the smart meter, which hinders the prevention and investigation of high-risk accidents.

[0003] For an electric meter, if its induced current is greater than its rated current at a certain moment, this moment is the high-risk disconnection moment of the electric meter, otherwise, this moment is the low-risk disconnection moment of the electric meter. However, the existing technology can only determine whether the current moment or the past moment is a high-risk disconnection moment or a low-risk disconnection moment, but cannot determine whether the future moment is a high-risk disconnection moment or a low-risk disconnection moment. The key is that there is a lack of an effective prediction mechanism for the induced current of the electric meter at future moments. Summary of the invention

[0004] In order to solve the technical problems in the prior art, the present invention provides a smart meter disconnection timing analysis system, which can design an AI prediction body with a customized structure for the intelligent prediction of the induced current of the target meter at the next moment after the current moment. Specifically, the AI ​​prediction body is a radial basis function neural network after each training, and the number of training times is positively correlated with the number of coil turns of the target meter, so that different AI prediction bodies are designed for different target meters, and then a plurality of basic data are targetedly screened for the intelligent prediction of the induced current of the target meter at the next moment after the current moment to ensure the reliability and stability of the intelligent prediction results, the plurality of basic data include the induced currents corresponding to the past moments before the current moment, the configuration data of the load currently used by the user of the target meter, and a plurality of reference information of the target meter. The configuration data of the load currently used by the target meter user includes the rated power of each share, the upper limit value of each working current and the lower limit value of each working current corresponding to each load currently used by the target meter user, and multiple reference information of the target meter, including the number of coil turns, coil cross-sectional diameter, coil resistance, meter core weight and meter core volume of the target meter. Finally, a timing judgment device is introduced for intelligent prediction. When the predicted value of the induced current of the target meter at the next moment after the current moment is greater than the rated current of the target meter, the next moment after the current moment is used as the high-risk disconnection moment of the target meter. Otherwise, the next moment after the current moment is used as the low-risk disconnection moment of the target meter, thereby completing the intelligent prediction of the high-risk timing of each meter and providing key reference information for avoiding and troubleshooting the high-risk timing of the meter.

[0005] According to the present invention, a smart meter disconnection timing analysis system is provided, the system comprising:

[0006] A data capture mechanism, used to obtain configuration data of a load currently used by a target meter user, wherein the configuration data of the load currently used by the target meter user includes each share of rated power, each share of working current upper limit value, and each share of working current lower limit value corresponding to each load currently used by the target meter user, and the target meter is a smart meter;

[0007] An information collection mechanism is used to obtain the number of coil turns, coil cross-sectional diameter, coil resistance, meter core weight and meter core volume of the target electric meter, and output the number of coil turns, coil cross-sectional diameter, coil resistance, meter core weight and meter core volume of the target electric meter as multiple reference information of the target electric meter;

[0008] A network reconstruction mechanism is used to perform a preset number of trainings on the radial basis neural network to obtain the radial basis neural network after each training, and output the radial basis neural network after each training as an AI prediction body, wherein the value of the preset number is positively correlated with the number of coil turns of the target electric meter;

[0009] The induction prediction device is connected to the data capture mechanism, the information collection mechanism and the network reconstruction mechanism respectively, and is used to use the AI ​​prediction body to intelligently predict the predicted value of the induction current of the target meter at the next moment after the current moment based on the respective induction currents corresponding to the target meter at each past moment before the current moment, the configuration data of the load currently used by the user of the target meter, multiple reference information of the target meter and the number of loads currently used by the user of the target meter;

[0010] A timing judgment device is connected to the induction prediction device, and is used to use the next moment after the current moment as the high-risk disconnection moment of the target meter when the predicted value of the induction current of the target meter after the current moment is greater than the rated current of the target meter;

[0011] The timing judgment device is further used to use the next moment after the current moment as the low-risk disconnection moment of the target meter when the predicted value of the induced current of the target meter after the current moment is less than or equal to the rated current of the target meter;

[0012] Among them, the AI ​​prediction body is used to intelligently predict the predicted value of the induced current of the target meter at the next moment of the current moment based on the respective induced currents corresponding to the target meter at each past moment before the current moment, the configuration data of the load currently used by the target meter user, multiple reference information of the target meter and the number of loads currently used by the target meter user. The predicted value includes: each past moment before the current moment includes the current moment, and each past moment before the current moment and the next moment of the current moment are evenly spaced on the time axis;

[0013] Among them, the AI ​​prediction body is used to intelligently predict the induced current of the target meter at the next moment of the current moment based on the respective induced currents corresponding to the target meter at each past moment before the current moment, the configuration data of the target meter user's current load, multiple reference information of the target meter and the number of loads currently used by the target meter user. The predicted value of the induced current of the target meter at the next moment of the current moment also includes: the number of moments of each past moment before the current moment is proportional to the number of loads currently used by the target meter user.

[0014] Therefore, the present invention has at least the following three important invention points:

[0015] Invention point A: Designing an AI prediction body with a customized structure for intelligent prediction of the induced current of the target meter at the next moment after the current moment. Specifically, the AI ​​prediction body is a radial basis neural network after each training, and the number of training times is positively correlated with the number of coil turns of the target meter, so that different AI prediction bodies are designed for different target meters;

[0016] Invention point B: For the intelligent prediction of the induced current of the target meter at the next moment after the current moment, multiple basic data are targeted to ensure the reliability and stability of the intelligent prediction result, wherein the multiple basic data include the induced currents corresponding to the past moments before the current moment, the configuration data of the load currently used by the target meter user, and multiple reference information of the target meter, wherein the configuration data of the load currently used by the target meter user includes the rated power of each share corresponding to each load currently used by the target meter user, the upper limit value of each working current, and the lower limit value of each working current, and the multiple reference information of the target meter are the number of coil turns, coil cross-sectional diameter, coil resistance, meter core weight, and meter core volume of the target meter;

[0017] Invention point C: When the predicted value of the induced current of the target meter at the next moment after the current moment is greater than the rated current of the target meter, the next moment after the current moment is used as the high-risk disconnection moment of the target meter; otherwise, the next moment after the current moment is used as the low-risk disconnection moment of the target meter, thereby completing the intelligent prediction of the high-risk timing of each meter and providing key reference information for avoiding and troubleshooting the high-risk timing of the meter. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0019] Figure 1 Schematic diagram of the internal structure of a smart meter disconnection timing analysis system according to implementation A of the present invention.

[0020] Figure 2 Schematic diagram of the internal structure of a smart meter disconnection timing analysis system according to implementation B of the present invention.

[0021] Figure 3 Schematic diagram of the internal structure of a smart meter disconnection timing analysis system according to implementation scheme C of the present invention. DETAILED DESCRIPTION

[0022] The implementation scheme of the smart meter disconnection timing analysis system of the present invention will be described in detail below with reference to the accompanying drawings.

[0023] Figure 1 This is a schematic diagram of the internal structure of a smart meter disconnection timing analysis system according to Embodiment A of the present invention, wherein the system comprises:

[0024] A data capture mechanism, used to obtain configuration data of a load currently used by a target meter user, wherein the configuration data of the load currently used by the target meter user includes each share of rated power, each share of working current upper limit value, and each share of working current lower limit value corresponding to each load currently used by the target meter user, and the target meter is a smart meter;

[0025] For example, a data capture mechanism is used to obtain configuration data of a load currently used by a target meter user, wherein the configuration data of the load currently used by the target meter user includes each share of rated power, each share of upper limit value of working current, and each share of lower limit value of working current corresponding to each load currently used by the target meter user, and the target meter is a smart meter including: the data capture mechanism has multiple parameter capture components built in, which are used to respectively obtain each share of rated power, each share of upper limit value of working current, and each share of lower limit value of working current corresponding to each load currently used by the target meter user;

[0026] An information collection mechanism is used to obtain the number of coil turns, coil cross-sectional diameter, coil resistance, meter core weight and meter core volume of the target electric meter, and output the number of coil turns, coil cross-sectional diameter, coil resistance, meter core weight and meter core volume of the target electric meter as multiple reference information of the target electric meter;

[0027] A network reconstruction mechanism is used to perform a preset number of trainings on the radial basis neural network to obtain the radial basis neural network after each training, and output the radial basis neural network after each training as an AI prediction body, wherein the value of the preset number is positively correlated with the number of coil turns of the target electric meter;

[0028] The induction prediction device is connected to the data capture mechanism, the information collection mechanism and the network reconstruction mechanism respectively, and is used to use the AI ​​prediction body to intelligently predict the predicted value of the induction current of the target meter at the next moment after the current moment based on the respective induction currents corresponding to the target meter at each past moment before the current moment, the configuration data of the load currently used by the user of the target meter, multiple reference information of the target meter and the number of loads currently used by the user of the target meter;

[0029] A timing judgment device is connected to the induction prediction device, and is used to use the next moment after the current moment as the high-risk disconnection moment of the target meter when the predicted value of the induction current of the target meter after the current moment is greater than the rated current of the target meter;

[0030] The timing judgment device is further used to use the next moment after the current moment as the low-risk disconnection moment of the target meter when the predicted value of the induced current of the target meter after the current moment is less than or equal to the rated current of the target meter;

[0031] Among them, the AI ​​prediction body is used to intelligently predict the predicted value of the induced current of the target meter at the next moment of the current moment based on the respective induced currents corresponding to the target meter at each past moment before the current moment, the configuration data of the load currently used by the target meter user, multiple reference information of the target meter and the number of loads currently used by the target meter user. The predicted value includes: each past moment before the current moment includes the current moment, and each past moment before the current moment and the next moment of the current moment are evenly spaced on the time axis;

[0032] Among them, the AI ​​prediction body is used to intelligently predict the predicted value of the induced current of the target meter at the next moment of the current moment based on the respective induced currents corresponding to the target meter at each past moment before the current moment, the configuration data of the load currently used by the target meter user, multiple reference information of the target meter and the number of loads currently used by the target meter user. The predicted value also includes: the number of moments of each past moment before the current moment is proportional to the number of loads currently used by the target meter user;

[0033] The configuration data of the load currently used by the target meter user is obtained, and the configuration data of the load currently used by the target meter user includes the rated power of each share, the upper limit value of each working current, and the lower limit value of each working current corresponding to each load currently used by the target meter user, including: for each load, the specific value of its working current is between the upper limit value of its corresponding working current and the lower limit value of its corresponding working current;

[0034] Among them, a preset number of trainings are performed on the radial basis neural network to obtain the radial basis neural network after each training, and the radial basis neural network after each training is output as an AI prediction body, and the value of the preset number is positively correlated with the number of coil turns of the target electric meter, including: the more the number of coil turns of the target electric meter, the larger the value of the preset number.

[0035] Figure 2 Schematic diagram of the internal structure of a smart meter disconnection timing analysis system according to implementation B of the present invention.

[0036] Compared with implementation A, the smart meter disconnection timing analysis system shown in implementation B may further include the following components:

[0037] An ASIC control chip is connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism respectively, and is used to provide configuration operations of working parameters for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner;

[0038] The ASIC control chip is respectively connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism, and is used to provide the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism with configuration operations of working parameters in a time-sharing manner, including: the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism share the same working parameter configuration interface;

[0039] Wherein, the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism use different configuration address data;

[0040] Wherein, a parallel connection of a communication data link is established between each of the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism through a parallel data bus;

[0041] Among them, the parallel connection of the communication data link established between each of the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism through a parallel data bus includes: the parallel data bus is one of an 8-bit parallel data bus, a 16-bit parallel data bus and a 32-bit parallel data bus.

[0042] Figure 3 Schematic diagram of the internal structure of a smart meter disconnection timing analysis system according to implementation scheme C of the present invention.

[0043] Compared with implementation scheme A, the smart meter disconnection timing analysis system shown in implementation scheme C may also include the following components:

[0044] A power support device is connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism respectively, and is used to provide power distribution support of different working voltages for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner;

[0045] The power support device is respectively connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism, and is used to provide power distribution support with different working voltages for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner, including: two or more devices with the same working voltage requirements in the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism use the same power supply line;

[0046] Wherein, the power support device is respectively connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism, and is used to provide power distribution support of different working voltages for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner, and further includes: the power support device is an uninterruptible power supply device;

[0047] Among them, the power support device is respectively connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism, and is used to provide power distribution support with different working voltages for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in time-sharing, and further includes: providing different working voltages including 3.3V working voltage for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in time-sharing;

[0048] And wherein, the power support device is respectively connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism, and is used to provide power distribution support with different working voltages for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner, and also includes: providing different working voltages including 5V working voltage for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner.

[0049] In addition, in the smart meter disconnection timing analysis system, the AI ​​prediction body is used to intelligently predict the predicted value of the induced current of the target meter at the next moment of the current moment based on the respective induced currents corresponding to the target meter at each past moment before the current moment, the configuration data of the load currently used by the target meter user, the multiple reference information of the target meter, and the number of loads currently used by the target meter user. It also includes: inputting the respective induced currents corresponding to the target meter at each past moment before the current moment, the configuration data of the load currently used by the target meter user, the multiple reference information of the target meter, and the number of loads currently used by the target meter user into the AI ​​prediction body in parallel;

[0050] And wherein, using an AI prediction body to intelligently predict the predicted value of the induced current of the target meter at the next moment after the current moment based on the respective induced currents corresponding to the target meter at each past moment before the current moment, the configuration data of the target meter user's current load, multiple reference information of the target meter and the number of loads currently used by the target meter user also includes: executing the AI ​​prediction body to obtain the predicted value of the induced current of the target meter at the next moment after the current moment output by the AI ​​prediction body.

[0051] The smart meter disconnection timing analysis system of the present invention solves the technical problem in the prior art that it is difficult to predict in advance whether the future moment of the meter will be a high-risk disconnection moment. By using a customized AI prediction body, the predicted value of the induced current of the target meter at the next moment after the current moment is predicted, and then it is determined whether the next moment after the current moment is a high-risk disconnection moment for the target meter, thereby completing the intelligent prediction of whether the future moment of each meter will be a high-risk opportunity.

[0052] Although the present invention has been comprehensively described by way of example, it should be understood that various changes and modifications are apparent to those skilled in the art. Therefore, unless otherwise indicated, changes and modifications depart from the scope of the present invention, such changes and modifications should all be considered to be included in the scope of the present invention.

Claims

1. A smart meter disconnection timing analysis system, characterized in that: The system comprises: A data capture mechanism, used to obtain configuration data of a load currently used by a target meter user, wherein the configuration data of the load currently used by the target meter user includes each share of rated power, each share of working current upper limit value, and each share of working current lower limit value corresponding to each load currently used by the target meter user, and the target meter is a smart meter; An information collection mechanism is used to obtain the number of coil turns, coil cross-sectional diameter, coil resistance, meter core weight and meter core volume of the target electric meter, and output the number of coil turns, coil cross-sectional diameter, coil resistance, meter core weight and meter core volume of the target electric meter as multiple reference information of the target electric meter; A network reconstruction mechanism is used to perform a preset number of trainings on the radial basis neural network to obtain the radial basis neural network after each training, and output the radial basis neural network after each training as an AI prediction body, wherein the value of the preset number is positively correlated with the number of coil turns of the target electric meter; The induction prediction device is connected to the data capture mechanism, the information collection mechanism and the network reconstruction mechanism respectively, and is used to use the AI ​​prediction body to intelligently predict the predicted value of the induction current of the target meter at the next moment after the current moment based on the respective induction currents corresponding to the target meter at each past moment before the current moment, the configuration data of the load currently used by the user of the target meter, multiple reference information of the target meter and the number of loads currently used by the user of the target meter; A timing judgment device is connected to the induction prediction device, and is used to use the next moment after the current moment as the high-risk disconnection moment of the target meter when the predicted value of the induction current of the target meter after the current moment is greater than the rated current of the target meter; The timing judgment device is further used to use the next moment after the current moment as the low-risk disconnection moment of the target meter when the predicted value of the induced current of the target meter after the current moment is less than or equal to the rated current of the target meter; Among them, the AI ​​prediction body is used to intelligently predict the predicted value of the induced current of the target meter at the next moment of the current moment based on the respective induced currents corresponding to the target meter at each past moment before the current moment, the configuration data of the load currently used by the target meter user, multiple reference information of the target meter and the number of loads currently used by the target meter user. The predicted value includes: each past moment before the current moment includes the current moment, and each past moment before the current moment and the next moment of the current moment are evenly spaced on the time axis; Among them, the AI ​​prediction body is used to intelligently predict the induced current of the target meter at the next moment of the current moment based on the respective induced currents corresponding to the target meter at each past moment before the current moment, the configuration data of the target meter user's current load, multiple reference information of the target meter and the number of loads currently used by the target meter user. The predicted value of the induced current of the target meter at the next moment of the current moment also includes: the number of moments of each past moment before the current moment is proportional to the number of loads currently used by the target meter user.

2. The smart meter disconnection timing analysis system according to claim 1, characterized in that: Acquire the configuration data of the load currently used by the target meter user, wherein the configuration data of the load currently used by the target meter user includes the rated power of each share, the upper limit value of each working current, and the lower limit value of each working current corresponding to each load currently used by the target meter user, including: for each load, the specific value of its working current is between the upper limit value of its corresponding working current and the lower limit value of its corresponding working current; Among them, a preset number of trainings are performed on the radial basis neural network to obtain the radial basis neural network after each training, and the radial basis neural network after each training is output as an AI prediction body, and the value of the preset number is positively correlated with the number of coil turns of the target electric meter, including: the more the number of coil turns of the target electric meter, the larger the value of the preset number.

3. The smart meter disconnection timing analysis system according to claim 2, characterized in that: The system further comprises: An ASIC control chip is connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism respectively, and is used to provide configuration operations of working parameters for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner; Among them, the ASIC control chip is respectively connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism, and is used to provide the configuration operations of working parameters for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in time sharing, including: the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism share the same working parameter configuration interface.

4. The smart meter disconnection timing analysis system according to claim 3, characterized in that: The sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism use different configuration address data.

5. The smart meter disconnection timing analysis system according to claim 3, characterized in that: Establishing parallel connections of communication data links between the sensing prediction device, the data capture mechanism, the information collection mechanism, and the network reconstruction mechanism through parallel data buses; Among them, the parallel connection of the communication data link established between each of the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism through a parallel data bus includes: the parallel data bus is one of an 8-bit parallel data bus, a 16-bit parallel data bus and a 32-bit parallel data bus.

6. The smart meter disconnection timing analysis system according to claim 2, characterized in that: The system further comprises: A power support device is connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism respectively, and is used to provide power distribution support of different working voltages for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner; Among them, the power support device is respectively connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism, and is used to provide power distribution support with different working voltages for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner, including: among the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism, two or more devices with the same working voltage requirements use the same power supply line.

7. The smart meter disconnection timing analysis system according to claim 6, characterized in that: The power support device is respectively connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism, and is used to provide power distribution support with different working voltages for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner, and also includes: the power support device is an uninterruptible power supply device.

8. The smart meter disconnection timing analysis system according to claim 7, characterized in that: The power support device is respectively connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism, and is used to provide power distribution support with different working voltages for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner, and also includes: providing different working voltages including 3.3V working voltage for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner.

9. The smart meter disconnection timing analysis system according to claim 8, characterized in that: The power support device is respectively connected to the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism, and is used to provide power distribution support with different working voltages for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner, and also includes: providing different working voltages including a 5V working voltage for the sensing prediction device, the data capture mechanism, the information collection mechanism and the network reconstruction mechanism in a time-sharing manner.

Images