Intelligent electric meter fault detection system

Abstract

The invention relates to an intelligent electric meter fault detection system. The system comprises a target analysis mechanism and a target analysis mechanism, the AI analysis module is used for introducing an AI analysis model according to a preset time length and various configuration information of a target intelligent electric meter; intelligently analyzing a fault type identifier of the target intelligent electric meter at the current moment according to the remote meter reading of the target intelligent electric meter at the current moment and each remote meter reading corresponding to each previous moment before the current moment; and the type mapping mechanism is used for determining the type name of the fault type corresponding to the fault type identifier as the current fault type name. Through the system, the AI analysis model can be used to intelligently analyze the fault type identifier of the target intelligent electric meter at the current moment, and then the current fault type name is determined, and the current fault type name is wirelessly sent to the handheld terminal of the nearest worker, so that the intelligent level and the automation level of intelligent electric meter management are improved.

Description

Technical Field

[0001] The present invention relates to the field of smart electric meters, and more specifically, to a smart electric meter fault detection system. Background Art

[0002] Smart meters are one of the basic devices for data collection in smart grids (especially smart distribution networks). They are responsible for collecting, measuring and transmitting raw electric energy data, and are the basis for information integration, analysis optimization and information presentation. In addition to the basic electricity consumption metering function of traditional electric energy meters, smart meters also have two-way multi-rate metering function, user-side control function, two-way data communication function with multiple data transmission modes, anti-electricity theft function and other intelligent functions in order to adapt to the use of smart grids and new energy.

[0003] However, due to the relatively complete packaging and high integration of smart meters, it is difficult to diagnose faults of smart meters on-site by disassembly, and it is even more impossible to judge through remote diagnosis. At the same time, the fault types of smart meters may change over time. Therefore, how to non-destructively judge the fault types of smart meters by time is one of the technical problems that need to be solved at present. Summary of the invention

[0004] In order to solve the technical problems in related fields, the present invention provides a smart meter fault detection system, which uses an AI analysis model to intelligently analyze the fault type identification of the target smart meter at the current moment according to a preset time length, various configuration information of the target smart meter, the remote meter reading of the target smart meter at the current moment, and the remote meter readings corresponding to each past moment before the current moment, and then uses a type mapping mechanism to determine the type name of the fault type corresponding to the fault type identification of the target smart meter at the current moment obtained by the intelligent analysis as the current fault type name, and wirelessly sends the current fault type name to the handheld terminal of the nearest staff, thereby improving the intelligence and automation levels of smart meter management.

[0005] The present invention needs to have at least the following important invention points: Invention point A: Performing multi-level conversion processing on the deep neural network to obtain an AI analysis model, wherein each level of conversion processing performed on the deep neural network is each learning operation performed on the deep neural network, thereby realizing an artificial intelligence model with a customized structure for performing subsequent smart meter fault type analysis; Invention point B: Using an AI analysis model to intelligently analyze the fault type identification of the target smart meter at the current moment based on the preset time length, various configuration information of the target smart meter, the remote meter reading of the target smart meter at the current moment, and the remote meter readings corresponding to each past moment before the current moment, wherein the number of each past moment before the current moment is positively correlated with the number of various fault types of the smart meter. The targeted selection of the above multiple basic data ensures the reliability and effectiveness of the fault type analysis of the target smart meter; Invention point C: A type mapping mechanism is used to determine the type name of the fault type corresponding to the fault type identifier existing at the current moment of the target smart meter obtained by intelligent analysis as the current fault type name, and the current fault type name is wirelessly sent to the handheld terminal of the nearest staff member, thereby improving the intelligence and automation level of smart meter management.

[0006] According to the present invention, a smart meter fault detection system is provided, the system comprising: An identification storage device, used to store fault type identifications corresponding to various fault types of the smart meter, wherein the various fault types include battery undervoltage, metering inaccuracy, power abnormality, clock error, and communication failure, and different fault types correspond to different fault type identifications; A multi-level conversion device, used to perform multi-level conversion processing on a deep neural network to obtain an AI analysis model, wherein the multi-level conversion processing on the deep neural network to obtain the AI ​​analysis model includes: each level of conversion processing performed on the deep neural network is each learning operation performed on the deep neural network; A first capture device is used to obtain the remote meter reading of the target smart meter at the current moment and the remote meter readings corresponding to each past moment before the current moment, wherein the current moment and each past moment before the current moment are evenly spaced on the time axis and a preset time length is spaced between each two adjacent moments; A second capture device is used to obtain voltage parameters, current parameters, accuracy level and usage time of a target smart meter to output as various configuration information of the target smart meter; A target analysis mechanism is connected to the identification storage device, the multi-stage conversion device, the first capture device and the second capture device respectively, and is used to introduce an AI analysis model to intelligently analyze the fault type identification of the target smart meter at the current moment according to a preset time length, various configuration information of the target smart meter, the remote meter reading of the target smart meter at the current moment, and various remote meter readings corresponding to various past moments before the current moment; A type mapping mechanism, connected to the target analysis mechanism, is used to determine the type name of the fault type corresponding to the fault type identifier of the target smart meter obtained by intelligent analysis at the current moment as the current fault type name, and wirelessly send the current fault type name to the handheld terminal of the nearest staff member; Among them, the remote meter reading of the target smart meter at the current moment and the remote meter readings corresponding to each past moment before the current moment are obtained, the current moment and each past moment before it are evenly spaced on the time axis and the preset time length between each two adjacent moments includes: the number of each past moment before the current moment is positively correlated with the number of various fault types of the smart meter.

[0007] The smart meter fault detection system of the present invention has a compact structure and stable operation. Since it can use the AI ​​analysis model to intelligently analyze the fault type identification of the target smart meter at the current moment, and then determine the current fault type name, and wirelessly send the current fault type name to the handheld terminal of the nearest staff, it improves the intelligence and automation level of smart meter management. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Those skilled in the art may better understand the numerous advantages of the present invention by referring to the accompanying drawings, in which:

[0009] Figure 1 It is a structural schematic diagram of a smart meter fault detection system according to the primary embodiment of the present invention.

[0010] Figure 2 It is a structural schematic diagram of a smart meter fault detection system according to a secondary embodiment of the present invention.

[0011] Figure 3 FIG. 4 is a schematic diagram of the structure of a smart meter fault detection system according to another embodiment of the present invention. DETAILED DESCRIPTION

[0012] Figure 1 1 is a schematic diagram of the structure of a smart meter fault detection system according to a primary embodiment of the present invention, the system comprising: An identification storage device, used to store fault type identifications corresponding to various fault types of the smart meter, wherein the various fault types include battery undervoltage, metering inaccuracy, power abnormality, clock error, and communication failure, and different fault types correspond to different fault type identifications; For example, an identification storage device is used to store fault type identifications corresponding to various fault types of a smart meter, wherein the various fault types include battery undervoltage, metering inaccuracy, power abnormality, clock error, and communication failure, and different fault types correspond to different fault type identifications, including: the identification storage device is a TF storage chip or a FLASH flash memory; A multi-level conversion device, used to perform multi-level conversion processing on a deep neural network to obtain an AI analysis model, wherein the multi-level conversion processing on the deep neural network to obtain the AI ​​analysis model includes: each level of conversion processing performed on the deep neural network is each learning operation performed on the deep neural network; A first capture device is used to obtain the remote meter reading of the target smart meter at the current moment and the remote meter readings corresponding to each past moment before the current moment, wherein the current moment and each past moment before the current moment are evenly spaced on the time axis and a preset time length is spaced between each two adjacent moments; A second capture device is used to obtain voltage parameters, current parameters, accuracy level and usage time of a target smart meter to output as various configuration information of the target smart meter; A target analysis mechanism is connected to the identification storage device, the multi-stage conversion device, the first capture device and the second capture device respectively, and is used to introduce an AI analysis model to intelligently analyze the fault type identification of the target smart meter at the current moment according to a preset time length, various configuration information of the target smart meter, the remote meter reading of the target smart meter at the current moment, and various remote meter readings corresponding to various past moments before the current moment; A type mapping mechanism, connected to the target analysis mechanism, is used to determine the type name of the fault type corresponding to the fault type identifier of the target smart meter obtained by intelligent analysis at the current moment as the current fault type name, and wirelessly send the current fault type name to the handheld terminal of the nearest staff member; Wherein, the remote meter reading of the target smart meter at the current moment and the remote meter readings corresponding to the past moments before the current moment are obtained, the current moment and the past moments before it are evenly spaced on the time axis and the preset time length between each two adjacent moments includes: the number of past moments before the current moment is positively correlated with the number of various fault types of the smart meter; Wherein, various fault types of the smart meter are stored and correspond to various fault type identifiers, wherein the various fault types include battery undervoltage, inaccurate measurement, abnormal power, clock error and communication failure, and different fault types correspond to different fault type identifiers, including: the various fault types of the smart meter are stored and correspond to various fault type identifiers, which are all binary values; And wherein, the AI ​​analysis model is introduced to intelligently analyze the fault type identification of the target smart meter at the current moment according to the preset time length, the various configuration information of the target smart meter, the remote meter reading of the target smart meter at the current moment, and the remote meter readings corresponding to each past moment before the current moment, including: the preset time length, the various configuration information of the target smart meter, the remote meter reading of the target smart meter at the current moment, and the remote meter readings corresponding to each past moment before the current moment are converted into binary values ​​respectively, and then input into the AI ​​analysis model in parallel.

[0013] Figure 2 It is a structural schematic diagram of a smart meter fault detection system according to a secondary embodiment of the present invention.

[0014] and Figure 1 different, Figure 2 The smart meter fault detection system in the system can also include the following components: A code analysis device, connected to the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device, respectively, for measuring the current fault code inside the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device respectively; Wherein, the code analysis device is respectively connected to the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device, and is used to respectively measure the current fault codes inside the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device, including: the code analysis device includes a plurality of fault self-checking units, which are respectively connected to the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device, so as to respectively measure the current fault codes inside the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device; The code analysis device includes a plurality of fault self-checking units, which are respectively connected to the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device to respectively measure the current fault codes inside the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device, including: the internal structures of the plurality of fault self-checking units respectively used by the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are the same; Among them, the code analysis device includes multiple fault self-detection units, which are used to connect to the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device respectively, so as to respectively measure the current fault codes inside the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device respectively. It also includes: the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device respectively use multiple fault self-detection units to perform internal self-detection operations.

[0015] Figure 3 FIG. 4 is a schematic diagram of the structure of a smart meter fault detection system according to another embodiment of the present invention.

[0016] and Figure 1 different, Figure 3 The smart meter fault detection system in the system can also include the following components: A percentage analysis device is arranged near the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device and is respectively connected to the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device, and is used for real-time measurement of the operation utilization percentage of the respective operators of the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device.

[0017] Next, the specific structure of the smart meter fault detection system of the present invention will be further described.

[0018] In the smart meter fault detection system according to various embodiments of the present invention: The target analysis mechanism, the multi-stage conversion device, the first capture device, and the second capture device each include a signal input unit and a signal output unit, and the signal input unit and the signal output unit each include a ground terminal.

[0019] In the smart meter fault detection system according to various embodiments of the present invention: The target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are respectively implemented by different CPLD chips, and the CPLD chips are designed by VHDL language.

[0020] And in the smart meter fault detection system according to various embodiments of the present invention: The target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are each provided with a plurality of heat dissipation holes on their respective shells, and the plurality of heat dissipation holes of any one of the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are evenly distributed on their shells; Among them, the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are each provided with a plurality of heat dissipation holes on their respective shells, and the plurality of heat dissipation holes of any one of the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are evenly distributed on their shells, including: the aperture values ​​of each of the plurality of heat dissipation holes of any one of the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are the same.

[0021] In addition, in the smart meter fault detection system, an AI analysis model is introduced to intelligently analyze the fault type identification of the target smart meter at the current moment according to a preset time length, various configuration information of the target smart meter, the remote meter reading of the target smart meter at the current moment, and the remote meter readings corresponding to each past moment before the current moment, and further includes: executing the AI ​​analysis model to obtain the fault type identification of the target smart meter at the current moment represented by a binary value output by the AI ​​analysis model.

[0022] Furthermore, the present invention is not limited to the above-described embodiments, and various modifications may be made based on the spirit of the present invention, which should not be excluded from the requirements of the present invention.

Claims

1. A smart meter fault detection system, characterized in that: The system comprises: An identification storage device, used to store fault type identifications corresponding to various fault types of the smart meter, wherein the various fault types include battery undervoltage, metering inaccuracy, power abnormality, clock error, and communication failure, and different fault types correspond to different fault type identifications; A multi-level conversion device, used to perform multi-level conversion processing on a deep neural network to obtain an AI analysis model, wherein the multi-level conversion processing on the deep neural network to obtain the AI ​​analysis model includes: each level of conversion processing performed on the deep neural network is each learning operation performed on the deep neural network; A first capture device is used to obtain the remote meter reading of the target smart meter at the current moment and each remote meter reading corresponding to each past moment before the current moment, wherein the current moment and each past moment before it are evenly spaced on the time axis and a preset time length is spaced between each two adjacent moments, including: the number of each past moment before the current moment is positively correlated with the number of various fault types of the smart meter; A second capture device is used to obtain voltage parameters, current parameters, accuracy level and usage time of a target smart meter to output as various configuration information of the target smart meter; A target analysis mechanism is connected to the identification storage device, the multi-stage conversion device, the first capture device and the second capture device respectively, and is used to introduce an AI analysis model to intelligently analyze the fault type identification of the target smart meter at the current moment according to a preset time length, various configuration information of the target smart meter, the remote meter reading of the target smart meter at the current moment, and various remote meter readings corresponding to various past moments before the current moment; The type mapping mechanism is connected to the target analysis mechanism, and is used to determine the type name of the fault type corresponding to the fault type identification existing in the target smart meter at the current moment obtained by intelligent analysis as the current fault type name, and wirelessly send the current fault type name to the handheld terminal of the nearest staff member.

2. The smart meter fault detection system according to claim 1, characterized in that: The various fault types of the smart meter are stored and correspond to the fault type identifiers, wherein the various fault types include battery undervoltage, inaccurate measurement, abnormal power, clock error, and communication failure. Different fault types correspond to different fault type identifiers, including: the various fault types of the smart meter are stored and correspond to different fault type identifiers, which are all binary values; Among them, the introduction of the AI ​​analysis model to intelligently analyze the fault type identification of the target smart meter at the current moment according to the preset time length, the various configuration information of the target smart meter, the remote meter reading of the target smart meter at the current moment, and the remote meter readings corresponding to each past moment before the current moment includes: performing binary value conversion on the preset time length, the various configuration information of the target smart meter, the remote meter reading of the target smart meter at the current moment, and the remote meter readings corresponding to each past moment before the current moment, and then inputting them into the AI ​​analysis model in parallel.

3. The smart meter fault detection system according to claim 2, characterized in that: The system comprises: A code analysis device, connected to the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device, respectively, for measuring the current fault code inside the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device respectively; Among them, the code analysis device is respectively connected to the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device, and is used to respectively measure the current fault codes inside the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device. The code analysis device includes multiple fault self-detection units, which are respectively connected to the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device, and are used to respectively measure the current fault codes inside the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device.

4. The smart meter fault detection system according to claim 3, characterized in that: The code analysis device includes multiple fault self-detection units, which are used to be connected to the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device respectively, so as to respectively measure the current fault codes inside the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device respectively, including: the internal structures of the multiple fault self-detection units used by the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are the same.

5. The smart meter fault detection system according to claim 4, characterized in that: The code analysis device includes multiple fault self-detection units, which are used to connect to the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device respectively, so as to respectively measure the current fault codes inside the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device respectively. It also includes: the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device respectively use multiple fault self-detection units to perform internal self-detection operations.

6. The smart meter fault detection system according to claim 2, characterized in that: The system further comprises: A percentage analysis device is arranged near the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device and is respectively connected to the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device, and is used for real-time measurement of the operation utilization percentage of the respective operators of the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device.

7. The smart meter fault detection system according to any one of claims 2 to 6, characterized in that: The target analysis mechanism, the multi-stage conversion device, the first capture device, and the second capture device each include a signal input unit and a signal output unit, and the signal input unit and the signal output unit each include a ground terminal.

8. The smart meter fault detection system according to any one of claims 2 to 6, characterized in that: The target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are respectively implemented by different CPLD chips, and the CPLD chips are designed by VHDL language.

9. The smart meter fault detection system according to any one of claims 2 to 6, characterized in that: The target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are each provided with a plurality of heat dissipation holes on their respective shells, and the plurality of heat dissipation holes of any one of the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are evenly distributed on their shells; Among them, the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are each provided with a plurality of heat dissipation holes on their respective shells, and the plurality of heat dissipation holes of any one of the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are evenly distributed on their shells, including: the aperture values ​​of each of the plurality of heat dissipation holes of any one of the target analysis mechanism, the multi-stage conversion device, the first capture device and the second capture device are the same.

Images