Management system for electricity meter seal authentication
By using the BP neural network model on the meter seal and combining the visual data in the top shot, real-time intelligent detection of the meter seal status is achieved, which solves the loopholes in the seal status detection in the existing technology and improves the security of meter management sex.
Patent Information
- Application Number
- CN202411422197.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-12
- Publication Date
- 2025-01-14
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The lack of an identification mechanism for the changes in the sealing state of the meter in the prior art has led to loopholes in the meter management and the inability to detect the sealing length changes in real time.
By obtaining the coordinate values and depth of field data of each edge pixel point in the imaging pattern sealed in the live top shot, removing the arithmetic average value after the maximum and minimum values, the BP neural network model is trained to detect the current length of the meter seal. numerical value, realize distributed intelligent detection of the sealing state of the meter.
Real-time and intelligent detection of the sealing status of the meter is realized, and the changes in the seal length can be accurately judged, which improves the safety and reliability of meter management.
Smart Images
Figure CN119313636A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the field of electric meters, and in particular to a management system for electric meter seal identification. Background Art
[0002] The general direct-type single-phase meter and three-phase meter can directly read the number minus the last reading to get the power of this stage. The direct-type meter has a thicker incoming line, and if you look closely, it is not connected through a transformer. The three-phase meter is connected through a current transformer. The meter has 10 wires. You need to observe the current ratio of the connected current transformer. The current transformer is marked on the nameplate, and it is a number ratio of 5, such as 100 / 5150 / 5, etc. The number read on the meter multiplied by the current ratio is the measured power. To be accurate, you must add the transformer loss and line loss.
[0003] Single-phase meters measure the amount of three-phase electricity. The way to read the electricity is to directly connect the meter and read the number on the meter multiplied by 3. If the meter is connected through a transformer, the meter number should be read and multiplied by the transformer current multiple and then multiplied by 3. Smart meters only have one LCD screen. If it is a single-phase meter, it will directly display the total amount of electricity and the remaining amount of electricity. You can read the readings directly. If it is an IC card meter, only the light-emitting tube is displayed, which is a single-graphics meter. There will be a small red dot on the meter. If the red dot jumps to the total usage, it is the total usage, and if it jumps to the remaining, it is the remaining. For dual-graphics meters, you can read from the top or the bottom. The direct reading of the three-phase prepaid meter is direct, and the reading of the mutual inductance meter is multiplied by the transformer multiple.
[0004] The lead seal on the large cover of the electric energy meter is locked by the inspection, repair, and manufacturing departments of the electric energy meter, while the lead seal on the small cover is locked by the power supply company's meter installation and inspection personnel. Regardless of the size of the lead seal, it is a kind of fortified seal. Except for personnel who are professionally equipped with sealing pliers, no other personnel are allowed to open it on their own. However, the existing technology lacks a targeted identification mechanism for changes in the seal state of the electric energy meter, such as changes in the seal length, resulting in loopholes in the current electric energy meter management. Summary of the invention
[0005] In order to solve the technical problems in the related fields, the present invention provides a management system for identifying electric meter seals, which obtains the horizontal coordinate values and vertical coordinate values corresponding to each edge pixel point in the imaging pattern sealed in the on-site overhead picture, and obtains the arithmetic mean of multiple depth of field data after removing the maximum and minimum values of each depth of field data corresponding to each pixel point in the imaging pattern sealed in the on-site overhead picture, wherein a set number of multiple training actions are performed on the BP neural network to obtain the corresponding BP neural network model, and the number of training actions is monotonically positively related to the mean of the horizontal resolution and the vertical resolution of the on-site overhead picture. The customized structure design of the BP neural network model is completed, and then the horizontal coordinate values, vertical coordinate values, the arithmetic mean of the multiple depth data after removing the maximum and minimum values of the depth data corresponding to each pixel point in the imaging pattern sealed in the on-site aerial picture and the number of each edge pixel point in the imaging pattern sealed in the on-site aerial picture are taken as the input content of the BP neural network model item by item, and the BP neural network model is run to obtain the current length value of the seal output, thereby completing the distributed intelligent detection of the sealing status of the electric meters at various locations.
[0006] According to the present invention, a management system for electric meter seal identification is provided, the system comprising: A seal detection mechanism, used to detect and segment an image area where the seal of the electric meter is located from a live overhead picture obtained by photographing the top end face of the electric meter from an overhead perspective, and output it as a seal image area; A bird's-eye view execution mechanism, arranged just above the top end face of the electric meter and connected to the seal detection mechanism, for executing the shooting of the top end face of the electric meter from a bird's-eye view under the control of a network control instruction, and sending the obtained on-site bird's-eye view picture to the seal detection mechanism; The first analysis device is connected to the overhead shooting execution mechanism, and is used to obtain the horizontal coordinate values and vertical coordinate values corresponding to the edge pixel points in the imaging pattern sealed in the on-site overhead shooting picture, and obtain the arithmetic mean value of multiple depth of field data after removing the maximum value and the minimum value of the depth of field data corresponding to the pixel points in the imaging pattern sealed in the on-site overhead shooting picture; A target construction device is used to perform a set number of multiple training actions on the BP neural network to obtain a corresponding BP neural network model, wherein the number of training actions is monotonically positively correlated with the mean of the horizontal resolution and the vertical resolution of the on-site overhead view; A second analysis device is connected to the first analysis device and the target construction device respectively, and is used to use the horizontal coordinate values, vertical coordinate values, the depth data corresponding to each edge pixel point in the imaging pattern sealed in the on-site overhead picture, the arithmetic mean of multiple depth data after removing the maximum and minimum values of each depth data corresponding to each pixel point in the imaging pattern sealed in the on-site overhead picture, and the number of each edge pixel point in the imaging pattern sealed in the on-site overhead picture as the input content of the BP neural network model item by item, and execute the BP neural network model to obtain the current length value of the seal outputted by it; A state identification device connected to the second analysis device, used for wirelessly transmitting a data packet including the number of the electric meter where the seal is located and the seal length deviation information to a remote electric meter management server through a network transmission component when the current length value of the received seal is not within the reference length range of the seal when it leaves the factory; Among them, the seal detection mechanism is used to detect and segment the image area where the seal of the electric meter is located from the on-site overhead picture obtained by shooting the top end face of the electric meter from a bird's-eye view, and output it as the seal image area, including: detecting the image area where the seal of the electric meter is located from the on-site overhead picture based on the grayscale imaging features or shape imaging features of the seal.
[0007] It can be seen that the present invention has at least the following main inventive concepts: First: obtain the horizontal coordinate values and vertical coordinate values corresponding to each edge pixel point in the imaging pattern sealed in the aerial view of the scene, and obtain the arithmetic mean value of multiple depth of field data after removing the maximum value and the minimum value of each depth of field data corresponding to each pixel point in the imaging pattern sealed in the aerial view of the scene; Secondly: performing a set number of multiple training actions on the BP neural network to obtain a corresponding BP neural network model, wherein the number of training actions is monotonically positively correlated with the mean of the horizontal resolution and the vertical resolution of the on-site overhead view, thereby completing the customized structural design of the BP neural network model; Again: the horizontal coordinate values, vertical coordinate values corresponding to each edge pixel point in the imaging pattern sealed in the aerial picture of the scene, the arithmetic mean of the multiple depth data corresponding to each pixel point in the imaging pattern sealed in the aerial picture of the scene after removing the maximum and minimum values, and the number of each edge pixel point in the imaging pattern sealed in the aerial picture of the scene are used as the input content of the BP neural network model item by item, and the BP neural network model is run to obtain the current length value of the seal as its output, thereby completing the distributed intelligent detection of the sealing status of the electric meters at various locations. BRIEF DESCRIPTION OF THE DRAWINGS
[0008] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein: Figure 1 It is a structural block diagram of a management system for electric meter seal authentication according to the primary embodiment of the present invention.
[0009] Figure 2 It is a structural block diagram of a management system for electric meter seal authentication according to a secondary embodiment of the present invention.
[0010] Figure 3 FIG. 1 is a structural block diagram of a management system for electric meter seal authentication according to another embodiment of the present invention. DETAILED DESCRIPTION
[0011] The following will describe in detail an embodiment of a management system for electric meter seal authentication according to the present invention with reference to the accompanying drawings.
[0012] Figure 1 The structural block diagram of a management system for electric meter seal identification according to the primary embodiment of the present invention is shown, and the system includes: A seal detection mechanism, used to detect and segment an image area where the seal of the electric meter is located from a live overhead picture obtained by photographing the top end face of the electric meter from an overhead perspective, and output it as a seal image area; Specifically, the seal detection mechanism can be implemented by using a SOC chip, which is used to detect and segment the image area where the seal of the meter is located from the on-site overhead picture obtained by shooting the top end face of the meter from an overhead perspective, and output it as the seal image area; A bird's-eye view execution mechanism, arranged just above the top end face of the electric meter and connected to the seal detection mechanism, for executing the shooting of the top end face of the electric meter from a bird's-eye view under the control of a network control instruction, and sending the obtained on-site bird's-eye view picture to the seal detection mechanism; The first analysis device is connected to the overhead shooting execution mechanism, and is used to obtain the horizontal coordinate values and vertical coordinate values corresponding to the edge pixel points in the imaging pattern sealed in the on-site overhead shooting picture, and obtain the arithmetic mean value of multiple depth of field data after removing the maximum value and the minimum value of the depth of field data corresponding to the pixel points in the imaging pattern sealed in the on-site overhead shooting picture; A target construction device is used to perform a set number of multiple training actions on the BP neural network to obtain a corresponding BP neural network model, wherein the number of training actions is monotonically positively correlated with the mean of the horizontal resolution and the vertical resolution of the on-site overhead view; Specifically, the target construction device is used to perform a set number of multiple training actions on the BP neural network to obtain a corresponding BP neural network model, wherein the number of training actions of the multiple training actions is monotonically positively correlated with the mean of the horizontal resolution and the vertical resolution of the on-site overhead view, including: using a content conversion function to represent the numerical conversion relationship of the number of training actions of the multiple training actions and the mean of the horizontal resolution and the vertical resolution of the on-site overhead view; A second analysis device is connected to the first analysis device and the target construction device respectively, and is used to use the horizontal coordinate values, vertical coordinate values, the depth data corresponding to each edge pixel point in the imaging pattern sealed in the on-site overhead picture, the arithmetic mean of multiple depth data after removing the maximum and minimum values of each depth data corresponding to each pixel point in the imaging pattern sealed in the on-site overhead picture, and the number of each edge pixel point in the imaging pattern sealed in the on-site overhead picture as the input content of the BP neural network model item by item, and execute the BP neural network model to obtain the current length value of the seal outputted by it; A state identification device connected to the second analysis device, used for wirelessly transmitting a data packet including the number of the electric meter where the seal is located and the seal length deviation information to a remote electric meter management server through a network transmission component when the current length value of the received seal is not within the reference length range of the seal when it leaves the factory; The seal detection mechanism is used to detect and segment the image area where the seal of the electric meter is located from the on-site overhead picture obtained by shooting the top end face of the electric meter from a bird's-eye view, and output it as the seal image area, including: detecting the image area where the seal of the electric meter is located from the on-site overhead picture based on the grayscale imaging features or shape imaging features of the seal; The seal detection mechanism is used to detect and segment the image area where the seal of the electric meter is located from the on-site overhead picture obtained by shooting the top end face of the electric meter from an overhead perspective, and output as the seal image area also includes: the grayscale imaging feature of the seal is the grayscale value distribution interval corresponding to the seal, and the shape imaging feature of the seal is the standard shape pattern of the seal; Among them, the state identification device is connected to the second analysis device, and is used to wirelessly transmit a data packet that packages the number of the meter where the seal is located and the seal length deviation information to a remote meter management server through a network transmission component when the current length value of the received seal is not within the reference length range of the seal in the factory state. The data packet includes: the data packet is an IP data packet.
[0013] Figure 2 It is a structural block diagram of a management system for electric meter seal authentication according to a secondary embodiment of the present invention.
[0014] Compared to Figure 1 , Figure 2 The management system for meter seal identification may also include: In a management system for electric meter seal identification according to various embodiments of the present invention: a power detection mechanism includes a plurality of power detection units for respectively detecting current input powers of the second analysis device, the first analysis device, the target construction device, and the state identification device; The power detection mechanism includes a plurality of power detection units, and is used to respectively detect the current input power of the second analysis device, the first analysis device, the target structure device, and the state identification device, including: calculating the current input power of each of the second analysis device, the first analysis device, the target structure device, and the state identification device by respectively measuring the real-time power supply voltage and the real-time power supply current for the second analysis device, the first analysis device, the target structure device, and the state identification device; The calculation of the respective current input powers by measuring the real-time power supply voltage and the real-time power supply current for the second analysis device, the first analysis device, the target structure device and the state identification device respectively includes: for any device of the second analysis device, the first analysis device, the target structure device and the state identification device, the current input power thereof is the product of its real-time power supply voltage and its real-time power supply current; Wherein, the power detection mechanism includes a plurality of power detection units for respectively detecting the current input power of the second analysis device, the first analysis device, the target construction device and the state identification device, and further includes: the plurality of power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device have the same power measurement upper limit threshold and power measurement lower limit threshold; Among them, the power detection mechanism includes multiple power detection units, which are used to respectively detect the current input power of the second analysis device, the first analysis device, the target construction device and the state identification device. It also includes: the internal structures of the multiple power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device are the same.
[0015] Figure 3 FIG. 1 is a structural block diagram of a management system for electric meter seal authentication according to another embodiment of the present invention.
[0016] Compared to Figure 1 , Figure 3 The management system for meter seal identification may also include: an on-site notification mechanism, connected to the plurality of power detection units respectively used for the second analysis device, the first analysis device, the target construction device, and the state identification device, and configured to perform corresponding power notification operations based on power measurement results of the plurality of power detection units respectively used for the second analysis device, the first analysis device, the target construction device, and the state identification device; Wherein, the on-site notification mechanism is respectively connected to a plurality of power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device, and is used to perform corresponding power notification operations based on power measurement results of the plurality of power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device, including: the on-site notification mechanism includes a static storage unit for storing a power notification threshold; Among them, the on-site notification mechanism is respectively connected to multiple power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device, and is used to perform corresponding power notification operations based on the power measurement results of the multiple power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device. It also includes: the on-site notification mechanism performs corresponding power notification operations for the second analysis device, the first analysis device, the target construction device and the state identification device based on the voice playback mode.
[0017] At the same time, in the management system for identifying the seal of the electric meter, the overhead shooting actuator is arranged directly above the top end surface of the electric meter and connected to the seal detection mechanism. It is used to execute the shooting of the top end surface of the electric meter from a overhead shooting perspective under the control of the network control instruction, and send the obtained on-site overhead shooting picture to the seal detection mechanism. The overhead shooting actuator includes: the overhead shooting actuator has a built-in network control interface, an overhead shooting lens, a photoelectric sensor and a flexible circuit board.
[0018] The management system for electric meter seal identification of the present invention is used to address the technical problem in the prior art of lacking a targeted distributed intelligent detection mechanism for the real-time status of electric meter seals at various locations. By using customized screened seal visualization data and a targeted customized BP neural network model to intelligently identify the real-time status of electric meter seals based on an artificial intelligence model, distributed intelligent detection of the seal status of various electric meters is completed, solving the above technical problem.
[0019] In addition, the above-mentioned embodiment is described for ease of understanding the present invention, and the present invention is not limited to the above-mentioned embodiment. On the contrary, the present invention is intended to cover various modifications and equivalent structures included within the scope of the appended claims, and the scope of the claims conforms to the broadest interpretation to include such modifications and equivalent structures allowed by all laws.
Claims
1. A management system for electric meter seal identification, characterized in that: The system comprises: A seal detection mechanism, used to detect and segment an image area where the seal of the electric meter is located from a live overhead picture obtained by photographing the top end face of the electric meter from an overhead perspective, and output it as a seal image area; A bird's-eye view execution mechanism, arranged just above the top end face of the electric meter and connected to the seal detection mechanism, for executing the shooting of the top end face of the electric meter from a bird's-eye view under the control of a network control instruction, and sending the obtained on-site bird's-eye view picture to the seal detection mechanism; The first analysis device is connected to the overhead shooting execution mechanism, and is used to obtain the horizontal coordinate values and vertical coordinate values corresponding to the edge pixel points in the imaging pattern sealed in the on-site overhead shooting picture, and obtain the arithmetic mean value of multiple depth of field data after removing the maximum value and the minimum value of the depth of field data corresponding to the pixel points in the imaging pattern sealed in the on-site overhead shooting picture; A target construction device is used to perform a set number of multiple training actions on the BP neural network to obtain a corresponding BP neural network model, wherein the number of training actions is monotonically positively correlated with the mean of the horizontal resolution and the vertical resolution of the on-site overhead view; A second analysis device is connected to the first analysis device and the target construction device respectively, and is used to use the horizontal coordinate values, vertical coordinate values, the depth data corresponding to each edge pixel point in the imaging pattern sealed in the on-site overhead picture, the arithmetic mean of multiple depth data after removing the maximum and minimum values of each depth data corresponding to each pixel point in the imaging pattern sealed in the on-site overhead picture, and the number of each edge pixel point in the imaging pattern sealed in the on-site overhead picture as the input content of the BP neural network model item by item, and execute the BP neural network model to obtain the current length value of the seal outputted by it; A state identification device connected to the second analysis device, used for wirelessly transmitting a data packet including the number of the electric meter where the seal is located and the seal length deviation information to a remote electric meter management server through a network transmission component when the current length value of the received seal is not within the reference length range of the seal when it leaves the factory; Among them, the seal detection mechanism is used to detect and segment the image area where the seal of the electric meter is located from the on-site overhead picture obtained by shooting the top end face of the electric meter from a bird's-eye view, and output it as the seal image area, including: detecting the image area where the seal of the electric meter is located from the on-site overhead picture based on the grayscale imaging features or shape imaging features of the seal.
2. The management system for electric meter seal identification as claimed in claim 1, characterized in that: The seal detection mechanism is used to detect and segment the image area where the seal of the electric meter is located from the on-site overhead picture obtained by shooting the top end face of the electric meter from the overhead perspective, and output as the seal image area also includes: the grayscale imaging feature of the seal is the grayscale value distribution interval corresponding to the seal, and the shape imaging feature of the seal is the standard shape pattern of the seal; Among them, the state identification device is connected to the second analysis device, and is used to wirelessly transmit a data packet that packages the number of the meter where the seal is located and the seal length deviation information to a remote meter management server through a network transmission component when the current length value of the received seal is not within the reference length range of the seal in the factory state. The data packet includes: the data packet is an IP data packet.
3. The management system for electric meter seal identification as claimed in claim 2, characterized in that: The system further comprises: A power detection mechanism, comprising a plurality of power detection units, for respectively detecting current input powers of the second analysis device, the first analysis device, the target construction device, and the state identification device; Among them, the power detection mechanism includes multiple power detection units, which are used to respectively detect the current input power of the second analysis device, the first analysis device, the target construction device and the state identification device, including: calculating the current input power of each of them by measuring the real-time power supply voltage and the real-time power supply current for the second analysis device, the first analysis device, the target construction device and the state identification device respectively.
4. The management system for electric meter seal identification as claimed in claim 3, characterized in that: The calculation of the respective current input powers is completed by measuring the real-time power supply voltage and the real-time power supply current for the second analysis device, the first analysis device, the target construction device and the state identification device respectively, including: for any device of the second analysis device, the first analysis device, the target construction device and the state identification device, its current input power is the product of its real-time power supply voltage and its real-time power supply current.
5. The management system for electric meter seal identification as claimed in claim 3, characterized in that: The power detection mechanism includes multiple power detection units for respectively detecting the current input power of the second analysis device, the first analysis device, the target construction device and the state identification device, and also includes: the multiple power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device have the same power measurement upper limit threshold and power measurement lower limit threshold.
6. The management system for electric meter seal identification as claimed in claim 5, characterized in that: The power detection mechanism includes multiple power detection units for respectively detecting the current input power of the second analysis device, the first analysis device, the target construction device and the state identification device. It also includes: the multiple power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device have the same internal structure.
7. The management system for electric meter seal identification as claimed in claim 2, characterized in that: The system further comprises: The on-site notification mechanism is respectively connected to the multiple power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device, and is used to perform corresponding power notification operations based on the power measurement results of the multiple power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device.
8. The management system for electric meter seal identification as claimed in claim 7, characterized in that: An on-site notification mechanism is respectively connected to a plurality of power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device, and is used to perform corresponding power notification operations based on power measurement results of the plurality of power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device, including: the on-site notification mechanism includes a static storage unit for storing a power notification threshold.
9. The management system for electric meter seal identification as claimed in claim 8, characterized in that: An on-site notification mechanism is respectively connected to a plurality of power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device, and is used to perform corresponding power notification operations based on power measurement results of the plurality of power detection units respectively used for the second analysis device, the first analysis device, the target construction device and the state identification device. The on-site notification mechanism also includes: the on-site notification mechanism performs corresponding power notification operations for the second analysis device, the first analysis device, the target construction device and the state identification device based on a voice playback mode.