A method and system for automatically reading meters in a substation

Abstract

The application discloses a kind of transformer substation in-station instrument automatic meter reading method and system, it is related to power station inspection technical field, including: meter reading work is completed by transformer substation in-station instrument meter reading software, including automatic meter reading module and meter reading photo analysis module;Automatic meter reading module is used to use mobile terminal and main control room computer to establish network communication, obtains meter reading photo by photographing field instrument to mobile terminal, and is returned to main control room computer, is downloaded and is transmitted to meter reading photo analysis module calculation;Meter reading photo analysis module is used to initialize meter reading photo, position target and calculate the instrument contained in meter reading photo, extract the outline of target, identify the edge coordinates of instrument pointer by contour matching mode, calculate the instrument reading pointed by instrument pointer by looking up black and white boundary in binary image.The application can replace artificial field meter reading, automatically obtain the reading of transformer substation instrument by field photo identification, generates instrument data report.

Description

Technical Field

[0001] The present invention relates to the technical field of power station inspection, and in particular to an automatic meter reading method and system for instruments in a transformer substation. Background Art

[0002] With the rapid expansion of power grids, the number of substations is also increasing. Substation inspections have become a crucial means of ensuring safe substation operation and power supply security. Substation inspections often involve reading important information displayed on various instruments to determine the parameters of each substation device.

[0003] Currently, meter reading during substation inspections is still done manually. That is, upon arrival at the substation, inspectors must manually inspect and read the information displayed on each meter. However, in the actual operation of a substation, especially during the inspection of on-site equipment, the parameters indicated by the meters are extremely important and require specific personnel. Therefore, manual meter reading often presents the following problems: ① Due to the excessive number of on-site instruments, on-site staff often miss or make incorrect readings; ② Due to inexperience, on-site staff may make mistakes in meter reading. Therefore, a device or method capable of automatic meter reading is essential. In the early stages of a substation inspection, before the inspection begins, staff must read the instruments within the substation. Existing methods for reading on-site instruments generally rely on manual operation. The excessive number of on-site instruments can easily increase staff workload and work intensity, reducing efficiency. Therefore, a method capable of automatic meter reading is needed.

[0004] Therefore, in response to the above shortcomings, it is necessary to provide a method for automatic meter reading of instruments in substations, which can reduce the inspection cost of substations, reduce the inspection intensity, and reduce the workload of inspection personnel, so as to realize automatic meter reading of instruments in substations and reduce the workload of staff. Summary of the Invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the present invention provides a method and system for automatic meter reading of instruments in a substation to solve the problem in the prior art that the meter reading results of instruments in a substation are dependent on operation and maintenance engineers, with high labor costs, and may result in misreading, missed readings, etc., and the statistical efficiency is low.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: an automatic meter reading system for instruments within a substation, comprising: meter reading is performed by meter reading software within the substation, the meter reading software comprising an automatic meter reading module and a meter reading photo analysis module; the automatic meter reading module is configured to establish network communication with a main control room computer using a mobile terminal, take photos of on-site instruments via the mobile terminal to obtain meter reading photos, and transmit the meter reading photos back to the main control room computer. The main control room computer automatically downloads the meter reading photos and transmits them to the meter reading photo analysis module for calculation; the meter reading photo analysis module is configured to initialize the meter reading photos, locate targets using a scale-invariant feature transformation, calculate the instruments included in the meter reading photos, extract the contours of the targets, convert them into a binary image, locate black and white boundaries in the binary image, identify the edge coordinates of the instrument pointer using contour matching, and calculate the meter reading pointed to by the instrument pointer by locating the black and white boundaries in the binary image.

[0008] As a preferred solution of the automatic meter reading system for substation instruments described in the present invention, the mobile terminal communicates with the main control room computer through the network, so that the main control room computer receives meter reading photos uploaded by on-site operation and maintenance, and reports the identified meter data to the main control room computer in real time; the wireless transmission module is one of an NB-IoT module, a LoRaWAN module, and a Bluetooth module.

[0009] As a preferred solution of the automatic meter reading system for substation instruments described in the present invention, the meter reading photo analysis module calculates the meter reading based on the position of the meter pointer, including the following steps: calculating the coordinates of all meter pointers in the meter reading photo; determining whether the pointer positions of all meters have been calculated, and if so, continuing the calculation; otherwise ending; performing instrument pointer position analysis, using a binary tuple to represent the instrument pointer position, and obtaining meter pointer position binary data; and matching the instrument pointer position binary data with a meter reading database to obtain the meter reading.

[0010] As a preferred solution of the automatic meter reading system for substation instruments described in the present invention, the meter pointer position binary data is matched with the meter reading database, specifically, there is a one-to-one correspondence between the pointer position binary data of each meter and the meter reading database.

[0011] As a preferred scheme of the transformer substation on-site instrument automatic meter reading system, wherein: obtaining the instrument reading comprises the following steps: extracting all kinds of instrument pattern samples from the instrument database, and identifying the instrument intention by YOLO algorithm model training; SIFT is used to identify the photo and locate all the instrument patterns; the instrument frame in the photo is extracted and converted into a binary picture, the pointer position is found out by using the contour matching method, and the pointer picture is extracted to obtain the pointer position in all pictures; taking the pointer as the center point, moving 20 pixels upward as the first point and moving 40 pixels downward as the second point, and taking the coordinates of the two points as a binary tuple to represent the pointer position; the pointer position binary tuple data is matched with the instrument database one by one; and the data reading is matched according to the pointer position binary tuple.

[0012] As a preferred scheme of the transformer substation on-site instrument automatic meter reading system, wherein: after obtaining the instrument reading, a transformer substation meter reading result report is generated; the transformer substation meter reading result report comprises a transformer substation meter reading result table, a transformer substation on-site instrument meter reading report and a transformer substation on-site instrument manual meter reading report.

[0013] As a preferred scheme of the transformer substation on-site instrument automatic meter reading system, wherein: the transformer substation meter reading result table is a report generated by the automatic meter reading module for the reading and standard value of all instruments in each site, and the abnormal situation is marked for manual confirmation and processing; the transformer substation on-site instrument meter reading report is a blank report generated according to the specific instrument types and quantities of the meter reading site of the transformer substation, and the report is manually confirmed and processed; and the transformer substation on-site instrument manual meter reading report: according to the manual meter reading condition of the transformer substation, the meter reading personnel generate the instrument data report of the site by one-key confirmation of the operation and maintenance personnel on the basis of the manual meter reading data, so as to confirm the meter reading condition of the instrument of the site.

[0014] To further solve the above technical problems, the present application provides the following technical scheme: a transformer substation on-site instrument automatic meter reading method, comprising: a transformer substation on-site instrument meter reading software establishes network communication with a master control room computer through a mobile terminal, takes a photo of a field instrument and transmits the photo to the master control room computer; YOLO algorithm is used to train and identify instrument samples, SIFT feature transformation method is used to locate the instrument, and the photo is converted into a binary picture; taking the pointer as the center point, moving up and down to determine two point coordinates to form a binary tuple, identifying the pointer position by contour matching and matching with the database to obtain the reading; the master control room computer generates a transformer substation meter reading result table according to the identification result, marks the abnormal situation and supports manual confirmation and processing; the system generates a blank report according to the instrument types of the site, and generates a data report by one-key confirmation of the operation and maintenance personnel based on the manual meter reading data.

[0015] A computer device includes a memory and a processor, wherein the memory stores a computer program, and is characterized in that when the processor executes the computer program, the steps of the automatic meter reading method for instruments in a substation are implemented.

[0016] A computer-readable storage medium stores a computer program thereon, wherein when the computer program is executed by a processor, the steps of the above-mentioned method for automatic meter reading of instruments in a substation are implemented.

[0017] The beneficial effects of the present invention are as follows: the present invention can replace manual on-site meter reading. By identifying on-site photos, it can automatically obtain the readings of instruments in the substation and generate instrument data reports, thereby reducing manual workload and improving meter reading efficiency and accuracy. The present invention can record on-site photos and calibration values ​​throughout the process for subsequent verification. RPA can automatically analyze on-site instrument photos, identify instrument data, and generate instrument data reports. For manual meter reading, automatic photography and data collection can be performed on-site. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is a schematic diagram of the overall process of an automatic meter reading method for substation instruments proposed by the present invention;

[0020] Figure 2 This is a computer equipment diagram of a method for automatic meter reading in a substation proposed by the present invention. DETAILED DESCRIPTION

[0021] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0023] Example 1, with reference to Figure 1 For an embodiment of the present application, an automatic meter reading system for substation internal instruments is provided.

[0024] Specifically, the meter reading work is completed by the substation internal instrument meter reading software, which includes an automatic meter reading module and a meter reading photo analysis module.

[0025] The automatic meter reading module includes the following steps in sequence:

[0026] S1: Establish network communication between the mobile terminal and the main control room computer to ensure accurate and secure data transmission between the mobile terminal and the main control room computer.

[0027] S2: The operation and maintenance personnel take photos of the field instruments using the mobile terminal to obtain meter reading photos, and then return the meter reading photos to the main control room computer.

[0028] S3: The main control room computer automatically downloads the meter reading photos and transmits them to the meter reading photo analysis module for calculation.

[0029] The present application introduces an automatic meter reading module and a meter reading photo analysis module to realize automatic meter reading and data reading of substation internal instruments, solving the problems of low efficiency, easy mistakes and missed data, and untimely identification of abnormal data in traditional manual meter reading. The traditional method relies on field personnel to record instrument readings one by one, which not only has a large workload, but also is prone to errors and omissions. To overcome these defects, the present application uses image recognition algorithms to automatically extract instrument pointer positions and reading data, directly obtains instrument readings through photo recognition and returns them in real time, greatly reducing manual intervention and on-site errors. This automatic identification mechanism effectively improves the accuracy and efficiency of the meter reading process, and is especially suitable for scenarios with a large number of instruments and complex types in substations, having significant technical advantages.

[0030] The meter reading photo analysis module processes the meter reading photos to obtain instrument readings, with the following specific steps:

[0031] A1: Initialize the meter reading photo and use the scale-invariant feature transformation method to locate the target and calculate the instruments contained in the meter reading photo.

[0032] A2: Extract the contour of the target and convert it to a binary image.

[0033] A3: Find the black and white boundary in the binary image and identify the edge coordinates of the instrument pointer through contour matching.

[0034] A4: Calculate the instrument reading pointed by the instrument pointer by finding the black and white boundary in the binary image.

[0035] Further, the mobile terminal communicates with the main control room computer through the network, so that the main control room computer receives the meter reading photos uploaded by the field operation and maintenance, and reports the recognized meter data to the main control room computer in real time.

[0036] Further, in the automatic meter reading module, the field photograph data is uploaded to the main control room computer through the wireless network.

[0037] The wireless transmission module is one of an NB-IoT module, a LoRaWAN module and a Bluetooth module.

[0038] Further, a recognition model adopting a YOLO algorithm is used to recognize the meter, and the recognition model is secondarily developed and trained on the local computer, so as to meet the accuracy requirement of application in field meter reading.

[0039] Further, the meter reading photo analysis module calculates the meter reading according to the position of the meter pointer, and the steps are as follows:

[0040] Calculate the coordinates of all meter pointers in the meter reading photo.

[0041] Judge whether the positions of all meter pointers in the photo are calculated, if yes, continue to calculate, otherwise, end.

[0042] Analyze the position of the meter pointer, and obtain the meter pointer position binary tuple data in a binary tuple mode.

[0043] Match the meter pointer position binary tuple data with the meter reading database to obtain the meter reading. It should be noted that the meter pointer position binary tuple data is matched with the meter reading database, and the specific scheme is that there is a one-to-one correspondence between the meter pointer position binary tuple data of each meter and the meter reading database.

[0044] The meter pointer position binary tuple data and the meter reading database have a one-to-one correspondence.

[0045] It should be noted that the position of the meter pointer is the center of the pointer, the first point is obtained by moving 20 pixels upward from the center of the pointer, the second point is obtained by moving 40 pixels downward from the center of the pointer, and the position of the meter pointer is represented in a binary tuple mode by taking the first point and the second point as the binary tuple.

[0046] Further, according to the recognized meter pointer image, the meter data is automatically read by matching the meter pointer position binary tuple data with the meter database, and the specific steps are as follows:

[0047] The meter contained in the photo: all kinds of meter pattern samples are extracted from the meter database, and the meter indication intention is recognized by training the YOLO algorithm model;

[0048] Use scale-invariant feature transform (SIFT) to identify photos and locate all instrument patterns;

[0049] Instrument pointer position: Frame the instrument in the photo, convert it into a binary image, use contour matching to find the pointer position, extract the pointer image, and obtain the pointer position in all images;

[0050] Pointer position analysis: With the pointer as the center point, move 20 pixels upward as the first point, and move 40 pixels downward as the second point. The coordinates of the two points are used as a binary tuple to represent the pointer position.

[0051] Pointer position binary matching: Match the pointer position binary data with the instrument database one by one;

[0052] Instrument reading: Match the corresponding data reading based on the pointer position binary.

[0053] Preferably, during the data analysis and matching process, the present invention utilizes a binary coordinate matching method for pointer positions to map the meter pointer position to a database of readings. This method introduces a coordinate parsing and recognition model for pointer position binary pairs to address the problem of inaccurate data recognition caused by slight pointer offsets in traditional methods. The binary matching strategy not only improves data matching accuracy but also effectively avoids the limitations of traditional image recognition, which is susceptible to lighting and angle effects. This matching method provides the necessary support for ensuring meter reading accuracy and is particularly suitable for high-precision substation meter reading scenarios, significantly improving data stability and consistency.

[0054] In a further embodiment of the present invention, the report of automatic meter reading of the instrument in the substation is as follows:

[0055] Substation meter reading result table: At each site, the automatic meter reading module generates a report on the readings and standard values ​​of all meters at the site. Based on data jumps, no readings, etc., abnormalities are marked and manually confirmed and processed.

[0056] Substation meter reading report: Generate a corresponding number of blank reports based on the specific types and quantities of meters at the substation meter reading sites, and process them manually for confirmation.

[0057] Manual meter reading report for substation instruments: Based on the manual meter reading situation of the substation, the meter reader will confirm the manual meter reading data with one click by the operation and maintenance personnel, and automatically generate the instrument data report of the station to confirm the meter reading situation of the station instrument.

[0058] Inspection process video: in the process of inspection, the automatic meter reading module records the whole process, including instrument identification, judgment and confirmation of data, as an auxiliary daily inspection.

[0059] The process of obtaining the substation meter reading result table is:

[0060] First, set the meter reading result table: this table can set the site that needs to be metered;

[0061] Get all the instruments of the site from the background;

[0062] For each type of instrument, set the corresponding verification standard value;

[0063] According to the instrument identification result, generate the data report of the corresponding instrument, and mark the data anomaly in the table;

[0064] Set the inspection process video: the purpose of this step is to save the current inspection record; According to the inspection situation, generate a two-dimensional code at the corresponding position, which can be opened by the inspection personnel using the mobile terminal to scan the corresponding position record.

[0065] The process of obtaining the automatic meter reading report of the instrument in the substation is:

[0066] First, get the instrument database from the background, analyze all the data in the database, and generate the corresponding instrument report;

[0067] The data in the table is only used as reference data, and the default value is;

[0068] The inspection personnel inspect the site and take pictures of the instrument identification with a mobile terminal, which is uploaded to the computer through a wireless network;

[0069] The computer receives the on-site data, analyzes it, and generates an instrument data report; It can mark the data change;

[0070] Generate inspection process video: the purpose of this step is to save the current inspection record; According to the inspection situation, generate a two-dimensional code at the corresponding position, which can be opened by the inspection personnel using the mobile terminal to scan the corresponding position record.

[0071] The process of obtaining the manual meter reading report of the instrument in the station is:

[0072] First, set the instrument data report;

[0073] Get the instrument database from the background, analyze the instrument information of the station, and generate the table of the station;

[0074] When manual meter reading, the meter reader records the on-site instrument data in the corresponding table of the station;

[0075] Through RPA, after completing manual meter reading, the operation and maintenance personnel manually press the completion button to automatically generate a manual meter reading data report for the station.

[0076] It should be noted that using RPA to automatically fill in manual meter reading data to generate manual meter reading data reports specifically includes the following steps:

[0077] When reading the meter manually, the meter reader records the field meter data in the corresponding table at the station;

[0078] After completing manual meter reading, the operation and maintenance personnel manually press the completion button to trigger RPA to automatically generate a manual meter reading data report for the station.

[0079] Preferably, the present invention utilizes a wireless network communication module and RPA (Robotic Process Automation) technology to optimize the real-time data transmission and automatic reporting of manual meter reading data. The wireless communication module enables real-time transmission of meter data to the main control computer, ensuring that the operation and maintenance center can monitor data status in real time and quickly respond to any anomalies. RPA technology allows for the automatic generation of relevant reports after manual meter reading data is confirmed, reducing the frequency of manual intervention and the risk of error. These improvements are particularly suitable for scenarios where power system inspections require real-time and efficient data processing, providing fundamental support for automated and digital inspections and significantly improving work efficiency and system reliability.

[0080] In a further embodiment of the present invention, abnormal conditions in the automatic meter reading report of the substation instrument include meter damage, calibration value mismatch and missing.

[0081] In summary, compared with the existing technology, the present invention can replace manual on-site meter reading. Through on-site photo recognition, it can automatically obtain the readings of instruments in the substation and generate instrument data reports, thereby reducing manual workload and improving meter reading efficiency and accuracy. The present invention can record on-site photos and calibration values ​​throughout the process for subsequent verification. Through RPA, on-site instrument photos can be automatically analyzed, instrument data can be identified, and instrument data reports can be generated. For manual meter reading, automatic photography and data collection can be performed on-site.

[0082] Embodiment 2, an embodiment of the present invention, provides a method for automatic meter reading in a substation, comprising:

[0083] This embodiment realizes the automatic meter reading function of the station meters by using two modules: the automatic meter reading module and the meter reading photo analysis module.

[0084] In order to ensure the real-time performance of field instrument data, the present invention uses a wireless network to ensure the real-time performance of data transmission.

[0085] In the automatic meter reading module, the application designs an algorithm for automatically identifying the data of the station instrument, so as to ensure that the instrument data can be correctly identified.

[0086] Through the automatic meter reading report of the station instrument (including the meter reading result table of the substation, the meter reading report of the station instrument of the substation and the meter reading report of the station instrument of the substation), the automatic meter reading of the station instrument data can be accurately and quickly realized; through the running state diagnosis of the station instrument, the management personnel can accurately and quickly understand the state of the station instrument.

[0087] The application can help the operation and maintenance team to change from 'finding problems by people' to 'finding people by problems', and realize accurate inspection.

[0088] The application realizes the automatic meter reading function of the station instrument by using the automatic meter reading module and the meter reading photo analysis module. After the field operation and maintenance personnel take photos of the field instrument, the photos are returned to the background computer through the wireless network. The computer automatically analyzes the photos and automatically generates the data report, and provides quick and convenient assistance for the instrument diagnosis of the field personnel through the background analysis. The manual meter reading data filling function is realized through the RPA technology, so that the field inspection personnel can accurately and quickly confirm the inspection content.

[0089] Embodiment 3, refer to Figure 2 As an embodiment of the application, which is different from the previous embodiment, the function, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solution of the application or the part of the technical solution which essentially contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions for making a computer device (which can be a personal computer, a server or a network device) execute all or part of the steps of the method described in various embodiments of the application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk and various program code storage media.

[0090] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0091] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0092] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0093] Example 4 is an embodiment of the present invention, which provides an automatic meter reading method for instruments in a substation. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0094] This example presents a systematic comparative analysis of theoretical experiments. Three typical substations were selected as test scenarios, each containing 30 different types of meters (including voltmeters, ammeters, and power meters). The experiment compared the traditional manual meter reading method with the automatic meter reading system of the present invention. Each method was tested five times, and evaluation was conducted based on four dimensions: meter reading accuracy, meter reading efficiency, labor cost, and anomaly recognition rate.

[0095] Theoretical experimental results demonstrate that the proposed automatic meter reading system significantly outperforms traditional manual meter reading methods across all metrics. By combining the YOLO algorithm with SIFT feature recognition, the system achieves a meter recognition accuracy of 98.7%, an 8.9 percentage point improvement over manual meter reading. The average single-station meter reading time is reduced from 47 minutes to 12 minutes, a 74.5% efficiency improvement. Furthermore, the system achieves a 96.3% recognition rate for anomalies, compared to only 85.1% for manual meter reading. Detailed experimental data statistics are provided below:

[0096] Table 1 Experimental data statistics

[0097] Test indicators Traditional manual meter reading The present invention Improvement Meter reading accuracy (%) 89.8 98.7 8.9 Average single-station meter reading time (minutes) 47 12 74.5％ Single station labor cost (man-hours) 1.5 0.3 80％ Abnormal recognition rate (%) 85.1 96.3 11.2 Data upload timeliness rate (%) 76.5 99.8 23.3 Meter reading missed rate (%) 4.2 0.3 92.9％ System operation and maintenance cost (yuan / month / station) 0 180 - Data traceability completeness (%) 82.3 100 17.7

[0098] As shown in Table 1, the present invention has achieved significant improvements in various key performance indicators: the meter reading accuracy rate increased from 89.8% to 98.7%, indicating that the recognition scheme of the present invention combined with the YOLO algorithm of the SIFT feature transformation has high reliability; the average single-station meter reading time was significantly reduced from 47 minutes to 12 minutes, the efficiency was improved by 74.5%, and the labor cost was reduced by 80%, which fully verified the automation advantage of the present invention; in terms of abnormal identification, the recognition rate of the present invention reached 96.3%, an increase of 11.2 percentage points over the manual method, and the timely data upload rate was increased to 99.8%, and the missed reading rate was only 0.3%, a significant improvement over the manual method of 4.2%; although the system requires an operation and maintenance cost of 180 yuan per station per month, considering the significant savings in labor costs (reduced by 80%) and the improvement in data traceability integrity (reaching 100%), the investment is highly economical. These data fully confirm that the present invention has significant advantages in improving the efficiency, accuracy and reliability of substation meter reading.

[0099] In summary, the automatic identification system of the present invention can automatically obtain the instrument data in the station, automatically generate instrument data reports in the background, and mark out data jumps, no readings, etc., and at the same time, mark the abnormal conditions of the meter. This automatic meter reading method can help on-site operation and maintenance personnel accurately obtain the instrument data in the station, help on-site inspection personnel accurately grasp the changes in instrument data and the operating status of the meter, and use the background and on-site data for comparison and algorithm verification to provide rapid decision support for on-site operation and maintenance personnel. When the automatic meter reading module and the instrument operating status diagnosis are completed, the corresponding table can be automatically generated. In the diagnosis of the substation operating status, the timely prompt of abnormal points can accurately guide the on-site work and improve work efficiency and work accuracy.

[0100] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An automatic meter reading system for instruments in a substation, characterized in that: include: The meter reading work is completed by the substation station meter reading software, which includes an automatic meter reading module and a meter reading photo analysis module; The automatic meter reading module is used to establish network communication with the main control room computer using a mobile terminal, take a photo of the on-site instrument through the mobile terminal to obtain a meter reading photo, and transmit the meter reading photo back to the main control room computer. The main control room computer automatically downloads the meter reading photo and transmits it to the meter reading photo analysis module for calculation; The meter reading photo analysis module is used to initialize the meter reading photo, locate the target using a scale-invariant feature transformation and calculate the meters included in the meter reading photo, extract the target contour and convert it into a binary image, find the black and white boundary in the binary image, identify the edge coordinates of the meter pointer through contour matching, and calculate the meter reading pointed to by the meter pointer by finding the black and white boundary in the binary image; The meter reading photo analysis module calculates the meter reading based on the position of the meter pointer, including the following steps: Calculating the coordinates of all meter pointers in the meter reading photo; Determine whether the pointer positions of all instruments have been calculated. If so, continue the calculation; otherwise, end. Perform instrument pointer position analysis, use a binary tuple method to represent the instrument pointer position, and obtain binary tuple data of the instrument pointer position; Matching the meter pointer position binary data with the meter reading database to obtain the meter reading; The instrument pointer position binary data is matched with the instrument reading database, specifically, there is a one-to-one correspondence between the pointer position binary data of each instrument and the instrument reading database; Obtaining meter readings involves the following steps: Extract all kinds of instrument pattern samples from the instrument database and use the YOLO algorithm model to train and identify instrument diagrams; Use scale-invariant feature transform (SIFT) to identify photos and locate all instrument patterns; Frame the instrument in the photo, convert it into a binary image, use contour matching to find the pointer position, extract the pointer image, and obtain the pointer position in all images; With the pointer as the center point, move 20 pixels upward as the first point, and move 40 pixels downward as the second point. The coordinates of the two points are used as a tuple to represent the pointer position. Match the pointer position binary data with the instrument database one by one; Match the corresponding data readings according to the pointer position binary; After obtaining the meter reading, a substation meter reading result report is generated; The substation meter reading result report includes a substation meter reading result table, a substation in-station instrument meter reading report, and a substation in-station instrument manual meter reading report; The substation meter reading result table is a report of the readings and standard values ​​of all meters in each station generated by the automatic meter reading module, with abnormal conditions marked for manual confirmation and processing; The substation meter reading report is based on the specific meter types and quantities of the substation meter reading sites, and generates a corresponding number of blank reports, which are manually confirmed and processed; The manual meter reading report of the substation instrument: based on the manual meter reading situation of the substation, the meter reader performs one-click confirmation by the operation and maintenance personnel on the basis of the manual meter reading data, and automatically generates the station instrument data report to confirm the meter reading situation of the station instrument.

2. The automatic meter reading system for substation instruments according to claim 1, characterized in that: The mobile terminal communicates with the main control room computer via the network, so that the main control room computer receives meter reading photos uploaded by on-site operation and maintenance, and reports the recognized meter data to the main control room computer in real time; Network communication uses a wireless transmission module, which is one of the NB-IoT module, LoRaWAN module, and Bluetooth module.

3. A method for automatic meter reading of substation instruments using the automatic meter reading system of any one of claims 1 to 2, characterized in that: include: The meter reading software for substation instruments establishes network communication with the computer in the main control room through the mobile terminal, takes photos of the on-site instruments and transmits them back to the computer in the main control room; Use the YOLO algorithm to train and identify instrument samples, use the SIFT feature transformation method to locate the instrument, and convert the photo into a binary image; The pointer is moved up and down with the center point to determine the coordinates of the two points to form a binary tuple. The pointer position is identified by contour matching and matched with the database to obtain the reading; The computer in the main control room generates a substation meter reading result table based on the identification results, marks abnormal situations and supports manual confirmation processing; The system generates blank reports based on the type of site meters, and can generate data reports based on manual meter reading data with one click by operation and maintenance personnel.

4. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for automatic meter reading of instruments in a substation according to claim 3 are implemented.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for automatic meter reading of instruments in a substation according to claim 3 are implemented.

Images